Index
DatasetService(interface)DeploymentResourcePoolService(interface)EndpointService(interface)EvaluationService(interface)ExtensionExecutionService(interface)ExtensionRegistryService(interface)FeatureOnlineStoreAdminService(interface)FeatureOnlineStoreService(interface)FeatureRegistryService(interface)FeaturestoreOnlineServingService(interface)FeaturestoreService(interface)GenAiCacheService(interface)GenAiTuningService(interface)IndexEndpointService(interface)IndexService(interface)JobService(interface)LlmUtilityService(interface)MatchService(interface)MetadataService(interface)MigrationService(interface)ModelGardenService(interface)ModelMonitoringService(interface)ModelService(interface)NotebookService(interface)PersistentResourceService(interface)PipelineService(interface)PredictionService(interface)ReasoningEngineExecutionService(interface)ReasoningEngineService(interface)ScheduleService(interface)SpecialistPoolService(interface)TensorboardService(interface)VertexRagDataService(interface)VertexRagService(interface)VizierService(interface)AcceleratorType(enum)AddContextArtifactsAndExecutionsRequest(message)AddContextArtifactsAndExecutionsResponse(message)AddContextChildrenRequest(message)AddContextChildrenResponse(message)AddExecutionEventsRequest(message)AddExecutionEventsResponse(message)AddTrialMeasurementRequest(message)Annotation(message)AnnotationSpec(message)ApiAuth(message)ApiAuth.ApiKeyConfig(message)Artifact(message)Artifact.State(enum)ArtifactTypeSchema(message)AssignNotebookRuntimeOperationMetadata(message)AssignNotebookRuntimeRequest(message)Attribution(message)AugmentPromptRequest(message)AugmentPromptRequest.Model(message)AugmentPromptResponse(message)AuthConfig(message)AuthConfig.ApiKeyConfig(message)AuthConfig.GoogleServiceAccountConfig(message)AuthConfig.HttpBasicAuthConfig(message)AuthConfig.OauthConfig(message)AuthConfig.OidcConfig(message)AuthType(enum)AutomaticResources(message)AutoraterConfig(message)AutoscalingMetricSpec(message)AvroSource(message)BatchCancelPipelineJobsOperationMetadata(message)BatchCancelPipelineJobsRequest(message)BatchCancelPipelineJobsResponse(message)BatchCreateFeaturesOperationMetadata(message)BatchCreateFeaturesRequest(message)BatchCreateFeaturesResponse(message)BatchCreateTensorboardRunsRequest(message)BatchCreateTensorboardRunsResponse(message)BatchCreateTensorboardTimeSeriesRequest(message)BatchCreateTensorboardTimeSeriesResponse(message)BatchDedicatedResources(message)BatchDeletePipelineJobsRequest(message)BatchDeletePipelineJobsResponse(message)BatchImportEvaluatedAnnotationsRequest(message)BatchImportEvaluatedAnnotationsResponse(message)BatchImportModelEvaluationSlicesRequest(message)BatchImportModelEvaluationSlicesResponse(message)BatchMigrateResourcesOperationMetadata(message)BatchMigrateResourcesOperationMetadata.PartialResult(message)BatchMigrateResourcesRequest(message)BatchMigrateResourcesResponse(message)BatchPredictionJob(message)BatchPredictionJob.InputConfig(message)BatchPredictionJob.InstanceConfig(message)BatchPredictionJob.OutputConfig(message)BatchPredictionJob.OutputInfo(message)BatchReadFeatureValuesOperationMetadata(message)BatchReadFeatureValuesRequest(message)BatchReadFeatureValuesRequest.EntityTypeSpec(message)BatchReadFeatureValuesRequest.PassThroughField(message)BatchReadFeatureValuesResponse(message)BatchReadTensorboardTimeSeriesDataRequest(message)BatchReadTensorboardTimeSeriesDataResponse(message)BigQueryDestination(message)BigQuerySource(message)BleuInput(message)BleuInstance(message)BleuMetricValue(message)BleuResults(message)BleuSpec(message)Blob(message)BlurBaselineConfig(message)BoolArray(message)CachedContent(message)CachedContent.UsageMetadata(message)CancelBatchPredictionJobRequest(message)CancelCustomJobRequest(message)CancelHyperparameterTuningJobRequest(message)CancelPipelineJobRequest(message)CancelTrainingPipelineRequest(message)CancelTuningJobRequest(message)Candidate(message)Candidate.FinishReason(enum)ChatCompletionsRequest(message)CheckTrialEarlyStoppingStateMetatdata(message)CheckTrialEarlyStoppingStateRequest(message)CheckTrialEarlyStoppingStateResponse(message)Citation(message)CitationMetadata(message)Claim(message)ClientConnectionConfig(message)CodeExecutionResult(message)CodeExecutionResult.Outcome(enum)CoherenceInput(message)CoherenceInstance(message)CoherenceResult(message)CoherenceSpec(message)CometInput(message)CometInstance(message)CometResult(message)CometSpec(message)CometSpec.CometVersion(enum)CompleteTrialRequest(message)CompletionStats(message)ComputeTokensRequest(message)ComputeTokensResponse(message)ContainerRegistryDestination(message)ContainerSpec(message)Content(message)Context(message)CopyModelOperationMetadata(message)CopyModelRequest(message)CopyModelResponse(message)CorpusStatus(message)CorpusStatus.State(enum)CorroborateContentRequest(message)CorroborateContentRequest.Parameters(message)CorroborateContentResponse(message)CountTokensRequest(message)CountTokensResponse(message)CreateArtifactRequest(message)CreateBatchPredictionJobRequest(message)CreateCachedContentRequest(message)CreateContextRequest(message)CreateCustomJobRequest(message)CreateDatasetOperationMetadata(message)CreateDatasetRequest(message)CreateDatasetVersionOperationMetadata(message)CreateDatasetVersionRequest(message)CreateDeploymentResourcePoolOperationMetadata(message)CreateDeploymentResourcePoolRequest(message)CreateEndpointOperationMetadata(message)CreateEndpointRequest(message)CreateEntityTypeOperationMetadata(message)CreateEntityTypeRequest(message)CreateExecutionRequest(message)CreateExtensionControllerOperationMetadata(message)CreateFeatureGroupOperationMetadata(message)CreateFeatureGroupRequest(message)CreateFeatureMonitorJobRequest(message)CreateFeatureMonitorOperationMetadata(message)CreateFeatureMonitorRequest(message)CreateFeatureOnlineStoreOperationMetadata(message)CreateFeatureOnlineStoreRequest(message)CreateFeatureOperationMetadata(message)CreateFeatureRequest(message)CreateFeatureViewOperationMetadata(message)CreateFeatureViewRequest(message)CreateFeaturestoreOperationMetadata(message)CreateFeaturestoreRequest(message)CreateHyperparameterTuningJobRequest(message)CreateIndexEndpointOperationMetadata(message)CreateIndexEndpointRequest(message)CreateIndexOperationMetadata(message)CreateIndexRequest(message)CreateMetadataSchemaRequest(message)CreateMetadataStoreOperationMetadata(message)CreateMetadataStoreRequest(message)CreateModelDeploymentMonitoringJobRequest(message)CreateModelMonitorOperationMetadata(message)CreateModelMonitorRequest(message)CreateModelMonitoringJobRequest(message)CreateNotebookExecutionJobOperationMetadata(message)CreateNotebookExecutionJobRequest(message)CreateNotebookRuntimeTemplateOperationMetadata(message)CreateNotebookRuntimeTemplateRequest(message)CreatePersistentResourceOperationMetadata(message)CreatePersistentResourceRequest(message)CreatePipelineJobRequest(message)CreateRagCorpusOperationMetadata(message)CreateRagCorpusRequest(message)CreateReasoningEngineOperationMetadata(message)CreateReasoningEngineRequest(message)CreateRegistryFeatureOperationMetadata(message)CreateScheduleRequest(message)CreateSolverOperationMetadata(message)CreateSpecialistPoolOperationMetadata(message)CreateSpecialistPoolRequest(message)CreateStudyRequest(message)CreateTensorboardExperimentRequest(message)CreateTensorboardOperationMetadata(message)CreateTensorboardRequest(message)CreateTensorboardRunRequest(message)CreateTensorboardTimeSeriesRequest(message)CreateTrainingPipelineRequest(message)CreateTrialRequest(message)CreateTuningJobRequest(message)CsvDestination(message)CsvSource(message)CustomJob(message)CustomJobSpec(message)DataItem(message)DataItemView(message)Dataset(message)DatasetDistribution(message)DatasetDistribution.DistributionBucket(message)DatasetStats(message)DatasetVersion(message)DedicatedResources(message)DeleteArtifactRequest(message)DeleteBatchPredictionJobRequest(message)DeleteCachedContentRequest(message)DeleteContextRequest(message)DeleteCustomJobRequest(message)DeleteDatasetRequest(message)DeleteDatasetVersionRequest(message)DeleteDeploymentResourcePoolRequest(message)DeleteEndpointRequest(message)DeleteEntityTypeRequest(message)DeleteExecutionRequest(message)DeleteExtensionRequest(message)DeleteFeatureGroupRequest(message)DeleteFeatureMonitorRequest(message)DeleteFeatureOnlineStoreRequest(message)DeleteFeatureRequest(message)DeleteFeatureValuesOperationMetadata(message)DeleteFeatureValuesRequest(message)DeleteFeatureValuesRequest.SelectEntity(message)DeleteFeatureValuesRequest.SelectTimeRangeAndFeature(message)DeleteFeatureValuesResponse(message)DeleteFeatureValuesResponse.SelectEntity(message)DeleteFeatureValuesResponse.SelectTimeRangeAndFeature(message)DeleteFeatureViewRequest(message)DeleteFeaturestoreRequest(message)DeleteHyperparameterTuningJobRequest(message)DeleteIndexEndpointRequest(message)DeleteIndexRequest(message)DeleteMetadataStoreOperationMetadata(message)DeleteMetadataStoreRequest(message)DeleteModelDeploymentMonitoringJobRequest(message)DeleteModelMonitorRequest(message)DeleteModelMonitoringJobRequest(message)DeleteModelRequest(message)DeleteModelVersionRequest(message)DeleteNotebookExecutionJobRequest(message)DeleteNotebookRuntimeRequest(message)DeleteNotebookRuntimeTemplateRequest(message)DeleteOperationMetadata(message)DeletePersistentResourceRequest(message)DeletePipelineJobRequest(message)DeleteRagCorpusRequest(message)DeleteRagFileRequest(message)DeleteReasoningEngineRequest(message)DeleteSavedQueryRequest(message)DeleteScheduleRequest(message)DeleteSpecialistPoolRequest(message)DeleteStudyRequest(message)DeleteTensorboardExperimentRequest(message)DeleteTensorboardRequest(message)DeleteTensorboardRunRequest(message)DeleteTensorboardTimeSeriesRequest(message)DeleteTrainingPipelineRequest(message)DeleteTrialRequest(message)DeployIndexOperationMetadata(message)DeployIndexRequest(message)DeployIndexResponse(message)DeployModelOperationMetadata(message)DeployModelRequest(message)DeployModelResponse(message)DeployOperationMetadata(message)DeployPublisherModelOperationMetadata(message)DeployPublisherModelRequest(message)DeployPublisherModelResponse(message)DeployRequest(message)DeployRequest.DeployConfig(message)DeployRequest.EndpointConfig(message)DeployRequest.ModelConfig(message)DeployResponse(message)DeploySolverOperationMetadata(message)DeployedIndex(message)DeployedIndexAuthConfig(message)DeployedIndexAuthConfig.AuthProvider(message)DeployedIndexRef(message)DeployedModel(message)DeployedModel.Status(message)DeployedModelRef(message)DeploymentResourcePool(message)DestinationFeatureSetting(message)DirectPredictRequest(message)DirectPredictResponse(message)DirectRawPredictRequest(message)DirectRawPredictResponse(message)DirectUploadSource(message)DiskSpec(message)DistillationDataStats(message)DistillationHyperParameters(message)DistillationSpec(message)DoubleArray(message)DynamicRetrievalConfig(message)DynamicRetrievalConfig.Mode(enum)EncryptionSpec(message)Endpoint(message)EntityIdSelector(message)EntityType(message)EnvVar(message)ErrorAnalysisAnnotation(message)ErrorAnalysisAnnotation.AttributedItem(message)ErrorAnalysisAnnotation.QueryType(enum)EvaluateDatasetOperationMetadata(message)EvaluateDatasetRequest(message)EvaluateDatasetResponse(message)EvaluateInstancesRequest(message)EvaluateInstancesResponse(message)EvaluatedAnnotation(message)EvaluatedAnnotation.EvaluatedAnnotationType(enum)EvaluatedAnnotationExplanation(message)EvaluationDataset(message)Event(message)Event.Type(enum)ExactMatchInput(message)ExactMatchInstance(message)ExactMatchMetricValue(message)ExactMatchResults(message)ExactMatchSpec(message)Examples(message)Examples.ExampleGcsSource(message)Examples.ExampleGcsSource.DataFormat(enum)ExamplesOverride(message)ExamplesOverride.DataFormat(enum)ExamplesRestrictionsNamespace(message)ExecutableCode(message)ExecutableCode.Language(enum)ExecuteExtensionRequest(message)ExecuteExtensionResponse(message)Execution(message)Execution.State(enum)ExplainRequest(message)ExplainResponse(message)ExplainResponse.ConcurrentExplanation(message)Explanation(message)ExplanationMetadata(message)ExplanationMetadata.InputMetadata(message)ExplanationMetadata.InputMetadata.Encoding(enum)ExplanationMetadata.InputMetadata.FeatureValueDomain(message)ExplanationMetadata.InputMetadata.Visualization(message)ExplanationMetadata.InputMetadata.Visualization.ColorMap(enum)ExplanationMetadata.InputMetadata.Visualization.OverlayType(enum)ExplanationMetadata.InputMetadata.Visualization.Polarity(enum)ExplanationMetadata.InputMetadata.Visualization.Type(enum)ExplanationMetadata.OutputMetadata(message)ExplanationMetadataOverride(message)ExplanationMetadataOverride.InputMetadataOverride(message)ExplanationParameters(message)ExplanationSpec(message)ExplanationSpecOverride(message)ExportDataConfig(message)ExportDataOperationMetadata(message)ExportDataRequest(message)ExportDataResponse(message)ExportFeatureValuesOperationMetadata(message)ExportFeatureValuesRequest(message)ExportFeatureValuesRequest.FullExport(message)ExportFeatureValuesRequest.SnapshotExport(message)ExportFeatureValuesResponse(message)ExportFractionSplit(message)ExportModelOperationMetadata(message)ExportModelOperationMetadata.OutputInfo(message)ExportModelRequest(message)ExportModelRequest.OutputConfig(message)ExportModelResponse(message)ExportPublisherModelResponse(message)ExportTensorboardTimeSeriesDataRequest(message)ExportTensorboardTimeSeriesDataResponse(message)Extension(message)ExtensionManifest(message)ExtensionManifest.ApiSpec(message)ExtensionOperation(message)ExtensionPrivateServiceConnectConfig(message)Fact(message)FasterDeploymentConfig(message)Feature(message)Feature.MonitoringStatsAnomaly(message)Feature.MonitoringStatsAnomaly.Objective(enum)Feature.ValueType(enum)FeatureGroup(message)FeatureGroup.BigQuery(message)FeatureGroup.BigQuery.TimeSeries(message)FeatureGroup.ServiceAgentType(enum)FeatureMonitor(message)FeatureMonitorJob(message)FeatureMonitorJob.FeatureMonitorJobTrigger(enum)FeatureMonitorJob.JobSummary(message)FeatureNoiseSigma(message)FeatureNoiseSigma.NoiseSigmaForFeature(message)FeatureOnlineStore(message)FeatureOnlineStore.Bigtable(message)FeatureOnlineStore.Bigtable.AutoScaling(message)FeatureOnlineStore.DedicatedServingEndpoint(message)FeatureOnlineStore.EmbeddingManagement(message) (deprecated)FeatureOnlineStore.Optimized(message)FeatureOnlineStore.State(enum)FeatureSelectionConfig(message)FeatureSelectionConfig.FeatureConfig(message)FeatureSelector(message)FeatureStatsAndAnomaly(message)FeatureStatsAndAnomalySpec(message)FeatureStatsAnomaly(message)FeatureValue(message)FeatureValue.Metadata(message)FeatureValueDestination(message)FeatureValueList(message)FeatureView(message)FeatureView.BigQuerySource(message)FeatureView.FeatureRegistrySource(message)FeatureView.FeatureRegistrySource.FeatureGroup(message)FeatureView.IndexConfig(message)FeatureView.IndexConfig.BruteForceConfig(message)FeatureView.IndexConfig.DistanceMeasureType(enum)FeatureView.IndexConfig.TreeAHConfig(message)FeatureView.OptimizedConfig(message)FeatureView.ServiceAgentType(enum)FeatureView.SyncConfig(message)FeatureView.VectorSearchConfig(message) (deprecated)FeatureView.VectorSearchConfig.BruteForceConfig(message)FeatureView.VectorSearchConfig.DistanceMeasureType(enum)FeatureView.VectorSearchConfig.TreeAHConfig(message)FeatureView.VertexRagSource(message)FeatureViewDataFormat(enum)FeatureViewDataKey(message)FeatureViewDataKey.CompositeKey(message)FeatureViewSync(message)FeatureViewSync.SyncSummary(message)Featurestore(message)Featurestore.OnlineServingConfig(message)Featurestore.OnlineServingConfig.Scaling(message)Featurestore.State(enum)FeaturestoreMonitoringConfig(message)FeaturestoreMonitoringConfig.ImportFeaturesAnalysis(message)FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.Baseline(enum)FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.State(enum)FeaturestoreMonitoringConfig.SnapshotAnalysis(message)FeaturestoreMonitoringConfig.ThresholdConfig(message)FetchFeatureValuesRequest(message)FetchFeatureValuesRequest.Format(enum) (deprecated)FetchFeatureValuesResponse(message)FetchFeatureValuesResponse.FeatureNameValuePairList(message)FetchFeatureValuesResponse.FeatureNameValuePairList.FeatureNameValuePair(message)FileData(message)FileStatus(message)FileStatus.State(enum)FilterSplit(message)FluencyInput(message)FluencyInstance(message)FluencyResult(message)FluencySpec(message)FractionSplit(message)FulfillmentInput(message)FulfillmentInstance(message)FulfillmentResult(message)FulfillmentSpec(message)FunctionCall(message)FunctionCallingConfig(message)FunctionCallingConfig.Mode(enum)FunctionDeclaration(message)FunctionResponse(message)GcsDestination(message)GcsSource(message)GenerateContentRequest(message)GenerateContentResponse(message)GenerateContentResponse.PromptFeedback(message)GenerateContentResponse.PromptFeedback.BlockedReason(enum)GenerateContentResponse.UsageMetadata(message)GenerateVideoResponse(message)GenerationConfig(message)GenerationConfig.MediaResolution(enum)GenerationConfig.Modality(enum)GenerationConfig.RoutingConfig(message)GenerationConfig.RoutingConfig.AutoRoutingMode(message)GenerationConfig.RoutingConfig.AutoRoutingMode.ModelRoutingPreference(enum)GenerationConfig.RoutingConfig.ManualRoutingMode(message)GenericOperationMetadata(message)GenieSource(message)GetAnnotationSpecRequest(message)GetArtifactRequest(message)GetBatchPredictionJobRequest(message)GetCachedContentRequest(message)GetContextRequest(message)GetCustomJobRequest(message)GetDatasetRequest(message)GetDatasetVersionRequest(message)GetDeploymentResourcePoolRequest(message)GetEndpointRequest(message)GetEntityTypeRequest(message)GetExecutionRequest(message)GetExtensionRequest(message)GetFeatureGroupRequest(message)GetFeatureMonitorJobRequest(message)GetFeatureMonitorRequest(message)GetFeatureOnlineStoreRequest(message)GetFeatureRequest(message)GetFeatureViewRequest(message)GetFeatureViewSyncRequest(message)GetFeaturestoreRequest(message)GetHyperparameterTuningJobRequest(message)GetIndexEndpointRequest(message)GetIndexRequest(message)GetMetadataSchemaRequest(message)GetMetadataStoreRequest(message)GetModelDeploymentMonitoringJobRequest(message)GetModelEvaluationRequest(message)GetModelEvaluationSliceRequest(message)GetModelMonitorRequest(message)GetModelMonitoringJobRequest(message)GetModelRequest(message)GetNotebookExecutionJobRequest(message)GetNotebookRuntimeRequest(message)GetNotebookRuntimeTemplateRequest(message)GetPersistentResourceRequest(message)GetPipelineJobRequest(message)GetPublisherModelRequest(message)GetRagCorpusRequest(message)GetRagFileRequest(message)GetReasoningEngineRequest(message)GetScheduleRequest(message)GetSpecialistPoolRequest(message)GetStudyRequest(message)GetTensorboardExperimentRequest(message)GetTensorboardRequest(message)GetTensorboardRunRequest(message)GetTensorboardTimeSeriesRequest(message)GetTrainingPipelineRequest(message)GetTrialRequest(message)GetTuningJobRequest(message)GoogleDriveSource(message)GoogleDriveSource.ResourceId(message)GoogleDriveSource.ResourceId.ResourceType(enum)GoogleSearchRetrieval(message)GroundednessInput(message)GroundednessInstance(message)GroundednessResult(message)GroundednessSpec(message)GroundingChunk(message)GroundingChunk.RetrievedContext(message)GroundingChunk.Web(message)GroundingMetadata(message)GroundingSupport(message)HarmCategory(enum)HttpElementLocation(enum)HyperparameterTuningJob(message)IdMatcher(message)ImportDataConfig(message)ImportDataOperationMetadata(message)ImportDataRequest(message)ImportDataResponse(message)ImportExtensionOperationMetadata(message)ImportExtensionRequest(message)ImportFeatureValuesOperationMetadata(message)ImportFeatureValuesRequest(message)ImportFeatureValuesRequest.FeatureSpec(message)ImportFeatureValuesResponse(message)ImportModelEvaluationRequest(message)ImportRagFilesConfig(message)ImportRagFilesOperationMetadata(message)ImportRagFilesRequest(message)ImportRagFilesResponse(message)Index(message)Index.IndexUpdateMethod(enum)IndexDatapoint(message)IndexDatapoint.CrowdingTag(message)IndexDatapoint.NumericRestriction(message)IndexDatapoint.NumericRestriction.Operator(enum)IndexDatapoint.Restriction(message)IndexDatapoint.SparseEmbedding(message)IndexEndpoint(message)IndexPrivateEndpoints(message)IndexStats(message)InputDataConfig(message)Int64Array(message)IntegratedGradientsAttribution(message)JiraSource(message)JiraSource.JiraQueries(message)JobState(enum)LargeModelReference(message)LineageSubgraph(message)ListAnnotationsRequest(message)ListAnnotationsResponse(message)ListArtifactsRequest(message)ListArtifactsResponse(message)ListBatchPredictionJobsRequest(message)ListBatchPredictionJobsResponse(message)ListCachedContentsRequest(message)ListCachedContentsResponse(message)ListContextsRequest(message)ListContextsResponse(message)ListCustomJobsRequest(message)ListCustomJobsResponse(message)ListDataItemsRequest(message)ListDataItemsResponse(message)ListDatasetVersionsRequest(message)ListDatasetVersionsResponse(message)ListDatasetsRequest(message)ListDatasetsResponse(message)ListDeploymentResourcePoolsRequest(message)ListDeploymentResourcePoolsResponse(message)ListEndpointsRequest(message)ListEndpointsResponse(message)ListEntityTypesRequest(message)ListEntityTypesResponse(message)ListExecutionsRequest(message)ListExecutionsResponse(message)ListExtensionsRequest(message)ListExtensionsResponse(message)ListFeatureGroupsRequest(message)ListFeatureGroupsResponse(message)ListFeatureMonitorJobsRequest(message)ListFeatureMonitorJobsResponse(message)ListFeatureMonitorsRequest(message)ListFeatureMonitorsResponse(message)ListFeatureOnlineStoresRequest(message)ListFeatureOnlineStoresResponse(message)ListFeatureViewSyncsRequest(message)ListFeatureViewSyncsResponse(message)ListFeatureViewsRequest(message)ListFeatureViewsResponse(message)ListFeaturesRequest(message)ListFeaturesResponse(message)ListFeaturestoresRequest(message)ListFeaturestoresResponse(message)ListHyperparameterTuningJobsRequest(message)ListHyperparameterTuningJobsResponse(message)ListIndexEndpointsRequest(message)ListIndexEndpointsResponse(message)ListIndexesRequest(message)ListIndexesResponse(message)ListMetadataSchemasRequest(message)ListMetadataSchemasResponse(message)ListMetadataStoresRequest(message)ListMetadataStoresResponse(message)ListModelDeploymentMonitoringJobsRequest(message)ListModelDeploymentMonitoringJobsResponse(message)ListModelEvaluationSlicesRequest(message)ListModelEvaluationSlicesResponse(message)ListModelEvaluationsRequest(message)ListModelEvaluationsResponse(message)ListModelMonitoringJobsRequest(message)ListModelMonitoringJobsResponse(message)ListModelMonitorsRequest(message)ListModelMonitorsResponse(message)ListModelVersionCheckpointsRequest(message)ListModelVersionCheckpointsResponse(message)ListModelVersionsRequest(message)ListModelVersionsResponse(message)ListModelsRequest(message)ListModelsResponse(message)ListNotebookExecutionJobsRequest(message)ListNotebookExecutionJobsResponse(message)ListNotebookRuntimeTemplatesRequest(message)ListNotebookRuntimeTemplatesResponse(message)ListNotebookRuntimesRequest(message)ListNotebookRuntimesResponse(message)ListOptimalTrialsRequest(message)ListOptimalTrialsResponse(message)ListPersistentResourcesRequest(message)ListPersistentResourcesResponse(message)ListPipelineJobsRequest(message)ListPipelineJobsResponse(message)ListPublisherModelsRequest(message)ListPublisherModelsResponse(message)ListRagCorporaRequest(message)ListRagCorporaResponse(message)ListRagFilesRequest(message)ListRagFilesResponse(message)ListReasoningEnginesRequest(message)ListReasoningEnginesResponse(message)ListSavedQueriesRequest(message)ListSavedQueriesResponse(message)ListSchedulesRequest(message)ListSchedulesResponse(message)ListSpecialistPoolsRequest(message)ListSpecialistPoolsResponse(message)ListStudiesRequest(message)ListStudiesResponse(message)ListTensorboardExperimentsRequest(message)ListTensorboardExperimentsResponse(message)ListTensorboardRunsRequest(message)ListTensorboardRunsResponse(message)ListTensorboardTimeSeriesRequest(message)ListTensorboardTimeSeriesResponse(message)ListTensorboardsRequest(message)ListTensorboardsResponse(message)ListTrainingPipelinesRequest(message)ListTrainingPipelinesResponse(message)ListTrialsRequest(message)ListTrialsResponse(message)ListTuningJobsRequest(message)ListTuningJobsResponse(message)LogprobsResult(message)LogprobsResult.Candidate(message)LogprobsResult.TopCandidates(message)LookupStudyRequest(message)MachineSpec(message)ManualBatchTuningParameters(message)Measurement(message)Measurement.Metric(message)MergeVersionAliasesRequest(message)MetadataSchema(message)MetadataSchema.MetadataSchemaType(enum)MetadataStore(message)MetadataStore.DataplexConfig(message)MetadataStore.MetadataStoreState(message)Metric(message)Metric.AggregationMetric(enum)MetricxInput(message)MetricxInstance(message)MetricxResult(message)MetricxSpec(message)MetricxSpec.MetricxVersion(enum)MigratableResource(message)MigratableResource.AutomlDataset(message)MigratableResource.AutomlModel(message)MigratableResource.DataLabelingDataset(message)MigratableResource.DataLabelingDataset.DataLabelingAnnotatedDataset(message)MigratableResource.MlEngineModelVersion(message)MigrateResourceRequest(message)MigrateResourceRequest.MigrateAutomlDatasetConfig(message)MigrateResourceRequest.MigrateAutomlModelConfig(message)MigrateResourceRequest.MigrateDataLabelingDatasetConfig(message)MigrateResourceRequest.MigrateDataLabelingDatasetConfig.MigrateDataLabelingAnnotatedDatasetConfig(message)MigrateResourceRequest.MigrateMlEngineModelVersionConfig(message)MigrateResourceResponse(message)Modality(enum)ModalityTokenCount(message)Model(message)Model.BaseModelSource(message)Model.DeploymentResourcesType(enum)Model.ExportFormat(message)Model.ExportFormat.ExportableContent(enum)Model.OriginalModelInfo(message)ModelContainerSpec(message)ModelDeploymentMonitoringBigQueryTable(message)ModelDeploymentMonitoringBigQueryTable.LogSource(enum)ModelDeploymentMonitoringBigQueryTable.LogType(enum)ModelDeploymentMonitoringJob(message)ModelDeploymentMonitoringJob.LatestMonitoringPipelineMetadata(message)ModelDeploymentMonitoringJob.MonitoringScheduleState(enum)ModelDeploymentMonitoringObjectiveConfig(message)ModelDeploymentMonitoringObjectiveType(enum)ModelDeploymentMonitoringScheduleConfig(message)ModelEvaluation(message)ModelEvaluation.BiasConfig(message)ModelEvaluation.ModelEvaluationExplanationSpec(message)ModelEvaluationSlice(message)ModelEvaluationSlice.Slice(message)ModelEvaluationSlice.Slice.SliceSpec(message)ModelEvaluationSlice.Slice.SliceSpec.Range(message)ModelEvaluationSlice.Slice.SliceSpec.SliceConfig(message)ModelEvaluationSlice.Slice.SliceSpec.Value(message)ModelExplanation(message)ModelGardenSource(message)ModelMonitor(message)ModelMonitor.ModelMonitoringTarget(message)ModelMonitor.ModelMonitoringTarget.VertexModelSource(message)ModelMonitoringAlert(message)ModelMonitoringAlertCondition(message)ModelMonitoringAlertConfig(message)ModelMonitoringAlertConfig.EmailAlertConfig(message)ModelMonitoringAnomaly(message)ModelMonitoringAnomaly.TabularAnomaly(message)ModelMonitoringConfig(message)ModelMonitoringInput(message)ModelMonitoringInput.BatchPredictionOutput(message)ModelMonitoringInput.ModelMonitoringDataset(message)ModelMonitoringInput.ModelMonitoringDataset.ModelMonitoringBigQuerySource(message)ModelMonitoringInput.ModelMonitoringDataset.ModelMonitoringGcsSource(message)ModelMonitoringInput.ModelMonitoringDataset.ModelMonitoringGcsSource.DataFormat(enum)ModelMonitoringInput.TimeOffset(message)ModelMonitoringInput.VertexEndpointLogs(message)ModelMonitoringJob(message)ModelMonitoringJobExecutionDetail(message)ModelMonitoringJobExecutionDetail.ProcessedDataset(message)ModelMonitoringNotificationSpec(message)ModelMonitoringNotificationSpec.EmailConfig(message)ModelMonitoringNotificationSpec.NotificationChannelConfig(message)ModelMonitoringObjectiveConfig(message)ModelMonitoringObjectiveConfig.ExplanationConfig(message)ModelMonitoringObjectiveConfig.ExplanationConfig.ExplanationBaseline(message)ModelMonitoringObjectiveConfig.ExplanationConfig.ExplanationBaseline.PredictionFormat(enum)ModelMonitoringObjectiveConfig.PredictionDriftDetectionConfig(message)ModelMonitoringObjectiveConfig.TrainingDataset(message)ModelMonitoringObjectiveConfig.TrainingPredictionSkewDetectionConfig(message)ModelMonitoringObjectiveSpec(message)ModelMonitoringObjectiveSpec.DataDriftSpec(message)ModelMonitoringObjectiveSpec.FeatureAttributionSpec(message)ModelMonitoringObjectiveSpec.TabularObjective(message)ModelMonitoringOutputSpec(message)ModelMonitoringSchema(message)ModelMonitoringSchema.FieldSchema(message)ModelMonitoringSpec(message)ModelMonitoringStats(message)ModelMonitoringStatsAnomalies(message)ModelMonitoringStatsAnomalies.FeatureHistoricStatsAnomalies(message)ModelMonitoringStatsDataPoint(message)ModelMonitoringStatsDataPoint.TypedValue(message)ModelMonitoringStatsDataPoint.TypedValue.DistributionDataValue(message)ModelMonitoringTabularStats(message)ModelSourceInfo(message)ModelSourceInfo.ModelSourceType(enum)ModelVersionCheckpoint(message)MutateDeployedIndexOperationMetadata(message)MutateDeployedIndexRequest(message)MutateDeployedIndexResponse(message)MutateDeployedModelOperationMetadata(message)MutateDeployedModelRequest(message)MutateDeployedModelResponse(message)NearestNeighborQuery(message)NearestNeighborQuery.Embedding(message)NearestNeighborQuery.NumericFilter(message)NearestNeighborQuery.NumericFilter.Operator(enum)NearestNeighborQuery.Parameters(message)NearestNeighborQuery.StringFilter(message)NearestNeighborSearchOperationMetadata(message)NearestNeighborSearchOperationMetadata.ContentValidationStats(message)NearestNeighborSearchOperationMetadata.RecordError(message)NearestNeighborSearchOperationMetadata.RecordError.RecordErrorType(enum)NearestNeighbors(message)NearestNeighbors.Neighbor(message)Neighbor(message)NetworkSpec(message)NfsMount(message)NotebookEucConfig(message)NotebookExecutionJob(message)NotebookExecutionJob.CustomEnvironmentSpec(message)NotebookExecutionJob.DataformRepositorySource(message)NotebookExecutionJob.DirectNotebookSource(message)NotebookExecutionJob.GcsNotebookSource(message)NotebookExecutionJob.WorkbenchRuntime(message)NotebookExecutionJobView(enum)NotebookIdleShutdownConfig(message)NotebookRuntime(message)NotebookRuntime.HealthState(enum)NotebookRuntime.RuntimeState(enum)NotebookRuntimeTemplate(message)NotebookRuntimeTemplateRef(message)NotebookRuntimeType(enum)NotebookSoftwareConfig(message)OutputConfig(message)OutputInfo(message)PSCAutomationConfig(message)PairwiseChoice(enum)PairwiseMetricInput(message)PairwiseMetricInstance(message)PairwiseMetricResult(message)PairwiseMetricSpec(message)PairwiseQuestionAnsweringQualityInput(message)PairwiseQuestionAnsweringQualityInstance(message)PairwiseQuestionAnsweringQualityResult(message)PairwiseQuestionAnsweringQualitySpec(message)PairwiseSummarizationQualityInput(message)PairwiseSummarizationQualityInstance(message)PairwiseSummarizationQualityResult(message)PairwiseSummarizationQualitySpec(message)Part(message)PartnerModelTuningSpec(message)PauseModelDeploymentMonitoringJobRequest(message)PauseScheduleRequest(message)PersistentDiskSpec(message)PersistentResource(message)PersistentResource.State(enum)PipelineFailurePolicy(enum)PipelineJob(message)PipelineJob.RuntimeConfig(message)PipelineJob.RuntimeConfig.DefaultRuntime(message)PipelineJob.RuntimeConfig.InputArtifact(message)PipelineJob.RuntimeConfig.PersistentResourceRuntimeDetail(message)PipelineJob.RuntimeConfig.PersistentResourceRuntimeDetail.TaskResourceUnavailableTimeoutBehavior(enum)PipelineJobDetail(message)PipelineState(enum)PipelineTaskDetail(message)PipelineTaskDetail.ArtifactList(message)PipelineTaskDetail.PipelineTaskStatus(message)PipelineTaskDetail.State(enum)PipelineTaskExecutorDetail(message)PipelineTaskExecutorDetail.ContainerDetail(message)PipelineTaskExecutorDetail.CustomJobDetail(message)PipelineTaskRerunConfig(message)PipelineTaskRerunConfig.ArtifactList(message)PipelineTaskRerunConfig.Inputs(message)PipelineTemplateMetadata(message)PointwiseMetricInput(message)PointwiseMetricInstance(message)PointwiseMetricResult(message)PointwiseMetricSpec(message)Port(message)PostStartupScriptConfig(message)PostStartupScriptConfig.PostStartupScriptBehavior(enum)PrebuiltVoiceConfig(message)PredefinedSplit(message)PredictLongRunningMetadata(message)PredictLongRunningResponse(message)PredictRequest(message)PredictRequestResponseLoggingConfig(message)PredictResponse(message)PredictSchemata(message)Presets(message)Presets.Modality(enum)Presets.Query(enum)PrivateEndpoints(message)PrivateServiceConnectConfig(message)Probe(message)Probe.ExecAction(message)Probe.GrpcAction(message)Probe.HttpGetAction(message)Probe.HttpHeader(message)Probe.TcpSocketAction(message)PscAutomatedEndpoints(message)PscInterfaceConfig(message)PublisherModel(message)PublisherModel.CallToAction(message)PublisherModel.CallToAction.Deploy(message)PublisherModel.CallToAction.Deploy.DeployMetadata(message)PublisherModel.CallToAction.DeployGke(message)PublisherModel.CallToAction.DeployVertex(message)PublisherModel.CallToAction.OpenFineTuningPipelines(message)PublisherModel.CallToAction.OpenNotebooks(message)PublisherModel.CallToAction.RegionalResourceReferences(message)PublisherModel.CallToAction.ViewRestApi(message)PublisherModel.Documentation(message)PublisherModel.LaunchStage(enum)PublisherModel.OpenSourceCategory(enum)PublisherModel.Parent(message)PublisherModel.ResourceReference(message)PublisherModel.VersionState(enum)PublisherModelView(enum)PurgeArtifactsMetadata(message)PurgeArtifactsRequest(message)PurgeArtifactsResponse(message)PurgeContextsMetadata(message)PurgeContextsRequest(message)PurgeContextsResponse(message)PurgeExecutionsMetadata(message)PurgeExecutionsRequest(message)PurgeExecutionsResponse(message)PythonPackageSpec(message)QueryArtifactLineageSubgraphRequest(message)QueryContextLineageSubgraphRequest(message)QueryDeployedModelsRequest(message)QueryDeployedModelsResponse(message)QueryExecutionInputsAndOutputsRequest(message)QueryExtensionRequest(message)QueryExtensionResponse(message)QueryReasoningEngineRequest(message)QueryReasoningEngineResponse(message)QuestionAnsweringCorrectnessInput(message)QuestionAnsweringCorrectnessInstance(message)QuestionAnsweringCorrectnessResult(message)QuestionAnsweringCorrectnessSpec(message)QuestionAnsweringHelpfulnessInput(message)QuestionAnsweringHelpfulnessInstance(message)QuestionAnsweringHelpfulnessResult(message)QuestionAnsweringHelpfulnessSpec(message)QuestionAnsweringQualityInput(message)QuestionAnsweringQualityInstance(message)QuestionAnsweringQualityResult(message)QuestionAnsweringQualitySpec(message)QuestionAnsweringRelevanceInput(message)QuestionAnsweringRelevanceInstance(message)QuestionAnsweringRelevanceResult(message)QuestionAnsweringRelevanceSpec(message)RagContexts(message)RagContexts.Context(message)RagCorpus(message)RagEmbeddingModelConfig(message)RagEmbeddingModelConfig.HybridSearchConfig(message)RagEmbeddingModelConfig.SparseEmbeddingConfig(message)RagEmbeddingModelConfig.SparseEmbeddingConfig.Bm25(message)RagEmbeddingModelConfig.VertexPredictionEndpoint(message)RagFile(message)RagFile.RagFileType(enum)RagFileChunkingConfig(message)RagFileChunkingConfig.FixedLengthChunking(message)RagFileParsingConfig(message)RagFileParsingConfig.AdvancedParser(message)RagFileParsingConfig.LayoutParser(message)RagFileParsingConfig.LlmParser(message)RagFileTransformationConfig(message)RagQuery(message)RagQuery.Ranking(message)RagRetrievalConfig(message)RagRetrievalConfig.Filter(message)RagRetrievalConfig.HybridSearch(message)RagRetrievalConfig.Ranking(message)RagRetrievalConfig.Ranking.LlmRanker(message)RagRetrievalConfig.Ranking.RankService(message)RagVectorDbConfig(message)RagVectorDbConfig.Pinecone(message)RagVectorDbConfig.RagManagedDb(message)RagVectorDbConfig.VertexFeatureStore(message)RagVectorDbConfig.VertexVectorSearch(message)RagVectorDbConfig.Weaviate(message)RawPredictRequest(message)RayLogsSpec(message)RayMetricSpec(message)RaySpec(message)ReadFeatureValuesRequest(message)ReadFeatureValuesResponse(message)ReadFeatureValuesResponse.EntityView(message)ReadFeatureValuesResponse.EntityView.Data(message)ReadFeatureValuesResponse.FeatureDescriptor(message)ReadFeatureValuesResponse.Header(message)ReadTensorboardBlobDataRequest(message)ReadTensorboardBlobDataResponse(message)ReadTensorboardSizeRequest(message)ReadTensorboardSizeResponse(message)ReadTensorboardTimeSeriesDataRequest(message)ReadTensorboardTimeSeriesDataResponse(message)ReadTensorboardUsageRequest(message)ReadTensorboardUsageResponse(message)ReadTensorboardUsageResponse.PerMonthUsageData(message)ReadTensorboardUsageResponse.PerUserUsageData(message)ReasoningEngine(message)ReasoningEngineSpec(message)ReasoningEngineSpec.PackageSpec(message)RebaseTunedModelOperationMetadata(message)RebaseTunedModelRequest(message)RebootPersistentResourceOperationMetadata(message)RebootPersistentResourceRequest(message)RemoveContextChildrenRequest(message)RemoveContextChildrenResponse(message)RemoveDatapointsRequest(message)RemoveDatapointsResponse(message)ReservationAffinity(message)ReservationAffinity.Type(enum)ResourcePool(message)ResourcePool.AutoscalingSpec(message)ResourceRuntime(message)ResourceRuntimeSpec(message)ResourcesConsumed(message)RestoreDatasetVersionOperationMetadata(message)RestoreDatasetVersionRequest(message)ResumeModelDeploymentMonitoringJobRequest(message)ResumeScheduleRequest(message)Retrieval(message)RetrievalConfig(message)RetrievalMetadata(message)RetrieveContextsRequest(message)RetrieveContextsRequest.VertexRagStore(message)RetrieveContextsRequest.VertexRagStore.RagResource(message)RetrieveContextsResponse(message)RolloutOptions(message)RougeInput(message)RougeInstance(message)RougeMetricValue(message)RougeResults(message)RougeSpec(message)RuntimeArtifact(message)RuntimeConfig(message)RuntimeConfig.CodeInterpreterRuntimeConfig(message)RuntimeConfig.VertexAISearchRuntimeConfig(message)SafetyInput(message)SafetyInstance(message)SafetyRating(message)SafetyRating.HarmProbability(enum)SafetyRating.HarmSeverity(enum)SafetyResult(message)SafetySetting(message)SafetySetting.HarmBlockMethod(enum)SafetySetting.HarmBlockThreshold(enum)SafetySpec(message)SampledShapleyAttribution(message)SamplingStrategy(message)SamplingStrategy.RandomSampleConfig(message)SavedQuery(message)Scalar(message)Schedule(message)Schedule.RunResponse(message)Schedule.State(enum)ScheduleConfig(message)Scheduling(message)Scheduling.Strategy(enum)Schema(message)SearchDataItemsRequest(message)SearchDataItemsRequest.OrderByAnnotation(message)SearchDataItemsResponse(message)SearchEntryPoint(message)SearchFeaturesRequest(message)SearchFeaturesResponse(message)SearchMigratableResourcesRequest(message)SearchMigratableResourcesResponse(message)SearchModelDeploymentMonitoringStatsAnomaliesRequest(message)SearchModelDeploymentMonitoringStatsAnomaliesRequest.StatsAnomaliesObjective(message)SearchModelDeploymentMonitoringStatsAnomaliesResponse(message)SearchModelMonitoringAlertsRequest(message)SearchModelMonitoringAlertsResponse(message)SearchModelMonitoringStatsFilter(message)SearchModelMonitoringStatsFilter.TabularStatsFilter(message)SearchModelMonitoringStatsRequest(message)SearchModelMonitoringStatsResponse(message)SearchNearestEntitiesRequest(message)SearchNearestEntitiesResponse(message)Segment(message)ServiceAccountSpec(message)SharePointSources(message)SharePointSources.SharePointSource(message)ShieldedVmConfig(message)SlackSource(message)SlackSource.SlackChannels(message)SlackSource.SlackChannels.SlackChannel(message)SmoothGradConfig(message)SpecialistPool(message)SpeechConfig(message)StartNotebookRuntimeOperationMetadata(message)StartNotebookRuntimeRequest(message)StartNotebookRuntimeResponse(message)StopNotebookRuntimeOperationMetadata(message)StopNotebookRuntimeRequest(message)StopNotebookRuntimeResponse(message)StopTrialRequest(message)StratifiedSplit(message)StreamDirectPredictRequest(message)StreamDirectPredictResponse(message)StreamDirectRawPredictRequest(message)StreamDirectRawPredictResponse(message)StreamQueryReasoningEngineRequest(message)StreamRawPredictRequest(message)StreamingFetchFeatureValuesRequest(message)StreamingFetchFeatureValuesResponse(message)StreamingPredictRequest(message)StreamingPredictResponse(message)StreamingRawPredictRequest(message)StreamingRawPredictResponse(message)StreamingReadFeatureValuesRequest(message)StringArray(message)StructFieldValue(message)StructValue(message)Study(message)Study.State(enum)StudySpec(message)StudySpec.Algorithm(enum)StudySpec.ConvexAutomatedStoppingSpec(message)StudySpec.ConvexStopConfig(message) (deprecated)StudySpec.DecayCurveAutomatedStoppingSpec(message)StudySpec.MeasurementSelectionType(enum)StudySpec.MedianAutomatedStoppingSpec(message)StudySpec.MetricSpec(message)StudySpec.MetricSpec.GoalType(enum)StudySpec.MetricSpec.SafetyMetricConfig(message)StudySpec.ObservationNoise(enum)StudySpec.ParameterSpec(message)StudySpec.ParameterSpec.CategoricalValueSpec(message)StudySpec.ParameterSpec.ConditionalParameterSpec(message)StudySpec.ParameterSpec.ConditionalParameterSpec.CategoricalValueCondition(message)StudySpec.ParameterSpec.ConditionalParameterSpec.DiscreteValueCondition(message)StudySpec.ParameterSpec.ConditionalParameterSpec.IntValueCondition(message)StudySpec.ParameterSpec.DiscreteValueSpec(message)StudySpec.ParameterSpec.DoubleValueSpec(message)StudySpec.ParameterSpec.IntegerValueSpec(message)StudySpec.ParameterSpec.ScaleType(enum)StudySpec.StudyStoppingConfig(message)StudySpec.TransferLearningConfig(message)StudyTimeConstraint(message)SuggestTrialsMetadata(message)SuggestTrialsRequest(message)SuggestTrialsResponse(message)SummarizationHelpfulnessInput(message)SummarizationHelpfulnessInstance(message)SummarizationHelpfulnessResult(message)SummarizationHelpfulnessSpec(message)SummarizationQualityInput(message)SummarizationQualityInstance(message)SummarizationQualityResult(message)SummarizationQualitySpec(message)SummarizationVerbosityInput(message)SummarizationVerbosityInstance(message)SummarizationVerbosityResult(message)SummarizationVerbositySpec(message)SupervisedHyperParameters(message)SupervisedHyperParameters.AdapterSize(enum)SupervisedTuningDataStats(message)SupervisedTuningDatasetDistribution(message)SupervisedTuningDatasetDistribution.DatasetBucket(message)SupervisedTuningSpec(message)SyncFeatureViewRequest(message)SyncFeatureViewResponse(message)TFRecordDestination(message)Tensor(message)Tensor.DataType(enum)Tensorboard(message)TensorboardBlob(message)TensorboardBlobSequence(message)TensorboardExperiment(message)TensorboardRun(message)TensorboardTensor(message)TensorboardTimeSeries(message)TensorboardTimeSeries.Metadata(message)TensorboardTimeSeries.ValueType(enum)ThresholdConfig(message)TimeSeriesData(message)TimeSeriesDataPoint(message)TimestampSplit(message)TokensInfo(message)Tool(message)Tool.CodeExecution(message)Tool.GoogleSearch(message)ToolCall(message)ToolCallValidInput(message)ToolCallValidInstance(message)ToolCallValidMetricValue(message)ToolCallValidResults(message)ToolCallValidSpec(message)ToolConfig(message)ToolNameMatchInput(message)ToolNameMatchInstance(message)ToolNameMatchMetricValue(message)ToolNameMatchResults(message)ToolNameMatchSpec(message)ToolParameterKVMatchInput(message)ToolParameterKVMatchInstance(message)ToolParameterKVMatchMetricValue(message)ToolParameterKVMatchResults(message)ToolParameterKVMatchSpec(message)ToolParameterKeyMatchInput(message)ToolParameterKeyMatchInstance(message)ToolParameterKeyMatchMetricValue(message)ToolParameterKeyMatchResults(message)ToolParameterKeyMatchSpec(message)ToolUseExample(message)ToolUseExample.ExtensionOperation(message)TrainingPipeline(message)Trajectory(message)TrajectoryAnyOrderMatchInput(message)TrajectoryAnyOrderMatchInstance(message)TrajectoryAnyOrderMatchMetricValue(message)TrajectoryAnyOrderMatchResults(message)TrajectoryAnyOrderMatchSpec(message)TrajectoryExactMatchInput(message)TrajectoryExactMatchInstance(message)TrajectoryExactMatchMetricValue(message)TrajectoryExactMatchResults(message)TrajectoryExactMatchSpec(message)TrajectoryInOrderMatchInput(message)TrajectoryInOrderMatchInstance(message)TrajectoryInOrderMatchMetricValue(message)TrajectoryInOrderMatchResults(message)TrajectoryInOrderMatchSpec(message)TrajectoryPrecisionInput(message)TrajectoryPrecisionInstance(message)TrajectoryPrecisionMetricValue(message)TrajectoryPrecisionResults(message)TrajectoryPrecisionSpec(message)TrajectoryRecallInput(message)TrajectoryRecallInstance(message)TrajectoryRecallMetricValue(message)TrajectoryRecallResults(message)TrajectoryRecallSpec(message)TrajectorySingleToolUseInput(message)TrajectorySingleToolUseInstance(message)TrajectorySingleToolUseMetricValue(message)TrajectorySingleToolUseResults(message)TrajectorySingleToolUseSpec(message)Trial(message)Trial.Parameter(message)Trial.State(enum)TrialContext(message)TunedModel(message)TunedModelRef(message)TuningDataStats(message)TuningJob(message)Type(enum)UndeployIndexOperationMetadata(message)UndeployIndexRequest(message)UndeployIndexResponse(message)UndeployModelOperationMetadata(message)UndeployModelRequest(message)UndeployModelResponse(message)UndeploySolverOperationMetadata(message)UnmanagedContainerModel(message)UpdateArtifactRequest(message)UpdateCachedContentRequest(message)UpdateContextRequest(message)UpdateDatasetRequest(message)UpdateDatasetVersionRequest(message)UpdateDeploymentResourcePoolOperationMetadata(message)UpdateDeploymentResourcePoolRequest(message)UpdateEndpointLongRunningRequest(message)UpdateEndpointOperationMetadata(message)UpdateEndpointRequest(message)UpdateEntityTypeRequest(message)UpdateExecutionRequest(message)UpdateExplanationDatasetOperationMetadata(message)UpdateExplanationDatasetRequest(message)UpdateExplanationDatasetResponse(message)UpdateExtensionRequest(message)UpdateFeatureGroupOperationMetadata(message)UpdateFeatureGroupRequest(message)UpdateFeatureMonitorOperationMetadata(message)UpdateFeatureMonitorRequest(message)UpdateFeatureOnlineStoreOperationMetadata(message)UpdateFeatureOnlineStoreRequest(message)UpdateFeatureOperationMetadata(message)UpdateFeatureRequest(message)UpdateFeatureViewOperationMetadata(message)UpdateFeatureViewRequest(message)UpdateFeaturestoreOperationMetadata(message)UpdateFeaturestoreRequest(message)UpdateIndexEndpointRequest(message)UpdateIndexOperationMetadata(message)UpdateIndexRequest(message)UpdateModelDeploymentMonitoringJobOperationMetadata(message)UpdateModelDeploymentMonitoringJobRequest(message)UpdateModelMonitorOperationMetadata(message)UpdateModelMonitorRequest(message)UpdateModelRequest(message)UpdateNotebookRuntimeTemplateRequest(message)UpdatePersistentResourceOperationMetadata(message)UpdatePersistentResourceRequest(message)UpdateRagCorpusOperationMetadata(message)UpdateRagCorpusRequest(message)UpdateReasoningEngineOperationMetadata(message)UpdateReasoningEngineRequest(message)UpdateScheduleRequest(message)UpdateSpecialistPoolOperationMetadata(message)UpdateSpecialistPoolRequest(message)UpdateTensorboardExperimentRequest(message)UpdateTensorboardOperationMetadata(message)UpdateTensorboardRequest(message)UpdateTensorboardRunRequest(message)UpdateTensorboardTimeSeriesRequest(message)UpgradeNotebookRuntimeOperationMetadata(message)UpgradeNotebookRuntimeRequest(message)UpgradeNotebookRuntimeResponse(message)UploadModelOperationMetadata(message)UploadModelRequest(message)UploadModelResponse(message)UploadRagFileConfig(message)UpsertDatapointsRequest(message)UpsertDatapointsResponse(message)UserActionReference(message)Value(message)VertexAISearch(message)VertexAiSearchConfig(message)VertexRagStore(message)VertexRagStore.RagResource(message)VideoMetadata(message)VoiceConfig(message)WorkerPoolSpec(message)WriteFeatureValuesPayload(message)WriteFeatureValuesRequest(message)WriteFeatureValuesResponse(message)WriteTensorboardExperimentDataRequest(message)WriteTensorboardExperimentDataResponse(message)WriteTensorboardRunDataRequest(message)WriteTensorboardRunDataResponse(message)XraiAttribution(message)
DatasetService
The service that manages Vertex AI Dataset and its child resources.
| CreateDataset |
|---|
|
Creates a Dataset.
|
| CreateDatasetVersion |
|---|
|
Create a version from a Dataset.
|
| DeleteDataset |
|---|
|
Deletes a Dataset.
|
| DeleteDatasetVersion |
|---|
|
Deletes a Dataset version.
|
| DeleteSavedQuery |
|---|
|
Deletes a SavedQuery.
|
| ExportData |
|---|
|
Exports data from a Dataset.
|
| GetAnnotationSpec |
|---|
|
Gets an AnnotationSpec.
|
| GetDataset |
|---|
|
Gets a Dataset.
|
| GetDatasetVersion |
|---|
|
Gets a Dataset version.
|
| ImportData |
|---|
|
Imports data into a Dataset.
|
| ListAnnotations |
|---|
|
Lists Annotations belongs to a dataitem This RPC is only available in InternalDatasetService. It is only used for exporting conversation data to CCAI Insights.
|
| ListDataItems |
|---|
|
Lists DataItems in a Dataset.
|
| ListDatasetVersions |
|---|
|
Lists DatasetVersions in a Dataset.
|
| ListDatasets |
|---|
|
Lists Datasets in a Location.
|
| ListSavedQueries |
|---|
|
Lists SavedQueries in a Dataset.
|
| RestoreDatasetVersion |
|---|
|
Restores a dataset version.
|
| SearchDataItems |
|---|
|
Searches DataItems in a Dataset.
|
| UpdateDataset |
|---|
|
Updates a Dataset.
|
| UpdateDatasetVersion |
|---|
|
Updates a DatasetVersion.
|
DeploymentResourcePoolService
A service that manages the DeploymentResourcePool resource.
| CreateDeploymentResourcePool |
|---|
|
Create a DeploymentResourcePool.
|
| DeleteDeploymentResourcePool |
|---|
|
Delete a DeploymentResourcePool.
|
| GetDeploymentResourcePool |
|---|
|
Get a DeploymentResourcePool.
|
| ListDeploymentResourcePools |
|---|
|
List DeploymentResourcePools in a location.
|
| QueryDeployedModels |
|---|
|
List DeployedModels that have been deployed on this DeploymentResourcePool.
|
| UpdateDeploymentResourcePool |
|---|
|
Update a DeploymentResourcePool.
|
EndpointService
A service for managing Vertex AI's Endpoints.
| CreateEndpoint |
|---|
|
Creates an Endpoint.
|
| DeleteEndpoint |
|---|
|
Deletes an Endpoint.
|
| DeployModel |
|---|
|
Deploys a Model into this Endpoint, creating a DeployedModel within it.
|
| GetEndpoint |
|---|
|
Gets an Endpoint.
|
| ListEndpoints |
|---|
|
Lists Endpoints in a Location.
|
| MutateDeployedModel |
|---|
|
Updates an existing deployed model. Updatable fields include
|
| UndeployModel |
|---|
|
Undeploys a Model from an Endpoint, removing a DeployedModel from it, and freeing all resources it's using.
|
| UpdateEndpoint |
|---|
|
Updates an Endpoint.
|
| UpdateEndpointLongRunning |
|---|
|
Updates an Endpoint with a long running operation.
|
EvaluationService
Vertex AI Online Evaluation Service.
| EvaluateDataset |
|---|
|
Evaluates a dataset based on a set of given metrics.
|
| EvaluateInstances |
|---|
|
Evaluates instances based on a given metric.
|
ExtensionExecutionService
A service for Extension execution.
| ExecuteExtension |
|---|
|
Executes the request against a given extension.
|
| QueryExtension |
|---|
|
Queries an extension with a default controller.
|
ExtensionRegistryService
A service for managing Vertex AI's Extension registry.
| DeleteExtension |
|---|
|
Deletes an Extension.
|
| GetExtension |
|---|
|
Gets an Extension.
|
| ImportExtension |
|---|
|
Imports an Extension.
|
| ListExtensions |
|---|
|
Lists Extensions in a location.
|
| UpdateExtension |
|---|
|
Updates an Extension.
|
FeatureOnlineStoreAdminService
The service that handles CRUD and List for resources for FeatureOnlineStore.
| CreateFeatureOnlineStore |
|---|
|
Creates a new FeatureOnlineStore in a given project and location.
|
| CreateFeatureView |
|---|
|
Creates a new FeatureView in a given FeatureOnlineStore.
|
| DeleteFeatureOnlineStore |
|---|
|
Deletes a single FeatureOnlineStore. The FeatureOnlineStore must not contain any FeatureViews.
|
| DeleteFeatureView |
|---|
|
Deletes a single FeatureView.
|
| GetFeatureOnlineStore |
|---|
|
Gets details of a single FeatureOnlineStore.
|
| GetFeatureView |
|---|
|
Gets details of a single FeatureView.
|
| GetFeatureViewSync |
|---|
|
Gets details of a single FeatureViewSync.
|
| ListFeatureOnlineStores |
|---|
|
Lists FeatureOnlineStores in a given project and location.
|
| ListFeatureViewSyncs |
|---|
|
Lists FeatureViewSyncs in a given FeatureView.
|
| ListFeatureViews |
|---|
|
Lists FeatureViews in a given FeatureOnlineStore.
|
| SyncFeatureView |
|---|
|
Triggers on-demand sync for the FeatureView.
|
| UpdateFeatureOnlineStore |
|---|
|
Updates the parameters of a single FeatureOnlineStore.
|
| UpdateFeatureView |
|---|
|
Updates the parameters of a single FeatureView.
|
FeatureOnlineStoreService
A service for fetching feature values from the online store.
| FetchFeatureValues |
|---|
|
Fetch feature values under a FeatureView.
|
| SearchNearestEntities |
|---|
|
Search the nearest entities under a FeatureView. Search only works for indexable feature view; if a feature view isn't indexable, returns Invalid argument response.
|
| StreamingFetchFeatureValues |
|---|
|
Bidirectional streaming RPC to fetch feature values under a FeatureView. Requests may not have a one-to-one mapping to responses and responses may be returned out-of-order to reduce latency.
|
FeatureRegistryService
The service that handles CRUD and List for resources for FeatureRegistry.
| BatchCreateFeatures |
|---|
|
Creates a batch of Features in a given FeatureGroup.
|
| CreateFeature |
|---|
|
Creates a new Feature in a given FeatureGroup.
|
| CreateFeatureGroup |
|---|
|
Creates a new FeatureGroup in a given project and location.
|
| CreateFeatureMonitor |
|---|
|
Creates a new FeatureMonitor in a given project, location and FeatureGroup.
|
| CreateFeatureMonitorJob |
|---|
|
Creates a new feature monitor job.
|
| DeleteFeature |
|---|
|
Deletes a single Feature.
|
| DeleteFeatureGroup |
|---|
|
Deletes a single FeatureGroup.
|
| DeleteFeatureMonitor |
|---|
|
Deletes a single FeatureMonitor.
|
| GetFeature |
|---|
|
Gets details of a single Feature.
|
| GetFeatureGroup |
|---|
|
Gets details of a single FeatureGroup.
|
| GetFeatureMonitor |
|---|
|
Gets details of a single FeatureMonitor.
|
| GetFeatureMonitorJob |
|---|
|
Get a feature monitor job.
|
| ListFeatureGroups |
|---|
|
Lists FeatureGroups in a given project and location.
|
| ListFeatureMonitorJobs |
|---|
|
List feature monitor jobs.
|
| ListFeatureMonitors |
|---|
|
Lists FeatureGroups in a given project and location.
|
| ListFeatures |
|---|
|
Lists Features in a given FeatureGroup.
|
| UpdateFeature |
|---|
|
Updates the parameters of a single Feature.
|
| UpdateFeatureGroup |
|---|
|
Updates the parameters of a single FeatureGroup.
|
| UpdateFeatureMonitor |
|---|
|
Updates the parameters of a single FeatureMonitor.
|
FeaturestoreOnlineServingService
A service for serving online feature values.
| ReadFeatureValues |
|---|
|
Reads Feature values of a specific entity of an EntityType. For reading feature values of multiple entities of an EntityType, please use StreamingReadFeatureValues.
|
| StreamingReadFeatureValues |
|---|
|
Reads Feature values for multiple entities. Depending on their size, data for different entities may be broken up across multiple responses.
|
| WriteFeatureValues |
|---|
|
Writes Feature values of one or more entities of an EntityType. The Feature values are merged into existing entities if any. The Feature values to be written must have timestamp within the online storage retention.
|
FeaturestoreService
The service that handles CRUD and List for resources for Featurestore.
| BatchCreateFeatures |
|---|
|
Creates a batch of Features in a given EntityType.
|
| BatchReadFeatureValues |
|---|
|
Batch reads Feature values from a Featurestore. This API enables batch reading Feature values, where each read instance in the batch may read Feature values of entities from one or more EntityTypes. Point-in-time correctness is guaranteed for Feature values of each read instance as of each instance's read timestamp.
|
| CreateEntityType |
|---|
|
Creates a new EntityType in a given Featurestore.
|
| CreateFeature |
|---|
|
Creates a new Feature in a given EntityType.
|
| CreateFeaturestore |
|---|
|
Creates a new Featurestore in a given project and location.
|
| DeleteEntityType |
|---|
|
Deletes a single EntityType. The EntityType must not have any Features or
|
| DeleteFeature |
|---|
|
Deletes a single Feature.
|
| DeleteFeatureValues |
|---|
|
Delete Feature values from Featurestore. The progress of the deletion is tracked by the returned operation. The deleted feature values are guaranteed to be invisible to subsequent read operations after the operation is marked as successfully done. If a delete feature values operation fails, the feature values returned from reads and exports may be inconsistent. If consistency is required, the caller must retry the same delete request again and wait till the new operation returned is marked as successfully done.
|
| DeleteFeaturestore |
|---|
|
Deletes a single Featurestore. The Featurestore must not contain any EntityTypes or
|
| ExportFeatureValues |
|---|
|
Exports Feature values from all the entities of a target EntityType.
|
| GetEntityType |
|---|
|
Gets details of a single EntityType.
|
| GetFeature |
|---|
|
Gets details of a single Feature.
|
| GetFeaturestore |
|---|
|
Gets details of a single Featurestore.
|
| ImportFeatureValues |
|---|
|
Imports Feature values into the Featurestore from a source storage. The progress of the import is tracked by the returned operation. The imported features are guaranteed to be visible to subsequent read operations after the operation is marked as successfully done. If an import operation fails, the Feature values returned from reads and exports may be inconsistent. If consistency is required, the caller must retry the same import request again and wait till the new operation returned is marked as successfully done. There are also scenarios where the caller can cause inconsistency.
|
| ListEntityTypes |
|---|
|
Lists EntityTypes in a given Featurestore.
|
| ListFeatures |
|---|
|
Lists Features in a given EntityType.
|
| ListFeaturestores |
|---|
|
Lists Featurestores in a given project and location.
|
| SearchFeatures |
|---|
|
Searches Features matching a query in a given project.
|
| UpdateEntityType |
|---|
|
Updates the parameters of a single EntityType.
|
| UpdateFeature |
|---|
|
Updates the parameters of a single Feature.
|
| UpdateFeaturestore |
|---|
|
Updates the parameters of a single Featurestore.
|
GenAiCacheService
Service for managing Vertex AI's CachedContent resource.
| CreateCachedContent |
|---|
|
Creates cached content, this call will initialize the cached content in the data storage, and users need to pay for the cache data storage.
|
| DeleteCachedContent |
|---|
|
Deletes cached content
|
| GetCachedContent |
|---|
|
Gets cached content configurations
|
| ListCachedContents |
|---|
|
Lists cached contents in a project
|
| UpdateCachedContent |
|---|
|
Updates cached content configurations
|
GenAiTuningService
A service for creating and managing GenAI Tuning Jobs.
| CancelTuningJob |
|---|
|
Cancels a TuningJob. Starts asynchronous cancellation on the TuningJob. The server makes a best effort to cancel the job, but success is not guaranteed. Clients can use
|
| CreateTuningJob |
|---|
|
Creates a TuningJob. A created TuningJob right away will be attempted to be run.
|
| GetTuningJob |
|---|
|
Gets a TuningJob.
|
| ListTuningJobs |
|---|
|
Lists TuningJobs in a Location.
|
| RebaseTunedModel |
|---|
|
Rebase a TunedModel.
|
IndexEndpointService
A service for managing Vertex AI's IndexEndpoints.
| CreateIndexEndpoint |
|---|
|
Creates an IndexEndpoint.
|
| DeleteIndexEndpoint |
|---|
|
Deletes an IndexEndpoint.
|
| DeployIndex |
|---|
|
Deploys an Index into this IndexEndpoint, creating a DeployedIndex within it.
|
| GetIndexEndpoint |
|---|
|
Gets an IndexEndpoint.
|
| ListIndexEndpoints |
|---|
|
Lists IndexEndpoints in a Location.
|
| MutateDeployedIndex |
|---|
|
Update an existing DeployedIndex under an IndexEndpoint.
|
| UndeployIndex |
|---|
|
Undeploys an Index from an IndexEndpoint, removing a DeployedIndex from it, and freeing all resources it's using.
|
| UpdateIndexEndpoint |
|---|
|
Updates an IndexEndpoint.
|
IndexService
A service for creating and managing Vertex AI's Index resources.
| CreateIndex |
|---|
|
Creates an Index.
|
| DeleteIndex |
|---|
|
Deletes an Index. An Index can only be deleted when all its
|
| GetIndex |
|---|
|
Gets an Index.
|
| ListIndexes |
|---|
|
Lists Indexes in a Location.
|
| RemoveDatapoints |
|---|
|
Remove Datapoints from an Index.
|
| UpdateIndex |
|---|
|
Updates an Index.
|
| UpsertDatapoints |
|---|
|
Add/update Datapoints into an Index.
|
JobService
A service for creating and managing Vertex AI's jobs.
| CancelBatchPredictionJob |
|---|
|
Cancels a BatchPredictionJob. Starts asynchronous cancellation on the BatchPredictionJob. The server makes the best effort to cancel the job, but success is not guaranteed. Clients can use
|
| CancelCustomJob |
|---|
|
Cancels a CustomJob. Starts asynchronous cancellation on the CustomJob. The server makes a best effort to cancel the job, but success is not guaranteed. Clients can use
|
| CancelHyperparameterTuningJob |
|---|
|
Cancels a HyperparameterTuningJob. Starts asynchronous cancellation on the HyperparameterTuningJob. The server makes a best effort to cancel the job, but success is not guaranteed. Clients can use
|
| CreateBatchPredictionJob |
|---|
|
Creates a BatchPredictionJob. A BatchPredictionJob once created will right away be attempted to start.
|
| CreateCustomJob |
|---|
|
Creates a CustomJob. A created CustomJob right away will be attempted to be run.
|
| CreateHyperparameterTuningJob |
|---|
|
Creates a HyperparameterTuningJob
|
| CreateModelDeploymentMonitoringJob |
|---|
|
Creates a ModelDeploymentMonitoringJob. It will run periodically on a configured interval.
|
| DeleteBatchPredictionJob |
|---|
|
Deletes a BatchPredictionJob. Can only be called on jobs that already finished.
|
| DeleteCustomJob |
|---|
|
Deletes a CustomJob.
|
| DeleteHyperparameterTuningJob |
|---|
|
Deletes a HyperparameterTuningJob.
|
| DeleteModelDeploymentMonitoringJob |
|---|
|
Deletes a ModelDeploymentMonitoringJob.
|
| GetBatchPredictionJob |
|---|
|
Gets a BatchPredictionJob
|
| GetCustomJob |
|---|
|
Gets a CustomJob.
|
| GetHyperparameterTuningJob |
|---|
|
Gets a HyperparameterTuningJob
|
| GetModelDeploymentMonitoringJob |
|---|
|
Gets a ModelDeploymentMonitoringJob.
|
| ListBatchPredictionJobs |
|---|
|
Lists BatchPredictionJobs in a Location.
|
| ListCustomJobs |
|---|
|
Lists CustomJobs in a Location.
|
| ListHyperparameterTuningJobs |
|---|
|
Lists HyperparameterTuningJobs in a Location.
|
| ListModelDeploymentMonitoringJobs |
|---|
|
Lists ModelDeploymentMonitoringJobs in a Location.
|
| PauseModelDeploymentMonitoringJob |
|---|
|
Pauses a ModelDeploymentMonitoringJob. If the job is running, the server makes a best effort to cancel the job. Will mark
|
| ResumeModelDeploymentMonitoringJob |
|---|
|
Resumes a paused ModelDeploymentMonitoringJob. It will start to run from next scheduled time. A deleted ModelDeploymentMonitoringJob can't be resumed.
|
| SearchModelDeploymentMonitoringStatsAnomalies |
|---|
|
Searches Model Monitoring Statistics generated within a given time window.
|
| UpdateModelDeploymentMonitoringJob |
|---|
|
Updates a ModelDeploymentMonitoringJob.
|
LlmUtilityService
Service for LLM related utility functions.
| ComputeTokens |
|---|
|
Return a list of tokens based on the input text.
|
MatchService
MatchService is a Google managed service for efficient vector similarity search at scale.
MetadataService
Service for reading and writing metadata entries.
| AddContextArtifactsAndExecutions |
|---|
|
Adds a set of Artifacts and Executions to a Context. If any of the Artifacts or Executions have already been added to a Context, they are simply skipped.
|
| AddContextChildren |
|---|
|
Adds a set of Contexts as children to a parent Context. If any of the child Contexts have already been added to the parent Context, they are simply skipped. If this call would create a cycle or cause any Context to have more than 10 parents, the request will fail with an INVALID_ARGUMENT error.
|
| AddExecutionEvents |
|---|
|
Adds Events to the specified Execution. An Event indicates whether an Artifact was used as an input or output for an Execution. If an Event already exists between the Execution and the Artifact, the Event is skipped.
|
| CreateArtifact |
|---|
|
Creates an Artifact associated with a MetadataStore.
|
| CreateContext |
|---|
|
Creates a Context associated with a MetadataStore.
|
| CreateExecution |
|---|
|
Creates an Execution associated with a MetadataStore.
|
| CreateMetadataSchema |
|---|
|
Creates a MetadataSchema.
|
| CreateMetadataStore |
|---|
|
Initializes a MetadataStore, including allocation of resources.
|
| DeleteArtifact |
|---|
|
Deletes an Artifact.
|
| DeleteContext |
|---|
|
Deletes a stored Context.
|
| DeleteExecution |
|---|
|
Deletes an Execution.
|
| DeleteMetadataStore |
|---|
|
Deletes a single MetadataStore and all its child resources (Artifacts, Executions, and Contexts).
|
| GetArtifact |
|---|
|
Retrieves a specific Artifact.
|
| GetContext |
|---|
|
Retrieves a specific Context.
|
| GetExecution |
|---|
|
Retrieves a specific Execution.
|
| GetMetadataSchema |
|---|
|
Retrieves a specific MetadataSchema.
|
| GetMetadataStore |
|---|
|
Retrieves a specific MetadataStore.
|
| ListArtifacts |
|---|
|
Lists Artifacts in the MetadataStore.
|
| ListContexts |
|---|
|
Lists Contexts on the MetadataStore.
|
| ListExecutions |
|---|
|
Lists Executions in the MetadataStore.
|
| ListMetadataSchemas |
|---|
|
Lists MetadataSchemas.
|
| ListMetadataStores |
|---|
|
Lists MetadataStores for a Location.
|
| PurgeArtifacts |
|---|
|
Purges Artifacts.
|
| PurgeContexts |
|---|
|
Purges Contexts.
|
| PurgeExecutions |
|---|
|
Purges Executions.
|
| QueryArtifactLineageSubgraph |
|---|
|
Retrieves lineage of an Artifact represented through Artifacts and Executions connected by Event edges and returned as a LineageSubgraph.
|
| QueryContextLineageSubgraph |
|---|
|
Retrieves Artifacts and Executions within the specified Context, connected by Event edges and returned as a LineageSubgraph.
|
| QueryExecutionInputsAndOutputs |
|---|
|
Obtains the set of input and output Artifacts for this Execution, in the form of LineageSubgraph that also contains the Execution and connecting Events.
|
| RemoveContextChildren |
|---|
|
Remove a set of children contexts from a parent Context. If any of the child Contexts were NOT added to the parent Context, they are simply skipped.
|
| UpdateArtifact |
|---|
|
Updates a stored Artifact.
|
| UpdateContext |
|---|
|
Updates a stored Context.
|
| UpdateExecution |
|---|
|
Updates a stored Execution.
|
MigrationService
A service that migrates resources from automl.googleapis.com, datalabeling.googleapis.com and ml.googleapis.com to Vertex AI.
| BatchMigrateResources |
|---|
|
Batch migrates resources from ml.googleapis.com, automl.googleapis.com, and datalabeling.googleapis.com to Vertex AI.
|
| SearchMigratableResources |
|---|
|
Searches all of the resources in automl.googleapis.com, datalabeling.googleapis.com and ml.googleapis.com that can be migrated to Vertex AI's given location.
|
ModelGardenService
The interface of Model Garden Service.
| Deploy |
|---|
|
Deploys a model to a new endpoint.
|
| DeployPublisherModel |
|---|
|
Deploys publisher models.
|
| GetPublisherModel |
|---|
|
Gets a Model Garden publisher model.
|
| ListPublisherModels |
|---|
|
Lists publisher models in Model Garden.
|
ModelMonitoringService
A service for creating and managing Vertex AI Model moitoring. This includes ModelMonitor resources, ModelMonitoringJob resources.
| CreateModelMonitor |
|---|
|
Creates a ModelMonitor.
|
| CreateModelMonitoringJob |
|---|
|
Creates a ModelMonitoringJob.
|
| DeleteModelMonitor |
|---|
|
Deletes a ModelMonitor.
|
| DeleteModelMonitoringJob |
|---|
|
Deletes a ModelMonitoringJob.
|
| GetModelMonitor |
|---|
|
Gets a ModelMonitor.
|
| GetModelMonitoringJob |
|---|
|
Gets a ModelMonitoringJob.
|
| ListModelMonitoringJobs |
|---|
|
Lists ModelMonitoringJobs. Callers may choose to read across multiple Monitors as per AIP-159 by using '-' (the hyphen or dash character) as a wildcard character instead of modelMonitor id in the parent. Format
|
| ListModelMonitors |
|---|
|
Lists ModelMonitors in a Location.
|
| SearchModelMonitoringAlerts |
|---|
|
Returns the Model Monitoring alerts.
|
| SearchModelMonitoringStats |
|---|
|
Searches Model Monitoring Stats generated within a given time window.
|
| UpdateModelMonitor |
|---|
|
Updates a ModelMonitor.
|
ModelService
A service for managing Vertex AI's machine learning Models.
| BatchImportEvaluatedAnnotations |
|---|
|
Imports a list of externally generated EvaluatedAnnotations.
|
| BatchImportModelEvaluationSlices |
|---|
|
Imports a list of externally generated ModelEvaluationSlice.
|
| CopyModel |
|---|
|
Copies an already existing Vertex AI Model into the specified Location. The source Model must exist in the same Project. When copying custom Models, the users themselves are responsible for
|
| DeleteModel |
|---|
|
Deletes a Model. A model cannot be deleted if any
|
| DeleteModelVersion |
|---|
|
Deletes a Model version. Model version can only be deleted if there are no
|
| ExportModel |
|---|
|
Exports a trained, exportable Model to a location specified by the user. A Model is considered to be exportable if it has at least one
|
| GetModel |
|---|
|
Gets a Model.
|
| GetModelEvaluation |
|---|
|
Gets a ModelEvaluation.
|
| GetModelEvaluationSlice |
|---|
|
Gets a ModelEvaluationSlice.
|
| ImportModelEvaluation |
|---|
|
Imports an externally generated ModelEvaluation.
|
| ListModelEvaluationSlices |
|---|
|
Lists ModelEvaluationSlices in a ModelEvaluation.
|
| ListModelEvaluations |
|---|
|
Lists ModelEvaluations in a Model.
|
| ListModelVersionCheckpoints |
|---|
|
Lists checkpoints of the specified model version.
|
| ListModelVersions |
|---|
|
Lists versions of the specified model.
|
| ListModels |
|---|
|
Lists Models in a Location.
|
| MergeVersionAliases |
|---|
|
Merges a set of aliases for a Model version.
|
| UpdateExplanationDataset |
|---|
|
Incrementally update the dataset used for an examples model.
|
| UpdateModel |
|---|
|
Updates a Model.
|
| UploadModel |
|---|
|
Uploads a Model artifact into Vertex AI.
|
NotebookService
The interface for Vertex Notebook service (a.k.a. Colab on Workbench).
| AssignNotebookRuntime |
|---|
|
Assigns a NotebookRuntime to a user for a particular Notebook file. This method will either returns an existing assignment or generates a new one.
|
| CreateNotebookExecutionJob |
|---|
|
Creates a NotebookExecutionJob.
|
| CreateNotebookRuntimeTemplate |
|---|
|
Creates a NotebookRuntimeTemplate.
|
| DeleteNotebookExecutionJob |
|---|
|
Deletes a NotebookExecutionJob.
|
| DeleteNotebookRuntime |
|---|
|
Deletes a NotebookRuntime.
|
| DeleteNotebookRuntimeTemplate |
|---|
|
Deletes a NotebookRuntimeTemplate.
|
| GetNotebookExecutionJob |
|---|
|
Gets a NotebookExecutionJob.
|
| GetNotebookRuntime |
|---|
|
Gets a NotebookRuntime.
|
| GetNotebookRuntimeTemplate |
|---|
|
Gets a NotebookRuntimeTemplate.
|
| ListNotebookExecutionJobs |
|---|
|
Lists NotebookExecutionJobs in a Location.
|
| ListNotebookRuntimeTemplates |
|---|
|
Lists NotebookRuntimeTemplates in a Location.
|
| ListNotebookRuntimes |
|---|
|
Lists NotebookRuntimes in a Location.
|
| StartNotebookRuntime |
|---|
|
Starts a NotebookRuntime.
|
| StopNotebookRuntime |
|---|
|
Stops a NotebookRuntime.
|
| UpdateNotebookRuntimeTemplate |
|---|
|
Updates a NotebookRuntimeTemplate.
|
| UpgradeNotebookRuntime |
|---|
|
Upgrades a NotebookRuntime.
|
PersistentResourceService
A service for managing Vertex AI's machine learning PersistentResource.
| CreatePersistentResource |
|---|
|
Creates a PersistentResource.
|
| DeletePersistentResource |
|---|
|
Deletes a PersistentResource.
|
| GetPersistentResource |
|---|
|
Gets a PersistentResource.
|
| ListPersistentResources |
|---|
|
Lists PersistentResources in a Location.
|
| RebootPersistentResource |
|---|
|
Reboots a PersistentResource.
|
| UpdatePersistentResource |
|---|
|
Updates a PersistentResource.
|
PipelineService
A service for creating and managing Vertex AI's pipelines. This includes both TrainingPipeline resources (used for AutoML and custom training) and PipelineJob resources (used for Vertex AI Pipelines).
| BatchCancelPipelineJobs |
|---|
|
Batch cancel PipelineJobs. Firstly the server will check if all the jobs are in non-terminal states, and skip the jobs that are already terminated. If the operation failed, none of the pipeline jobs are cancelled. The server will poll the states of all the pipeline jobs periodically to check the cancellation status. This operation will return an LRO.
|
| BatchDeletePipelineJobs |
|---|
|
Batch deletes PipelineJobs The Operation is atomic. If it fails, none of the PipelineJobs are deleted. If it succeeds, all of the PipelineJobs are deleted.
|
| CancelPipelineJob |
|---|
|
Cancels a PipelineJob. Starts asynchronous cancellation on the PipelineJob. The server makes a best effort to cancel the pipeline, but success is not guaranteed. Clients can use
|
| CancelTrainingPipeline |
|---|
|
Cancels a TrainingPipeline. Starts asynchronous cancellation on the TrainingPipeline. The server makes a best effort to cancel the pipeline, but success is not guaranteed. Clients can use
|
| CreatePipelineJob |
|---|
|
Creates a PipelineJob. A PipelineJob will run immediately when created.
|
| CreateTrainingPipeline |
|---|
|
Creates a TrainingPipeline. A created TrainingPipeline right away will be attempted to be run.
|
| DeletePipelineJob |
|---|
|
Deletes a PipelineJob.
|
| DeleteTrainingPipeline |
|---|
|
Deletes a TrainingPipeline.
|
| GetPipelineJob |
|---|
|
Gets a PipelineJob.
|
| GetTrainingPipeline |
|---|
|
Gets a TrainingPipeline.
|
| ListPipelineJobs |
|---|
|
Lists PipelineJobs in a Location.
|
| ListTrainingPipelines |
|---|
|
Lists TrainingPipelines in a Location.
|
PredictionService
A service for online predictions and explanations.
| ChatCompletions |
|---|
|
Exposes an OpenAI-compatible endpoint for chat completions.
|
| CountTokens |
|---|
|
Perform a token counting.
|
| DirectPredict |
|---|
|
Perform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks.
|
| DirectRawPredict |
|---|
|
Perform an unary online prediction request to a gRPC model server for custom containers.
|
| Explain |
|---|
|
Perform an online explanation. If
|
| GenerateContent |
|---|
|
Generate content with multimodal inputs.
|
| Predict |
|---|
|
Perform an online prediction.
|
| RawPredict |
|---|
|
Perform an online prediction with an arbitrary HTTP payload. The response includes the following HTTP headers:
|
| ServerStreamingPredict |
|---|
|
Perform a server-side streaming online prediction request for Vertex LLM streaming.
|
| StreamDirectPredict |
|---|
|
Perform a streaming online prediction request to a gRPC model server for Vertex first-party products and frameworks.
|
| StreamDirectRawPredict |
|---|
|
Perform a streaming online prediction request to a gRPC model server for custom containers.
|
| StreamGenerateContent |
|---|
|
Generate content with multimodal inputs with streaming support.
|
| StreamRawPredict |
|---|
|
Perform a streaming online prediction with an arbitrary HTTP payload.
|
| StreamingPredict |
|---|
|
Perform a streaming online prediction request for Vertex first-party products and frameworks.
|
| StreamingRawPredict |
|---|
|
Perform a streaming online prediction request through gRPC.
|
ReasoningEngineExecutionService
A service for executing queries on Reasoning Engine.
| QueryReasoningEngine |
|---|
|
Queries using a reasoning engine.
|
| StreamQueryReasoningEngine |
|---|
|
Streams queries using a reasoning engine.
|
ReasoningEngineService
A service for managing Vertex AI's Reasoning Engines.
| CreateReasoningEngine |
|---|
|
Creates a reasoning engine.
|
| DeleteReasoningEngine |
|---|
|
Deletes a reasoning engine.
|
| GetReasoningEngine |
|---|
|
Gets a reasoning engine.
|
| ListReasoningEngines |
|---|
|
Lists reasoning engines in a location.
|
| UpdateReasoningEngine |
|---|
|
Updates a reasoning engine.
|
ScheduleService
A service for creating and managing Vertex AI's Schedule resources to periodically launch shceudled runs to make API calls.
| CreateSchedule |
|---|
|
Creates a Schedule.
|
| DeleteSchedule |
|---|
|
Deletes a Schedule.
|
| GetSchedule |
|---|
|
Gets a Schedule.
|
| ListSchedules |
|---|
|
Lists Schedules in a Location.
|
| PauseSchedule |
|---|
|
Pauses a Schedule. Will mark
|
| ResumeSchedule |
|---|
|
Resumes a paused Schedule to start scheduling new runs. Will mark When the Schedule is resumed, new runs will be scheduled starting from the next execution time after the current time based on the time_specification in the Schedule. If
|
| UpdateSchedule |
|---|
|
Updates an active or paused Schedule. When the Schedule is updated, new runs will be scheduled starting from the updated next execution time after the update time based on the time_specification in the updated Schedule. All unstarted runs before the update time will be skipped while already created runs will NOT be paused or canceled.
|
SpecialistPoolService
A service for creating and managing Customer SpecialistPools. When customers start Data Labeling jobs, they can reuse/create Specialist Pools to bring their own Specialists to label the data. Customers can add/remove Managers for the Specialist Pool on Cloud console, then Managers will get email notifications to manage Specialists and tasks on CrowdCompute console.
| CreateSpecialistPool |
|---|
|
Creates a SpecialistPool.
|
| DeleteSpecialistPool |
|---|
|
Deletes a SpecialistPool as well as all Specialists in the pool.
|
| GetSpecialistPool |
|---|
|
Gets a SpecialistPool.
|
| ListSpecialistPools |
|---|
|
Lists SpecialistPools in a Location.
|
| UpdateSpecialistPool |
|---|
|
Updates a SpecialistPool.
|
TensorboardService
TensorboardService
| BatchCreateTensorboardRuns |
|---|
|
Batch create TensorboardRuns.
|
| BatchCreateTensorboardTimeSeries |
|---|
|
Batch create TensorboardTimeSeries that belong to a TensorboardExperiment.
|
| BatchReadTensorboardTimeSeriesData |
|---|
|
Reads multiple TensorboardTimeSeries' data. The data point number limit is 1000 for scalars, 100 for tensors and blob references. If the number of data points stored is less than the limit, all data is returned. Otherwise, the number limit of data points is randomly selected from this time series and returned.
|
| CreateTensorboard |
|---|
|
Creates a Tensorboard.
|
| CreateTensorboardExperiment |
|---|
|
Creates a TensorboardExperiment.
|
| CreateTensorboardRun |
|---|
|
Creates a TensorboardRun.
|
| CreateTensorboardTimeSeries |
|---|
|
Creates a TensorboardTimeSeries.
|
| DeleteTensorboard |
|---|
|
Deletes a Tensorboard.
|
| DeleteTensorboardExperiment |
|---|
|
Deletes a TensorboardExperiment.
|
| DeleteTensorboardRun |
|---|
|
Deletes a TensorboardRun.
|
| DeleteTensorboardTimeSeries |
|---|
|
Deletes a TensorboardTimeSeries.
|
| ExportTensorboardTimeSeriesData |
|---|
|
Exports a TensorboardTimeSeries' data. Data is returned in paginated responses.
|
| GetTensorboard |
|---|
|
Gets a Tensorboard.
|
| GetTensorboardExperiment |
|---|
|
Gets a TensorboardExperiment.
|
| GetTensorboardRun |
|---|
|
Gets a TensorboardRun.
|
| GetTensorboardTimeSeries |
|---|
|
Gets a TensorboardTimeSeries.
|
| ListTensorboardExperiments |
|---|
|
Lists TensorboardExperiments in a Location.
|
| ListTensorboardRuns |
|---|
|
Lists TensorboardRuns in a Location.
|
| ListTensorboardTimeSeries |
|---|
|
Lists TensorboardTimeSeries in a Location.
|
| ListTensorboards |
|---|
|
Lists Tensorboards in a Location.
|
| ReadTensorboardBlobData |
|---|
|
Gets bytes of TensorboardBlobs. This is to allow reading blob data stored in consumer project's Cloud Storage bucket without users having to obtain Cloud Storage access permission.
|
| ReadTensorboardSize |
|---|
|
Returns the storage size for a given TensorBoard instance.
|
| ReadTensorboardTimeSeriesData |
|---|
|
Reads a TensorboardTimeSeries' data. By default, if the number of data points stored is less than 1000, all data is returned. Otherwise, 1000 data points is randomly selected from this time series and returned. This value can be changed by changing max_data_points, which can't be greater than 10k.
|
| ReadTensorboardUsage |
|---|
|
Returns a list of monthly active users for a given TensorBoard instance.
|
| UpdateTensorboard |
|---|
|
Updates a Tensorboard.
|
| UpdateTensorboardExperiment |
|---|
|
Updates a TensorboardExperiment.
|
| UpdateTensorboardRun |
|---|
|
Updates a TensorboardRun.
|
| UpdateTensorboardTimeSeries |
|---|
|
Updates a TensorboardTimeSeries.
|
| WriteTensorboardExperimentData |
|---|
|
Write time series data points of multiple TensorboardTimeSeries in multiple TensorboardRun's. If any data fail to be ingested, an error is returned.
|
| WriteTensorboardRunData |
|---|
|
Write time series data points into multiple TensorboardTimeSeries under a TensorboardRun. If any data fail to be ingested, an error is returned.
|
VertexRagDataService
A service for managing user data for RAG.
| CreateRagCorpus |
|---|
|
Creates a RagCorpus.
|
| DeleteRagCorpus |
|---|
|
Deletes a RagCorpus.
|
| DeleteRagFile |
|---|
|
Deletes a RagFile.
|
| GetRagCorpus |
|---|
|
Gets a RagCorpus.
|
| GetRagFile |
|---|
|
Gets a RagFile.
|
| ImportRagFiles |
|---|
|
Import files from Google Cloud Storage or Google Drive into a RagCorpus.
|
| ListRagCorpora |
|---|
|
Lists RagCorpora in a Location.
|
| ListRagFiles |
|---|
|
Lists RagFiles in a RagCorpus.
|
| UpdateRagCorpus |
|---|
|
Updates a RagCorpus.
|
VertexRagService
A service for retrieving relevant contexts.
| AugmentPrompt |
|---|
|
Given an input prompt, it returns augmented prompt from vertex rag store to guide LLM towards generating grounded responses.
|
| CorroborateContent |
|---|
|
Given an input text, it returns a score that evaluates the factuality of the text. It also extracts and returns claims from the text and provides supporting facts.
|
| RetrieveContexts |
|---|
|
Retrieves relevant contexts for a query.
|
VizierService
Vertex AI Vizier API.
Vertex AI Vizier is a service to solve blackbox optimization problems, such as tuning machine learning hyperparameters and searching over deep learning architectures.
| AddTrialMeasurement |
|---|
|
Adds a measurement of the objective metrics to a Trial. This measurement is assumed to have been taken before the Trial is complete.
|
| CheckTrialEarlyStoppingState |
|---|
|
Checks whether a Trial should stop or not. Returns a long-running operation. When the operation is successful, it will contain a
|
| CompleteTrial |
|---|
|
Marks a Trial as complete.
|
| CreateStudy |
|---|
|
Creates a Study. A resource name will be generated after creation of the Study.
|
| CreateTrial |
|---|
|
Adds a user provided Trial to a Study.
|
| DeleteStudy |
|---|
|
Deletes a Study.
|
| DeleteTrial |
|---|
|
Deletes a Trial.
|
| GetStudy |
|---|
|
Gets a Study by name.
|
| GetTrial |
|---|
|
Gets a Trial.
|
| ListOptimalTrials |
|---|
|
Lists the pareto-optimal Trials for multi-objective Study or the optimal Trials for single-objective Study. The definition of pareto-optimal can be checked in wiki page. https://en.wikipedia.org/wiki/Pareto_efficiency
|
| ListStudies |
|---|
|
Lists all the studies in a region for an associated project.
|
| ListTrials |
|---|
|
Lists the Trials associated with a Study.
|
| LookupStudy |
|---|
|
Looks a study up using the user-defined display_name field instead of the fully qualified resource name.
|
| StopTrial |
|---|
|
Stops a Trial.
|
| SuggestTrials |
|---|
|
Adds one or more Trials to a Study, with parameter values suggested by Vertex AI Vizier. Returns a long-running operation associated with the generation of Trial suggestions. When this long-running operation succeeds, it will contain a
|
AcceleratorType
Represents a hardware accelerator type.
| Enums | |
|---|---|
ACCELERATOR_TYPE_UNSPECIFIED |
Unspecified accelerator type, which means no accelerator. |
NVIDIA_TESLA_K80 |
Deprecated: Nvidia Tesla K80 GPU has reached end of support, see https://cloud.google.com/compute/docs/eol/k80-eol. |
NVIDIA_TESLA_P100 |
Nvidia Tesla P100 GPU. |
NVIDIA_TESLA_V100 |
Nvidia Tesla V100 GPU. |
NVIDIA_TESLA_P4 |
Nvidia Tesla P4 GPU. |
NVIDIA_TESLA_T4 |
Nvidia Tesla T4 GPU. |
NVIDIA_TESLA_A100 |
Nvidia Tesla A100 GPU. |
NVIDIA_A100_80GB |
Nvidia A100 80GB GPU. |
NVIDIA_L4 |
Nvidia L4 GPU. |
NVIDIA_H100_80GB |
Nvidia H100 80Gb GPU. |
NVIDIA_H100_MEGA_80GB |
Nvidia H100 Mega 80Gb GPU. |
TPU_V2 |
TPU v2. |
TPU_V3 |
TPU v3. |
TPU_V4_POD |
TPU v4. |
TPU_V5_LITEPOD |
TPU v5. |
AddContextArtifactsAndExecutionsRequest
Request message for MetadataService.AddContextArtifactsAndExecutions.
| Fields | |
|---|---|
context |
Required. The resource name of the Context that the Artifacts and Executions belong to. Format: |
artifacts[] |
The resource names of the Artifacts to attribute to the Context. Format: |
executions[] |
The resource names of the Executions to associate with the Context. Format: |
AddContextArtifactsAndExecutionsResponse
This type has no fields.
Response message for MetadataService.AddContextArtifactsAndExecutions.
AddContextChildrenRequest
Request message for MetadataService.AddContextChildren.
| Fields | |
|---|---|
context |
Required. The resource name of the parent Context. Format: |
child_contexts[] |
The resource names of the child Contexts. |
AddContextChildrenResponse
This type has no fields.
Response message for MetadataService.AddContextChildren.
AddExecutionEventsRequest
Request message for MetadataService.AddExecutionEvents.
| Fields | |
|---|---|
execution |
Required. The resource name of the Execution that the Events connect Artifacts with. Format: |
events[] |
The Events to create and add. |
AddExecutionEventsResponse
This type has no fields.
Response message for MetadataService.AddExecutionEvents.
AddTrialMeasurementRequest
Request message for VizierService.AddTrialMeasurement.
| Fields | |
|---|---|
trial_name |
Required. The name of the trial to add measurement. Format: |
measurement |
Required. The measurement to be added to a Trial. |
Annotation
Used to assign specific AnnotationSpec to a particular area of a DataItem or the whole part of the DataItem.
| Fields | |
|---|---|
name |
Output only. Resource name of the Annotation. |
payload_schema_uri |
Required. Google Cloud Storage URI points to a YAML file describing |
payload |
Required. The schema of the payload can be found in |
create_time |
Output only. Timestamp when this Annotation was created. |
update_time |
Output only. Timestamp when this Annotation was last updated. |
etag |
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
annotation_source |
Output only. The source of the Annotation. |
labels |
Optional. The labels with user-defined metadata to organize your Annotations. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Annotation(System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. Following system labels exist for each Annotation:
|
AnnotationSpec
Identifies a concept with which DataItems may be annotated with.
| Fields | |
|---|---|
name |
Output only. Resource name of the AnnotationSpec. |
display_name |
Required. The user-defined name of the AnnotationSpec. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
create_time |
Output only. Timestamp when this AnnotationSpec was created. |
update_time |
Output only. Timestamp when AnnotationSpec was last updated. |
etag |
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
ApiAuth
The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead.
| Fields | |
|---|---|
Union field auth_config. The auth config. auth_config can be only one of the following: |
|
api_key_config |
The API secret. |
ApiKeyConfig
The API secret.
| Fields | |
|---|---|
api_key_secret_version |
Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version} |
Artifact
Instance of a general artifact.
| Fields | |
|---|---|
name |
Output only. The resource name of the Artifact. |
display_name |
User provided display name of the Artifact. May be up to 128 Unicode characters. |
uri |
The uniform resource identifier of the artifact file. May be empty if there is no actual artifact file. |
etag |
An eTag used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
The labels with user-defined metadata to organize your Artifacts. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Artifact (System labels are excluded). |
create_time |
Output only. Timestamp when this Artifact was created. |
update_time |
Output only. Timestamp when this Artifact was last updated. |
state |
The state of this Artifact. This is a property of the Artifact, and does not imply or capture any ongoing process. This property is managed by clients (such as Vertex AI Pipelines), and the system does not prescribe or check the validity of state transitions. |
schema_title |
The title of the schema describing the metadata. Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store. |
schema_version |
The version of the schema in schema_name to use. Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store. |
metadata |
Properties of the Artifact. Top level metadata keys' heading and trailing spaces will be trimmed. The size of this field should not exceed 200KB. |
description |
Description of the Artifact |
State
Describes the state of the Artifact.
| Enums | |
|---|---|
STATE_UNSPECIFIED |
Unspecified state for the Artifact. |
PENDING |
A state used by systems like Vertex AI Pipelines to indicate that the underlying data item represented by this Artifact is being created. |
LIVE |
A state indicating that the Artifact should exist, unless something external to the system deletes it. |
ArtifactTypeSchema
The definition of a artifact type in MLMD.
| Fields | |
|---|---|
schema_version |
The schema version of the artifact. If the value is not set, it defaults to the latest version in the system. |
Union field
|
|
schema_title |
The name of the type. The format of the title must be: |
schema_uri |
Points to a YAML file stored on Cloud Storage describing the format. Deprecated. Use [PipelineArtifactTypeSchema.schema_title][] or [PipelineArtifactTypeSchema.instance_schema][] instead. |
instance_schema |
Contains a raw YAML string, describing the format of the properties of the type. |
AssignNotebookRuntimeOperationMetadata
Metadata information for NotebookService.AssignNotebookRuntime.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
progress_message |
A human-readable message that shows the intermediate progress details of NotebookRuntime. |
AssignNotebookRuntimeRequest
Request message for NotebookService.AssignNotebookRuntime.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to get the NotebookRuntime assignment. Format: |
notebook_runtime_template |
Required. The resource name of the NotebookRuntimeTemplate based on which a NotebookRuntime will be assigned (reuse or create a new one). |
notebook_runtime |
Required. Provide runtime specific information (e.g. runtime owner, notebook id) used for NotebookRuntime assignment. |
notebook_runtime_id |
Optional. User specified ID for the notebook runtime. |
Attribution
Attribution that explains a particular prediction output.
| Fields | |
|---|---|
baseline_output_value |
Output only. Model predicted output if the input instance is constructed from the baselines of all the features defined in If the Model's predicted output has multiple dimensions (rank > 1), this is the value in the output located by If there are multiple baselines, their output values are averaged. |
instance_output_value |
Output only. Model predicted output on the corresponding [explanation instance][ExplainRequest.instances]. The field name of the output is determined by the key in If the Model predicted output has multiple dimensions, this is the value in the output located by |
feature_attributions |
Output only. Attributions of each explained feature. Features are extracted from the The value is a struct, whose keys are the name of the feature. The values are how much the feature in the The format of the value is determined by the feature's input format:
The |
output_index[] |
Output only. The index that locates the explained prediction output. If the prediction output is a scalar value, output_index is not populated. If the prediction output has multiple dimensions, the length of the output_index list is the same as the number of dimensions of the output. The i-th element in output_index is the element index of the i-th dimension of the output vector. Indices start from 0. |
output_display_name |
Output only. The display name of the output identified by This field is only populated iff the Model predicts display names as a separate field along with the explained output. The predicted display name must has the same shape of the explained output, and can be located using output_index. |
approximation_error |
Output only. Error of
See this introduction for more information. |
output_name |
Output only. Name of the explain output. Specified as the key in |
AugmentPromptRequest
Request message for AugmentPrompt.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location from which to augment prompt. The users must have permission to make a call in the project. Format: |
contents[] |
Optional. Input content to augment, only text format is supported for now. |
model |
Optional. Metadata of the backend deployed model. |
Union field data_source. The data source for retrieving contexts. data_source can be only one of the following: |
|
vertex_rag_store |
Optional. Retrieves contexts from the Vertex RagStore. |
Model
Metadata of the backend deployed model.
| Fields | |
|---|---|
model |
Optional. The model that the user will send the augmented prompt for content generation. |
model_version |
Optional. The model version of the backend deployed model. |
AugmentPromptResponse
Response message for AugmentPrompt.
| Fields | |
|---|---|
augmented_prompt[] |
Augmented prompt, only text format is supported for now. |
facts[] |
Retrieved facts from RAG data sources. |
AuthConfig
Auth configuration to run the extension.
| Fields | |
|---|---|
auth_type |
Type of auth scheme. |
Union field
|
|
api_key_config |
Config for API key auth. |
http_basic_auth_config |
Config for HTTP Basic auth. |
google_service_account_config |
Config for Google Service Account auth. |
oauth_config |
Config for user oauth. |
oidc_config |
Config for user OIDC auth. |
ApiKeyConfig
Config for authentication with API key.
| Fields | |
|---|---|
name |
Optional. The parameter name of the API key. E.g. If the API request is "https://example.com/act?api_key= |
api_key_secret |
Optional. The name of the SecretManager secret version resource storing the API key. Format:
|
http_element_location |
Optional. The location of the API key. |
GoogleServiceAccountConfig
Config for Google Service Account Authentication.
| Fields | |
|---|---|
service_account |
Optional. The service account that the extension execution service runs as.
|
HttpBasicAuthConfig
Config for HTTP Basic Authentication.
| Fields | |
|---|---|
credential_secret |
Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format:
|
OauthConfig
Config for user oauth.
| Fields | |
|---|---|
Union field
|
|
access_token |
Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. |
service_account |
The service account used to generate access tokens for executing the Extension.
|
OidcConfig
Config for user OIDC auth.
| Fields | |
|---|---|
Union field
|
|
id_token |
OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. |
service_account |
The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc).
|
AuthType
Type of Auth.
| Enums | |
|---|---|
AUTH_TYPE_UNSPECIFIED |
|
NO_AUTH |
No Auth. |
API_KEY_AUTH |
API Key Auth. |
HTTP_BASIC_AUTH |
HTTP Basic Auth. |
GOOGLE_SERVICE_ACCOUNT_AUTH |
Google Service Account Auth. |
OAUTH |
OAuth auth. |
OIDC_AUTH |
OpenID Connect (OIDC) Auth. |
AutomaticResources
A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines.
| Fields | |
|---|---|
min_replica_count |
Immutable. The minimum number of replicas that will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to |
max_replica_count |
Immutable. The maximum number of replicas that may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale to that many replicas is guaranteed (barring service outages). If traffic increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number. |
AutoraterConfig
The configs for autorater. This is applicable to both EvaluateInstances and EvaluateDataset.
| Fields | |
|---|---|
autorater_model |
Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: Tuned model endpoint format: |
sampling_count |
Optional. Number of samples for each instance in the dataset. If not specified, the default is 4. Minimum value is 1, maximum value is 32. |
flip_enabled |
Optional. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias. |
AutoscalingMetricSpec
The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
| Fields | |
|---|---|
metric_name |
Required. The resource metric name. Supported metrics:
|
target |
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided. |
AvroSource
The storage details for Avro input content.
| Fields | |
|---|---|
gcs_source |
Required. Google Cloud Storage location. |
BatchCancelPipelineJobsOperationMetadata
Runtime operation information for PipelineService.BatchCancelPipelineJobs.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
BatchCancelPipelineJobsRequest
Request message for PipelineService.BatchCancelPipelineJobs.
| Fields | |
|---|---|
parent |
Required. The name of the PipelineJobs' parent resource. Format: |
names[] |
Required. The names of the PipelineJobs to cancel. A maximum of 32 PipelineJobs can be cancelled in a batch. Format: |
BatchCancelPipelineJobsResponse
Response message for PipelineService.BatchCancelPipelineJobs.
| Fields | |
|---|---|
pipeline_jobs[] |
PipelineJobs cancelled. |
BatchCreateFeaturesOperationMetadata
Details of operations that perform batch create Features.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Feature. |
BatchCreateFeaturesRequest
Request message for FeaturestoreService.BatchCreateFeatures. Request message for FeatureRegistryService.BatchCreateFeatures.
| Fields | |
|---|---|
parent |
Required. The resource name of the EntityType/FeatureGroup to create the batch of Features under. Format: |
requests[] |
Required. The request message specifying the Features to create. All Features must be created under the same parent EntityType / FeatureGroup. The |
BatchCreateFeaturesResponse
Response message for FeaturestoreService.BatchCreateFeatures.
| Fields | |
|---|---|
features[] |
The Features created. |
BatchCreateTensorboardRunsRequest
Request message for TensorboardService.BatchCreateTensorboardRuns.
| Fields | |
|---|---|
parent |
Required. The resource name of the TensorboardExperiment to create the TensorboardRuns in. Format: |
requests[] |
Required. The request message specifying the TensorboardRuns to create. A maximum of 1000 TensorboardRuns can be created in a batch. |
BatchCreateTensorboardRunsResponse
Response message for TensorboardService.BatchCreateTensorboardRuns.
| Fields | |
|---|---|
tensorboard_runs[] |
The created TensorboardRuns. |
BatchCreateTensorboardTimeSeriesRequest
Request message for TensorboardService.BatchCreateTensorboardTimeSeries.
| Fields | |
|---|---|
parent |
Required. The resource name of the TensorboardExperiment to create the TensorboardTimeSeries in. Format: |
requests[] |
Required. The request message specifying the TensorboardTimeSeries to create. A maximum of 1000 TensorboardTimeSeries can be created in a batch. |
BatchCreateTensorboardTimeSeriesResponse
Response message for TensorboardService.BatchCreateTensorboardTimeSeries.
| Fields | |
|---|---|
tensorboard_time_series[] |
The created TensorboardTimeSeries. |
BatchDedicatedResources
A description of resources that are used for performing batch operations, are dedicated to a Model, and need manual configuration.
| Fields | |
|---|---|
machine_spec |
Required. Immutable. The specification of a single machine. |
starting_replica_count |
Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than |
max_replica_count |
Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10. |
BatchDeletePipelineJobsRequest
Request message for PipelineService.BatchDeletePipelineJobs.
| Fields | |
|---|---|
parent |
Required. The name of the PipelineJobs' parent resource. Format: |
names[] |
Required. The names of the PipelineJobs to delete. A maximum of 32 PipelineJobs can be deleted in a batch. Format: |
BatchDeletePipelineJobsResponse
Response message for PipelineService.BatchDeletePipelineJobs.
| Fields | |
|---|---|
pipeline_jobs[] |
PipelineJobs deleted. |
BatchImportEvaluatedAnnotationsRequest
Request message for ModelService.BatchImportEvaluatedAnnotations
| Fields | |
|---|---|
parent |
Required. The name of the parent ModelEvaluationSlice resource. Format: |
evaluated_annotations[] |
Required. Evaluated annotations resource to be imported. |
BatchImportEvaluatedAnnotationsResponse
Response message for ModelService.BatchImportEvaluatedAnnotations
| Fields | |
|---|---|
imported_evaluated_annotations_count |
Output only. Number of EvaluatedAnnotations imported. |
BatchImportModelEvaluationSlicesRequest
Request message for ModelService.BatchImportModelEvaluationSlices
| Fields | |
|---|---|
parent |
Required. The name of the parent ModelEvaluation resource. Format: |
model_evaluation_slices[] |
Required. Model evaluation slice resource to be imported. |
BatchImportModelEvaluationSlicesResponse
Response message for ModelService.BatchImportModelEvaluationSlices
| Fields | |
|---|---|
imported_model_evaluation_slices[] |
Output only. List of imported |
BatchMigrateResourcesOperationMetadata
Runtime operation information for MigrationService.BatchMigrateResources.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
partial_results[] |
Partial results that reflect the latest migration operation progress. |
PartialResult
Represents a partial result in batch migration operation for one MigrateResourceRequest.
| Fields | |
|---|---|
request |
It's the same as the value in |
Union field result. If the resource's migration is ongoing, none of the result will be set. If the resource's migration is finished, either error or one of the migrated resource name will be filled. result can be only one of the following: |
|
error |
The error result of the migration request in case of failure. |
model |
Migrated model resource name. |
dataset |
Migrated dataset resource name. |
BatchMigrateResourcesRequest
Request message for MigrationService.BatchMigrateResources.
| Fields | |
|---|---|
parent |
Required. The location of the migrated resource will live in. Format: |
migrate_resource_requests[] |
Required. The request messages specifying the resources to migrate. They must be in the same location as the destination. Up to 50 resources can be migrated in one batch. |
BatchMigrateResourcesResponse
Response message for MigrationService.BatchMigrateResources.
| Fields | |
|---|---|
migrate_resource_responses[] |
Successfully migrated resources. |
BatchPredictionJob
A job that uses a Model to produce predictions on multiple input instances. If predictions for significant portion of the instances fail, the job may finish without attempting predictions for all remaining instances.
| Fields | |
|---|---|
name |
Output only. Resource name of the BatchPredictionJob. |
display_name |
Required. The user-defined name of this BatchPredictionJob. |
model |
The name of the Model resource that produces the predictions via this job, must share the same ancestor Location. Starting this job has no impact on any existing deployments of the Model and their resources. Exactly one of model and unmanaged_container_model must be set. The model resource name may contain version id or version alias to specify the version. Example: The model resource could also be a publisher model. Example: |
model_version_id |
Output only. The version ID of the Model that produces the predictions via this job. |
unmanaged_container_model |
Contains model information necessary to perform batch prediction without requiring uploading to model registry. Exactly one of model and unmanaged_container_model must be set. |
input_config |
Required. Input configuration of the instances on which predictions are performed. The schema of any single instance may be specified via the |
instance_config |
Configuration for how to convert batch prediction input instances to the prediction instances that are sent to the Model. |
model_parameters |
The parameters that govern the predictions. The schema of the parameters may be specified via the |
output_config |
Required. The Configuration specifying where output predictions should be written. The schema of any single prediction may be specified as a concatenation of |
dedicated_resources |
The config of resources used by the Model during the batch prediction. If the Model |
service_account |
The service account that the DeployedModel's container runs as. If not specified, a system generated one will be used, which has minimal permissions and the custom container, if used, may not have enough permission to access other Google Cloud resources. Users deploying the Model must have the |
manual_batch_tuning_parameters |
Immutable. Parameters configuring the batch behavior. Currently only applicable when |
generate_explanation |
Generate explanation with the batch prediction results. When set to
If this field is set to true, either the |
explanation_spec |
Explanation configuration for this BatchPredictionJob. Can be specified only if This value overrides the value of |
output_info |
Output only. Information further describing the output of this job. |
state |
Output only. The detailed state of the job. |
error |
Output only. Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED. |
partial_failures[] |
Output only. Partial failures encountered. For example, single files that can't be read. This field never exceeds 20 entries. Status details fields contain standard Google Cloud error details. |
resources_consumed |
Output only. Information about resources that had been consumed by this job. Provided in real time at best effort basis, as well as a final value once the job completes. Note: This field currently may be not populated for batch predictions that use AutoML Models. |
completion_stats |
Output only. Statistics on completed and failed prediction instances. |
create_time |
Output only. Time when the BatchPredictionJob was created. |
start_time |
Output only. Time when the BatchPredictionJob for the first time entered the |
end_time |
Output only. Time when the BatchPredictionJob entered any of the following states: |
update_time |
Output only. Time when the BatchPredictionJob was most recently updated. |
labels |
The labels with user-defined metadata to organize BatchPredictionJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
encryption_spec |
Customer-managed encryption key options for a BatchPredictionJob. If this is set, then all resources created by the BatchPredictionJob will be encrypted with the provided encryption key. |
model_monitoring_config |
Model monitoring config will be used for analysis model behaviors, based on the input and output to the batch prediction job, as well as the provided training dataset. |
model_monitoring_stats_anomalies[] |
Get batch prediction job monitoring statistics. |
model_monitoring_status |
Output only. The running status of the model monitoring pipeline. |
disable_container_logging |
For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send User can disable container logging by setting this flag to true. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
InputConfig
Configures the input to BatchPredictionJob. See Model.supported_input_storage_formats for Model's supported input formats, and how instances should be expressed via any of them.
| Fields | |
|---|---|
instances_format |
Required. The format in which instances are given, must be one of the |
Union field source. Required. The source of the input. source can be only one of the following: |
|
gcs_source |
The Cloud Storage location for the input instances. |
bigquery_source |
The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored. |
InstanceConfig
Configuration defining how to transform batch prediction input instances to the instances that the Model accepts.
| Fields | |
|---|---|
instance_type |
The format of the instance that the Model accepts. Vertex AI will convert compatible Supported values are:
If not specified, Vertex AI converts the batch prediction input as follows:
|
key_field |
The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in
The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. |
included_fields[] |
Fields that will be included in the prediction instance that is sent to the Model. If When included_fields is populated, The input must be JSONL with objects at each line, BigQuery or TfRecord. |
excluded_fields[] |
Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if When excluded_fields is populated, The input must be JSONL with objects at each line, BigQuery or TfRecord. |
OutputConfig
Configures the output of BatchPredictionJob. See Model.supported_output_storage_formats for supported output formats, and how predictions are expressed via any of them.
| Fields | |
|---|---|
predictions_format |
Required. The format in which Vertex AI gives the predictions, must be one of the |
Union field destination. Required. The destination of the output. destination can be only one of the following: |
|
gcs_destination |
The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is |
bigquery_destination |
The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name |
OutputInfo
Further describes this job's output. Supplements output_config.
| Fields | |
|---|---|
bigquery_output_table |
Output only. The name of the BigQuery table created, in |
Union field output_location. The output location into which prediction output is written. output_location can be only one of the following: |
|
gcs_output_directory |
Output only. The full path of the Cloud Storage directory created, into which the prediction output is written. |
bigquery_output_dataset |
Output only. The path of the BigQuery dataset created, in |
BatchReadFeatureValuesOperationMetadata
Details of operations that batch reads Feature values.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Featurestore batch read Features values. |
BatchReadFeatureValuesRequest
Request message for FeaturestoreService.BatchReadFeatureValues.
| Fields | |
|---|---|
featurestore |
Required. The resource name of the Featurestore from which to query Feature values. Format: |
destination |
Required. Specifies output location and format. |
pass_through_fields[] |
When not empty, the specified fields in the *_read_instances source will be joined as-is in the output, in addition to those fields from the Featurestore Entity. For BigQuery source, the type of the pass-through values will be automatically inferred. For CSV source, the pass-through values will be passed as opaque bytes. |
entity_type_specs[] |
Required. Specifies EntityType grouping Features to read values of and settings. |
start_time |
Optional. Excludes Feature values with feature generation timestamp before this timestamp. If not set, retrieve oldest values kept in Feature Store. Timestamp, if present, must not have higher than millisecond precision. |
Union field
|
|
csv_read_instances |
Each read instance consists of exactly one read timestamp and one or more entity IDs identifying entities of the corresponding EntityTypes whose Features are requested. Each output instance contains Feature values of requested entities concatenated together as of the read time. An example read instance may be An example output instance may be Timestamp in each read instance must be millisecond-aligned.
The columns can be in any order. Values in the timestamp column must use the RFC 3339 format, e.g. |
bigquery_read_instances |
Similar to csv_read_instances, but from BigQuery source. |
EntityTypeSpec
Selects Features of an EntityType to read values of and specifies read settings.
| Fields | |
|---|---|
entity_type_id |
Required. ID of the EntityType to select Features. The EntityType id is the |
feature_selector |
Required. Selectors choosing which Feature values to read from the EntityType. |
settings[] |
Per-Feature settings for the batch read. |
PassThroughField
Describe pass-through fields in read_instance source.
| Fields | |
|---|---|
field_name |
Required. The name of the field in the CSV header or the name of the column in BigQuery table. The naming restriction is the same as |
BatchReadFeatureValuesResponse
This type has no fields.
Response message for FeaturestoreService.BatchReadFeatureValues.
BatchReadTensorboardTimeSeriesDataRequest
Request message for TensorboardService.BatchReadTensorboardTimeSeriesData.
| Fields | |
|---|---|
tensorboard |
Required. The resource name of the Tensorboard containing TensorboardTimeSeries to read data from. Format: |
time_series[] |
Required. The resource names of the TensorboardTimeSeries to read data from. Format: |
BatchReadTensorboardTimeSeriesDataResponse
Response message for TensorboardService.BatchReadTensorboardTimeSeriesData.
| Fields | |
|---|---|
time_series_data[] |
The returned time series data. |
BigQueryDestination
The BigQuery location for the output content.
| Fields | |
|---|---|
output_uri |
Required. BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms:
|
BigQuerySource
The BigQuery location for the input content.
| Fields | |
|---|---|
input_uri |
Required. BigQuery URI to a table, up to 2000 characters long. Accepted forms:
|
BleuInput
Input for bleu metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for bleu score metric. |
instances[] |
Required. Repeated bleu instances. |
BleuInstance
Spec for bleu instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Required. Ground truth used to compare against the prediction. |
BleuMetricValue
Bleu metric value for an instance.
| Fields | |
|---|---|
score |
Output only. Bleu score. |
BleuResults
Results for bleu metric.
| Fields | |
|---|---|
bleu_metric_values[] |
Output only. Bleu metric values. |
BleuSpec
Spec for bleu score metric - calculates the precision of n-grams in the prediction as compared to reference - returns a score ranging between 0 to 1.
| Fields | |
|---|---|
use_effective_order |
Optional. Whether to use_effective_order to compute bleu score. |
Blob
Content blob.
| Fields | |
|---|---|
mime_type |
Required. The IANA standard MIME type of the source data. |
data |
Required. Raw bytes. |
BlurBaselineConfig
Config for blur baseline.
When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
| Fields | |
|---|---|
max_blur_sigma |
The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline. |
BoolArray
A list of boolean values.
| Fields | |
|---|---|
values[] |
A list of bool values. |
CachedContent
A resource used in LLM queries for users to explicitly specify what to cache and how to cache.
| Fields | |
|---|---|
name |
Immutable. Identifier. The server-generated resource name of the cached content Format: projects/{project}/locations/{location}/cachedContents/{cached_content} |
display_name |
Optional. Immutable. The user-generated meaningful display name of the cached content. |
model |
Immutable. The name of the |
system_instruction |
Optional. Input only. Immutable. Developer set system instruction. Currently, text only |
contents[] |
Optional. Input only. Immutable. The content to cache |
tools[] |
Optional. Input only. Immutable. A list of |
tool_config |
Optional. Input only. Immutable. Tool config. This config is shared for all tools |
create_time |
Output only. Creation time of the cache entry. |
update_time |
Output only. When the cache entry was last updated in UTC time. |
usage_metadata |
Output only. Metadata on the usage of the cached content. |
Union field expiration. Expiration time of the cached content. expiration can be only one of the following: |
|
expire_time |
Timestamp of when this resource is considered expired. This is always provided on output, regardless of what was sent on input. |
ttl |
Input only. The TTL for this resource. The expiration time is computed: now + TTL. |
UsageMetadata
Metadata on the usage of the cached content.
| Fields | |
|---|---|
total_token_count |
Total number of tokens that the cached content consumes. |
text_count |
Number of text characters. |
image_count |
Number of images. |
video_duration_seconds |
Duration of video in seconds. |
audio_duration_seconds |
Duration of audio in seconds. |
CancelBatchPredictionJobRequest
Request message for JobService.CancelBatchPredictionJob.
| Fields | |
|---|---|
name |
Required. The name of the BatchPredictionJob to cancel. Format: |
CancelCustomJobRequest
Request message for JobService.CancelCustomJob.
| Fields | |
|---|---|
name |
Required. The name of the CustomJob to cancel. Format: |
CancelHyperparameterTuningJobRequest
Request message for JobService.CancelHyperparameterTuningJob.
| Fields | |
|---|---|
name |
Required. The name of the HyperparameterTuningJob to cancel. Format: |
CancelPipelineJobRequest
Request message for PipelineService.CancelPipelineJob.
| Fields | |
|---|---|
name |
Required. The name of the PipelineJob to cancel. Format: |
CancelTrainingPipelineRequest
Request message for PipelineService.CancelTrainingPipeline.
| Fields | |
|---|---|
name |
Required. The name of the TrainingPipeline to cancel. Format: |
CancelTuningJobRequest
Request message for GenAiTuningService.CancelTuningJob.
| Fields | |
|---|---|
name |
Required. The name of the TuningJob to cancel. Format: |
Candidate
A response candidate generated from the model.
| Fields | |
|---|---|
index |
Output only. Index of the candidate. |
content |
Output only. Content parts of the candidate. |
avg_logprobs |
Output only. Average log probability score of the candidate. |
logprobs_result |
Output only. Log-likelihood scores for the response tokens and top tokens |
finish_reason |
Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens. |
safety_ratings[] |
Output only. List of ratings for the safety of a response candidate. There is at most one rating per category. |
citation_metadata |
Output only. Source attribution of the generated content. |
grounding_metadata |
Output only. Metadata specifies sources used to ground generated content. |
finish_message |
Output only. Describes the reason the mode stopped generating tokens in more detail. This is only filled when |
FinishReason
The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
| Enums | |
|---|---|
FINISH_REASON_UNSPECIFIED |
The finish reason is unspecified. |
STOP |
Token generation reached a natural stopping point or a configured stop sequence. |
MAX_TOKENS |
Token generation reached the configured maximum output tokens. |
SAFETY |
Token generation stopped because the content potentially contains safety violations. NOTE: When streaming, content is empty if content filters blocks the output. |
RECITATION |
The token generation stopped because of potential recitation. |
OTHER |
All other reasons that stopped the token generation. |
BLOCKLIST |
Token generation stopped because the content contains forbidden terms. |
PROHIBITED_CONTENT |
Token generation stopped for potentially containing prohibited content. |
SPII |
Token generation stopped because the content potentially contains Sensitive Personally Identifiable Information (SPII). |
MALFORMED_FUNCTION_CALL |
The function call generated by the model is invalid. |
ChatCompletionsRequest
Request message for [PredictionService.ChatCompletions]
| Fields | |
|---|---|
endpoint |
Required. The name of the endpoint requested to serve the prediction. Format: |
http_body |
Optional. The prediction input. Supports HTTP headers and arbitrary data payload. |
CheckTrialEarlyStoppingStateMetatdata
This message will be placed in the metadata field of a google.longrunning.Operation associated with a CheckTrialEarlyStoppingState request.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for suggesting Trials. |
study |
The name of the Study that the Trial belongs to. |
trial |
The Trial name. |
CheckTrialEarlyStoppingStateRequest
Request message for VizierService.CheckTrialEarlyStoppingState.
| Fields | |
|---|---|
trial_name |
Required. The Trial's name. Format: |
CheckTrialEarlyStoppingStateResponse
Response message for VizierService.CheckTrialEarlyStoppingState.
| Fields | |
|---|---|
should_stop |
True if the Trial should stop. |
Citation
Source attributions for content.
| Fields | |
|---|---|
start_index |
Output only. Start index into the content. |
end_index |
Output only. End index into the content. |
uri |
Output only. Url reference of the attribution. |
title |
Output only. Title of the attribution. |
license |
Output only. License of the attribution. |
publication_date |
Output only. Publication date of the attribution. |
CitationMetadata
A collection of source attributions for a piece of content.
| Fields | |
|---|---|
citations[] |
Output only. List of citations. |
Claim
Claim that is extracted from the input text and facts that support it.
| Fields | |
|---|---|
fact_indexes[] |
Indexes of the facts supporting this claim. |
start_index |
Index in the input text where the claim starts (inclusive). |
end_index |
Index in the input text where the claim ends (exclusive). |
score |
Confidence score of this corroboration. |
ClientConnectionConfig
Configurations (e.g. inference timeout) that are applied on your endpoints.
| Fields | |
|---|---|
inference_timeout |
Customizable online prediction request timeout. |
CodeExecutionResult
Result of executing the [ExecutableCode].
Always follows a part containing the [ExecutableCode].
| Fields | |
|---|---|
outcome |
Required. Outcome of the code execution. |
output |
Optional. Contains stdout when code execution is successful, stderr or other description otherwise. |
Outcome
Enumeration of possible outcomes of the code execution.
| Enums | |
|---|---|
OUTCOME_UNSPECIFIED |
Unspecified status. This value should not be used. |
OUTCOME_OK |
Code execution completed successfully. |
OUTCOME_FAILED |
Code execution finished but with a failure. stderr should contain the reason. |
OUTCOME_DEADLINE_EXCEEDED |
Code execution ran for too long, and was cancelled. There may or may not be a partial output present. |
CoherenceInput
Input for coherence metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for coherence score metric. |
instance |
Required. Coherence instance. |
CoherenceInstance
Spec for coherence instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
CoherenceResult
Spec for coherence result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for coherence score. |
score |
Output only. Coherence score. |
confidence |
Output only. Confidence for coherence score. |
CoherenceSpec
Spec for coherence score metric.
| Fields | |
|---|---|
version |
Optional. Which version to use for evaluation. |
CometInput
Input for Comet metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for comet metric. |
instance |
Required. Comet instance. |
CometInstance
Spec for Comet instance - The fields used for evaluation are dependent on the comet version.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Optional. Ground truth used to compare against the prediction. |
source |
Optional. Source text in original language. |
CometResult
Spec for Comet result - calculates the comet score for the given instance using the version specified in the spec.
| Fields | |
|---|---|
score |
Output only. Comet score. Range depends on version. |
CometSpec
Spec for Comet metric.
| Fields | |
|---|---|
source_language |
Optional. Source language in BCP-47 format. |
target_language |
Optional. Target language in BCP-47 format. Covers both prediction and reference. |
version |
Required. Which version to use for evaluation. |
CometVersion
Comet version options.
| Enums | |
|---|---|
COMET_VERSION_UNSPECIFIED |
Comet version unspecified. |
COMET_22_SRC_REF |
Comet 22 for translation + source + reference (source-reference-combined). |
CompleteTrialRequest
Request message for VizierService.CompleteTrial.
| Fields | |
|---|---|
name |
Required. The Trial's name. Format: |
final_measurement |
Optional. If provided, it will be used as the completed Trial's final_measurement; Otherwise, the service will auto-select a previously reported measurement as the final-measurement |
trial_infeasible |
Optional. True if the Trial cannot be run with the given Parameter, and final_measurement will be ignored. |
infeasible_reason |
Optional. A human readable reason why the trial was infeasible. This should only be provided if |
CompletionStats
Success and error statistics of processing multiple entities (for example, DataItems or structured data rows) in batch.
| Fields | |
|---|---|
successful_count |
Output only. The number of entities that had been processed successfully. |
failed_count |
Output only. The number of entities for which any error was encountered. |
incomplete_count |
Output only. In cases when enough errors are encountered a job, pipeline, or operation may be failed as a whole. Below is the number of entities for which the processing had not been finished (either in successful or failed state). Set to -1 if the number is unknown (for example, the operation failed before the total entity number could be collected). |
successful_forecast_point_count |
Output only. The number of the successful forecast points that are generated by the forecasting model. This is ONLY used by the forecasting batch prediction. |
ComputeTokensRequest
Request message for ComputeTokens RPC call.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to get lists of tokens and token ids. |
instances[] |
Optional. The instances that are the input to token computing API call. Schema is identical to the prediction schema of the text model, even for the non-text models, like chat models, or Codey models. |
model |
Optional. The name of the publisher model requested to serve the prediction. Format: projects/{project}/locations/{location}/publishers/*/models/* |
contents[] |
Optional. Input content. |
ComputeTokensResponse
Response message for ComputeTokens RPC call.
| Fields | |
|---|---|
tokens_info[] |
Lists of tokens info from the input. A ComputeTokensRequest could have multiple instances with a prompt in each instance. We also need to return lists of tokens info for the request with multiple instances. |
ContainerRegistryDestination
The Container Registry location for the container image.
| Fields | |
|---|---|
output_uri |
Required. Container Registry URI of a container image. Only Google Container Registry and Artifact Registry are supported now. Accepted forms:
If a tag is not specified, "latest" will be used as the default tag. |
ContainerSpec
The spec of a Container.
| Fields | |
|---|---|
image_uri |
Required. The URI of a container image in the Container Registry that is to be run on each worker replica. |
command[] |
The command to be invoked when the container is started. It overrides the entrypoint instruction in Dockerfile when provided. |
args[] |
The arguments to be passed when starting the container. |
env[] |
Environment variables to be passed to the container. Maximum limit is 100. |
Content
The base structured datatype containing multi-part content of a message.
A Content includes a role field designating the producer of the Content and a parts field containing multi-part data that contains the content of the message turn.
| Fields | |
|---|---|
role |
Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset. |
parts[] |
Required. Ordered |
Context
Instance of a general context.
| Fields | |
|---|---|
name |
Immutable. The resource name of the Context. |
display_name |
User provided display name of the Context. May be up to 128 Unicode characters. |
etag |
An eTag used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
The labels with user-defined metadata to organize your Contexts. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Context (System labels are excluded). |
create_time |
Output only. Timestamp when this Context was created. |
update_time |
Output only. Timestamp when this Context was last updated. |
parent_contexts[] |
Output only. A list of resource names of Contexts that are parents of this Context. A Context may have at most 10 parent_contexts. |
schema_title |
The title of the schema describing the metadata. Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store. |
schema_version |
The version of the schema in schema_name to use. Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store. |
metadata |
Properties of the Context. Top level metadata keys' heading and trailing spaces will be trimmed. The size of this field should not exceed 200KB. |
description |
Description of the Context |
CopyModelOperationMetadata
Details of ModelService.CopyModel operation.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
CopyModelRequest
Request message for ModelService.CopyModel.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location into which to copy the Model. Format: |
source_model |
Required. The resource name of the Model to copy. That Model must be in the same Project. Format: |
encryption_spec |
Customer-managed encryption key options. If this is set, then the Model copy will be encrypted with the provided encryption key. |
Union field destination_model. If both fields are unset, a new Model will be created with a generated ID. destination_model can be only one of the following: |
|
model_id |
Optional. Copy source_model into a new Model with this ID. The ID will become the final component of the model resource name. This value may be up to 63 characters, and valid characters are |
parent_model |
Optional. Specify this field to copy source_model into this existing Model as a new version. Format: |
CopyModelResponse
Response message of ModelService.CopyModel operation.
| Fields | |
|---|---|
model |
The name of the copied Model resource. Format: |
model_version_id |
Output only. The version ID of the model that is copied. |
CorpusStatus
RagCorpus status.
| Fields | |
|---|---|
state |
Output only. RagCorpus life state. |
error_status |
Output only. Only when the |
State
RagCorpus life state.
| Enums | |
|---|---|
UNKNOWN |
This state is not supposed to happen. |
INITIALIZED |
RagCorpus resource entry is initialized, but hasn't done validation. |
ACTIVE |
RagCorpus is provisioned successfully and is ready to serve. |
ERROR |
RagCorpus is in a problematic situation. See error_message field for details. |
CorroborateContentRequest
Request message for CorroborateContent.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location from which to corroborate text. The users must have permission to make a call in the project. Format: |
facts[] |
Optional. Facts used to generate the text can also be used to corroborate the text. |
parameters |
Optional. Parameters that can be set to override default settings per request. |
content |
Optional. Input content to corroborate, only text format is supported for now. |
Parameters
Parameters that can be overrided per request.
| Fields | |
|---|---|
citation_threshold |
Optional. Only return claims with citation score larger than the threshold. |
CorroborateContentResponse
Response message for CorroborateContent.
| Fields | |
|---|---|
claims[] |
Claims that are extracted from the input content and facts that support the claims. |
corroboration_score |
Confidence score of corroborating content. Value is [0,1] with 1 is the most confidence. |
CountTokensRequest
Request message for PredictionService.CountTokens.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to perform token counting. Format: |
model |
Optional. The name of the publisher model requested to serve the prediction. Format: |
instances[] |
Optional. The instances that are the input to token counting call. Schema is identical to the prediction schema of the underlying model. |
contents[] |
Optional. Input content. |
tools[] |
Optional. A list of A |
system_instruction |
Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. |
generation_config |
Optional. Generation config that the model will use to generate the response. |
CountTokensResponse
Response message for PredictionService.CountTokens.
| Fields | |
|---|---|
total_tokens |
The total number of tokens counted across all instances from the request. |
total_billable_characters |
The total number of billable characters counted across all instances from the request. |
prompt_tokens_details[] |
Output only. List of modalities that were processed in the request input. |
CreateArtifactRequest
Request message for MetadataService.CreateArtifact.
| Fields | |
|---|---|
parent |
Required. The resource name of the MetadataStore where the Artifact should be created. Format: |
artifact |
Required. The Artifact to create. |
artifact_id |
The {artifact} portion of the resource name with the format: |
CreateBatchPredictionJobRequest
Request message for JobService.CreateBatchPredictionJob.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the BatchPredictionJob in. Format: |
batch_prediction_job |
Required. The BatchPredictionJob to create. |
CreateCachedContentRequest
Request message for GenAiCacheService.CreateCachedContent.
| Fields | |
|---|---|
parent |
Required. The parent resource where the cached content will be created |
cached_content |
Required. The cached content to create |
CreateContextRequest
Request message for MetadataService.CreateContext.
| Fields | |
|---|---|
parent |
Required. The resource name of the MetadataStore where the Context should be created. Format: |
context |
Required. The Context to create. |
context_id |
The {context} portion of the resource name with the format: |
CreateCustomJobRequest
Request message for JobService.CreateCustomJob.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the CustomJob in. Format: |
custom_job |
Required. The CustomJob to create. |
CreateDatasetOperationMetadata
Runtime operation information for DatasetService.CreateDataset.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
CreateDatasetRequest
Request message for DatasetService.CreateDataset.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the Dataset in. Format: |
dataset |
Required. The Dataset to create. |
CreateDatasetVersionOperationMetadata
Runtime operation information for DatasetService.CreateDatasetVersion.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
CreateDatasetVersionRequest
Request message for DatasetService.CreateDatasetVersion.
| Fields | |
|---|---|
parent |
Required. The name of the Dataset resource. Format: |
dataset_version |
Required. The version to be created. The same CMEK policies with the original Dataset will be applied the dataset version. So here we don't need to specify the EncryptionSpecType here. |
CreateDeploymentResourcePoolOperationMetadata
Runtime operation information for CreateDeploymentResourcePool method.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
CreateDeploymentResourcePoolRequest
Request message for CreateDeploymentResourcePool method.
| Fields | |
|---|---|
parent |
Required. The parent location resource where this DeploymentResourcePool will be created. Format: |
deployment_resource_pool |
Required. The DeploymentResourcePool to create. |
deployment_resource_pool_id |
Required. The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are |
CreateEndpointOperationMetadata
Runtime operation information for EndpointService.CreateEndpoint.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
CreateEndpointRequest
Request message for EndpointService.CreateEndpoint.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the Endpoint in. Format: |
endpoint |
Required. The Endpoint to create. |
endpoint_id |
Immutable. The ID to use for endpoint, which will become the final component of the endpoint resource name. If not provided, Vertex AI will generate a value for this ID. If the first character is a letter, this value may be up to 63 characters, and valid characters are If the first character is a number, this value may be up to 9 characters, and valid characters are When using HTTP/JSON, this field is populated based on a query string argument, such as |
CreateEntityTypeOperationMetadata
Details of operations that perform create EntityType.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for EntityType. |
CreateEntityTypeRequest
Request message for FeaturestoreService.CreateEntityType.
| Fields | |
|---|---|
parent |
Required. The resource name of the Featurestore to create EntityTypes. Format: |
entity_type |
The EntityType to create. |
entity_type_id |
Required. The ID to use for the EntityType, which will become the final component of the EntityType's resource name. This value may be up to 60 characters, and valid characters are The value must be unique within a featurestore. |
CreateExecutionRequest
Request message for MetadataService.CreateExecution.
| Fields | |
|---|---|
parent |
Required. The resource name of the MetadataStore where the Execution should be created. Format: |
execution |
Required. The Execution to create. |
execution_id |
The {execution} portion of the resource name with the format: |
CreateExtensionControllerOperationMetadata
Details of ExtensionControllerService.CreateExtensionController operation.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
CreateFeatureGroupOperationMetadata
Details of operations that perform create FeatureGroup.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for FeatureGroup. |
CreateFeatureGroupRequest
Request message for FeatureRegistryService.CreateFeatureGroup.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create FeatureGroups. Format: |
feature_group |
Required. The FeatureGroup to create. |
feature_group_id |
Required. The ID to use for this FeatureGroup, which will become the final component of the FeatureGroup's resource name. This value may be up to 128 characters, and valid characters are The value must be unique within the project and location. |
CreateFeatureMonitorJobRequest
Request message for [FeatureRegistryService.CreateFeatureMonitorJobRequest][].
| Fields | |
|---|---|
parent |
Required. The resource name of FeatureMonitor to create FeatureMonitorJob. Format: |
feature_monitor_job |
Required. The Monitor to create. |
feature_monitor_job_id |
Optional. Output only. System-generated ID for feature monitor job. |
CreateFeatureMonitorOperationMetadata
Details of operations that perform create FeatureMonitor.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Feature. |
CreateFeatureMonitorRequest
Request message for [FeatureRegistryService.CreateFeatureMonitorRequest][].
| Fields | |
|---|---|
parent |
Required. The resource name of FeatureGroup to create FeatureMonitor. Format: |
feature_monitor |
Required. The Monitor to create. |
feature_monitor_id |
Required. The ID to use for this FeatureMonitor, which will become the final component of the FeatureGroup's resource name. This value may be up to 60 characters, and valid characters are The value must be unique within the FeatureGroup. |
CreateFeatureOnlineStoreOperationMetadata
Details of operations that perform create FeatureOnlineStore.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for FeatureOnlineStore. |
CreateFeatureOnlineStoreRequest
Request message for FeatureOnlineStoreAdminService.CreateFeatureOnlineStore.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create FeatureOnlineStores. Format: |
feature_online_store |
Required. The FeatureOnlineStore to create. |
feature_online_store_id |
Required. The ID to use for this FeatureOnlineStore, which will become the final component of the FeatureOnlineStore's resource name. This value may be up to 60 characters, and valid characters are The value must be unique within the project and location. |
CreateFeatureOperationMetadata
Details of operations that perform create Feature.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Feature. |
CreateFeatureRequest
Request message for FeaturestoreService.CreateFeature. Request message for FeatureRegistryService.CreateFeature.
| Fields | |
|---|---|
parent |
Required. The resource name of the EntityType or FeatureGroup to create a Feature. Format for entity_type as parent: |
feature |
Required. The Feature to create. |
feature_id |
Required. The ID to use for the Feature, which will become the final component of the Feature's resource name. This value may be up to 128 characters, and valid characters are The value must be unique within an EntityType/FeatureGroup. |
CreateFeatureViewOperationMetadata
Details of operations that perform create FeatureView.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for FeatureView Create. |
CreateFeatureViewRequest
Request message for FeatureOnlineStoreAdminService.CreateFeatureView.
| Fields | |
|---|---|
parent |
Required. The resource name of the FeatureOnlineStore to create FeatureViews. Format: |
feature_view |
Required. The FeatureView to create. |
feature_view_id |
Required. The ID to use for the FeatureView, which will become the final component of the FeatureView's resource name. This value may be up to 60 characters, and valid characters are The value must be unique within a FeatureOnlineStore. |
run_sync_immediately |
Immutable. If set to true, one on demand sync will be run immediately, regardless whether the |
CreateFeaturestoreOperationMetadata
Details of operations that perform create Featurestore.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Featurestore. |
CreateFeaturestoreRequest
Request message for FeaturestoreService.CreateFeaturestore.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create Featurestores. Format: |
featurestore |
Required. The Featurestore to create. |
featurestore_id |
Required. The ID to use for this Featurestore, which will become the final component of the Featurestore's resource name. This value may be up to 60 characters, and valid characters are The value must be unique within the project and location. |
CreateHyperparameterTuningJobRequest
Request message for JobService.CreateHyperparameterTuningJob.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the HyperparameterTuningJob in. Format: |
hyperparameter_tuning_job |
Required. The HyperparameterTuningJob to create. |
CreateIndexEndpointOperationMetadata
Runtime operation information for IndexEndpointService.CreateIndexEndpoint.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
CreateIndexEndpointRequest
Request message for IndexEndpointService.CreateIndexEndpoint.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the IndexEndpoint in. Format: |
index_endpoint |
Required. The IndexEndpoint to create. |
CreateIndexOperationMetadata
Runtime operation information for IndexService.CreateIndex.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
nearest_neighbor_search_operation_metadata |
The operation metadata with regard to Matching Engine Index operation. |
CreateIndexRequest
Request message for IndexService.CreateIndex.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the Index in. Format: |
index |
Required. The Index to create. |
CreateMetadataSchemaRequest
Request message for MetadataService.CreateMetadataSchema.
| Fields | |
|---|---|
parent |
Required. The resource name of the MetadataStore where the MetadataSchema should be created. Format: |
metadata_schema |
Required. The MetadataSchema to create. |
metadata_schema_id |
The {metadata_schema} portion of the resource name with the format: |
CreateMetadataStoreOperationMetadata
Details of operations that perform MetadataService.CreateMetadataStore.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for creating a MetadataStore. |
CreateMetadataStoreRequest
Request message for MetadataService.CreateMetadataStore.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location where the MetadataStore should be created. Format: |
metadata_store |
Required. The MetadataStore to create. |
metadata_store_id |
The {metadatastore} portion of the resource name with the format: |
CreateModelDeploymentMonitoringJobRequest
Request message for JobService.CreateModelDeploymentMonitoringJob.
| Fields | |
|---|---|
parent |
Required. The parent of the ModelDeploymentMonitoringJob. Format: |
model_deployment_monitoring_job |
Required. The ModelDeploymentMonitoringJob to create |
CreateModelMonitorOperationMetadata
Runtime operation information for ModelMonitoringService.CreateModelMonitor.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
CreateModelMonitorRequest
Request message for ModelMonitoringService.CreateModelMonitor.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the ModelMonitor in. Format: |
model_monitor |
Required. The ModelMonitor to create. |
model_monitor_id |
Optional. The ID to use for the Model Monitor, which will become the final component of the model monitor resource name. The maximum length is 63 characters, and valid characters are |
CreateModelMonitoringJobRequest
Request message for ModelMonitoringService.CreateModelMonitoringJob.
| Fields | |
|---|---|
parent |
Required. The parent of the ModelMonitoringJob. Format: |
model_monitoring_job |
Required. The ModelMonitoringJob to create |
model_monitoring_job_id |
Optional. The ID to use for the Model Monitoring Job, which will become the final component of the model monitoring job resource name. The maximum length is 63 characters, and valid characters are |
CreateNotebookExecutionJobOperationMetadata
Metadata information for NotebookService.CreateNotebookExecutionJob.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
progress_message |
A human-readable message that shows the intermediate progress details of NotebookRuntime. |
CreateNotebookExecutionJobRequest
Request message for [NotebookService.CreateNotebookExecutionJob]
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the NotebookExecutionJob. Format: |
notebook_execution_job |
Required. The NotebookExecutionJob to create. |
notebook_execution_job_id |
Optional. User specified ID for the NotebookExecutionJob. |
CreateNotebookRuntimeTemplateOperationMetadata
Metadata information for NotebookService.CreateNotebookRuntimeTemplate.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
CreateNotebookRuntimeTemplateRequest
Request message for NotebookService.CreateNotebookRuntimeTemplate.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the NotebookRuntimeTemplate. Format: |
notebook_runtime_template |
Required. The NotebookRuntimeTemplate to create. |
notebook_runtime_template_id |
Optional. User specified ID for the notebook runtime template. |
CreatePersistentResourceOperationMetadata
Details of operations that perform create PersistentResource.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for PersistentResource. |
progress_message |
Progress Message for Create LRO |
CreatePersistentResourceRequest
Request message for PersistentResourceService.CreatePersistentResource.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the PersistentResource in. Format: |
persistent_resource |
Required. The PersistentResource to create. |
persistent_resource_id |
Required. The ID to use for the PersistentResource, which become the final component of the PersistentResource's resource name. The maximum length is 63 characters, and valid characters are |
CreatePipelineJobRequest
Request message for PipelineService.CreatePipelineJob.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the PipelineJob in. Format: |
pipeline_job |
Required. The PipelineJob to create. |
pipeline_job_id |
The ID to use for the PipelineJob, which will become the final component of the PipelineJob name. If not provided, an ID will be automatically generated. This value should be less than 128 characters, and valid characters are |
CreateRagCorpusOperationMetadata
Runtime operation information for VertexRagDataService.CreateRagCorpus.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
CreateRagCorpusRequest
Request message for VertexRagDataService.CreateRagCorpus.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the RagCorpus in. Format: |
rag_corpus |
Required. The RagCorpus to create. |
CreateReasoningEngineOperationMetadata
Details of ReasoningEngineService.CreateReasoningEngine operation.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
CreateReasoningEngineRequest
Request message for ReasoningEngineService.CreateReasoningEngine.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the ReasoningEngine in. Format: |
reasoning_engine |
Required. The ReasoningEngine to create. |
CreateRegistryFeatureOperationMetadata
Details of operations that perform create FeatureGroup.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Feature. |
CreateScheduleRequest
Request message for ScheduleService.CreateSchedule.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the Schedule in. Format: |
schedule |
Required. The Schedule to create. |
CreateSolverOperationMetadata
Runtime operation information for SolverService.CreateSolver.
| Fields | |
|---|---|
generic_metadata |
The generic operation information. |
CreateSpecialistPoolOperationMetadata
Runtime operation information for SpecialistPoolService.CreateSpecialistPool.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
CreateSpecialistPoolRequest
Request message for SpecialistPoolService.CreateSpecialistPool.
| Fields | |
|---|---|
parent |
Required. The parent Project name for the new SpecialistPool. The form is |
specialist_pool |
Required. The SpecialistPool to create. |
CreateStudyRequest
Request message for VizierService.CreateStudy.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the CustomJob in. Format: |
study |
Required. The Study configuration used to create the Study. |
CreateTensorboardExperimentRequest
Request message for TensorboardService.CreateTensorboardExperiment.
| Fields | |
|---|---|
parent |
Required. The resource name of the Tensorboard to create the TensorboardExperiment in. Format: |
tensorboard_experiment |
The TensorboardExperiment to create. |
tensorboard_experiment_id |
Required. The ID to use for the Tensorboard experiment, which becomes the final component of the Tensorboard experiment's resource name. This value should be 1-128 characters, and valid characters are |
CreateTensorboardOperationMetadata
Details of operations that perform create Tensorboard.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Tensorboard. |
CreateTensorboardRequest
Request message for TensorboardService.CreateTensorboard.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the Tensorboard in. Format: |
tensorboard |
Required. The Tensorboard to create. |
CreateTensorboardRunRequest
Request message for TensorboardService.CreateTensorboardRun.
| Fields | |
|---|---|
parent |
Required. The resource name of the TensorboardExperiment to create the TensorboardRun in. Format: |
tensorboard_run |
Required. The TensorboardRun to create. |
tensorboard_run_id |
Required. The ID to use for the Tensorboard run, which becomes the final component of the Tensorboard run's resource name. This value should be 1-128 characters, and valid characters are |
CreateTensorboardTimeSeriesRequest
Request message for TensorboardService.CreateTensorboardTimeSeries.
| Fields | |
|---|---|
parent |
Required. The resource name of the TensorboardRun to create the TensorboardTimeSeries in. Format: |
tensorboard_time_series_id |
Optional. The user specified unique ID to use for the TensorboardTimeSeries, which becomes the final component of the TensorboardTimeSeries's resource name. This value should match "[a-z0-9][a-z0-9-]{0, 127}" |
tensorboard_time_series |
Required. The TensorboardTimeSeries to create. |
CreateTrainingPipelineRequest
Request message for PipelineService.CreateTrainingPipeline.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the TrainingPipeline in. Format: |
training_pipeline |
Required. The TrainingPipeline to create. |
CreateTrialRequest
Request message for VizierService.CreateTrial.
| Fields | |
|---|---|
parent |
Required. The resource name of the Study to create the Trial in. Format: |
trial |
Required. The Trial to create. |
CreateTuningJobRequest
Request message for GenAiTuningService.CreateTuningJob.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to create the TuningJob in. Format: |
tuning_job |
Required. The TuningJob to create. |
CsvDestination
The storage details for CSV output content.
| Fields | |
|---|---|
gcs_destination |
Required. Google Cloud Storage location. |
CsvSource
The storage details for CSV input content.
| Fields | |
|---|---|
gcs_source |
Required. Google Cloud Storage location. |
CustomJob
Represents a job that runs custom workloads such as a Docker container or a Python package. A CustomJob can have multiple worker pools and each worker pool can have its own machine and input spec. A CustomJob will be cleaned up once the job enters terminal state (failed or succeeded).
| Fields | |
|---|---|
name |
Output only. Resource name of a CustomJob. |
display_name |
Required. The display name of the CustomJob. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
job_spec |
Required. Job spec. |
state |
Output only. The detailed state of the job. |
create_time |
Output only. Time when the CustomJob was created. |
start_time |
Output only. Time when the CustomJob for the first time entered the |
end_time |
Output only. Time when the CustomJob entered any of the following states: |
update_time |
Output only. Time when the CustomJob was most recently updated. |
error |
Output only. Only populated when job's state is |
labels |
The labels with user-defined metadata to organize CustomJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
encryption_spec |
Customer-managed encryption key options for a CustomJob. If this is set, then all resources created by the CustomJob will be encrypted with the provided encryption key. |
web_access_uris |
Output only. URIs for accessing interactive shells (one URI for each training node). Only available if The keys are names of each node in the training job; for example, The values are the URIs for each node's interactive shell. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
CustomJobSpec
Represents the spec of a CustomJob.
| Fields | |
|---|---|
persistent_resource_id |
Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. |
worker_pool_specs[] |
Required. The spec of the worker pools including machine type and Docker image. All worker pools except the first one are optional and can be skipped by providing an empty value. |
scheduling |
Scheduling options for a CustomJob. |
service_account |
Specifies the service account for workload run-as account. Users submitting jobs must have act-as permission on this run-as account. If unspecified, the Vertex AI Custom Code Service Agent for the CustomJob's project is used. |
network |
Optional. The full name of the Compute Engine network to which the Job should be peered. For example, To specify this field, you must have already configured VPC Network Peering for Vertex AI. If this field is left unspecified, the job is not peered with any network. |
reserved_ip_ranges[] |
Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. |
psc_interface_config |
Optional. Configuration for PSC-I for CustomJob. |
base_output_directory |
The Cloud Storage location to store the output of this CustomJob or HyperparameterTuningJob. For HyperparameterTuningJob, the baseOutputDirectory of each child CustomJob backing a Trial is set to a subdirectory of name The following Vertex AI environment variables will be passed to containers or python modules when this field is set: For CustomJob:
For CustomJob backing a Trial of HyperparameterTuningJob:
|
protected_artifact_location_id |
The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations |
tensorboard |
Optional. The name of a Vertex AI |
enable_web_access |
Optional. Whether you want Vertex AI to enable interactive shell access to training containers. If set to |
enable_dashboard_access |
Optional. Whether you want Vertex AI to enable access to the customized dashboard in training chief container. If set to |
experiment |
Optional. The Experiment associated with this job. Format: |
experiment_run |
Optional. The Experiment Run associated with this job. Format: |
models[] |
Optional. The name of the Model resources for which to generate a mapping to artifact URIs. Applicable only to some of the Google-provided custom jobs. Format: In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: |
DataItem
A piece of data in a Dataset. Could be an image, a video, a document or plain text.
| Fields | |
|---|---|
name |
Output only. The resource name of the DataItem. |
create_time |
Output only. Timestamp when this DataItem was created. |
update_time |
Output only. Timestamp when this DataItem was last updated. |
labels |
Optional. The labels with user-defined metadata to organize your DataItems. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one DataItem(System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
payload |
Required. The data that the DataItem represents (for example, an image or a text snippet). The schema of the payload is stored in the parent Dataset's |
etag |
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
DataItemView
A container for a single DataItem and Annotations on it.
| Fields | |
|---|---|
data_item |
The DataItem. |
annotations[] |
The Annotations on the DataItem. If too many Annotations should be returned for the DataItem, this field will be truncated per annotations_limit in request. If it was, then the has_truncated_annotations will be set to true. |
has_truncated_annotations |
True if and only if the Annotations field has been truncated. It happens if more Annotations for this DataItem met the request's annotation_filter than are allowed to be returned by annotations_limit. Note that if Annotations field is not being returned due to field mask, then this field will not be set to true no matter how many Annotations are there. |
Dataset
A collection of DataItems and Annotations on them.
| Fields | |
|---|---|
name |
Output only. Identifier. The resource name of the Dataset. Format: |
display_name |
Required. The user-defined name of the Dataset. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
description |
The description of the Dataset. |
metadata_schema_uri |
Required. Points to a YAML file stored on Google Cloud Storage describing additional information about the Dataset. The schema is defined as an OpenAPI 3.0.2 Schema Object. The schema files that can be used here are found in gs://google-cloud-aiplatform/schema/dataset/metadata/. |
metadata |
Required. Additional information about the Dataset. |
data_item_count |
Output only. The number of DataItems in this Dataset. Only apply for non-structured Dataset. |
create_time |
Output only. Timestamp when this Dataset was created. |
update_time |
Output only. Timestamp when this Dataset was last updated. |
etag |
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
The labels with user-defined metadata to organize your Datasets. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Dataset (System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. Following system labels exist for each Dataset:
|
saved_queries[] |
All SavedQueries belong to the Dataset will be returned in List/Get Dataset response. The annotation_specs field will not be populated except for UI cases which will only use |
encryption_spec |
Customer-managed encryption key spec for a Dataset. If set, this Dataset and all sub-resources of this Dataset will be secured by this key. |
metadata_artifact |
Output only. The resource name of the Artifact that was created in MetadataStore when creating the Dataset. The Artifact resource name pattern is |
model_reference |
Optional. Reference to the public base model last used by the dataset. Only set for prompt datasets. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
DatasetDistribution
Distribution computed over a tuning dataset.
| Fields | |
|---|---|
sum |
Output only. Sum of a given population of values. |
min |
Output only. The minimum of the population values. |
max |
Output only. The maximum of the population values. |
mean |
Output only. The arithmetic mean of the values in the population. |
median |
Output only. The median of the values in the population. |
p5 |
Output only. The 5th percentile of the values in the population. |
p95 |
Output only. The 95th percentile of the values in the population. |
buckets[] |
Output only. Defines the histogram bucket. |
DistributionBucket
Dataset bucket used to create a histogram for the distribution given a population of values.
| Fields | |
|---|---|
count |
Output only. Number of values in the bucket. |
left |
Output only. Left bound of the bucket. |
right |
Output only. Right bound of the bucket. |
DatasetStats
Statistics computed over a tuning dataset.
| Fields | |
|---|---|
tuning_dataset_example_count |
Output only. Number of examples in the tuning dataset. |
total_tuning_character_count |
Output only. Number of tuning characters in the tuning dataset. |
total_billable_character_count |
Output only. Number of billable characters in the tuning dataset. |
tuning_step_count |
Output only. Number of tuning steps for this Tuning Job. |
user_input_token_distribution |
Output only. Dataset distributions for the user input tokens. |
user_message_per_example_distribution |
Output only. Dataset distributions for the messages per example. |
user_dataset_examples[] |
Output only. Sample user messages in the training dataset uri. |
user_output_token_distribution |
Output only. Dataset distributions for the user output tokens. |
DatasetVersion
Describes the dataset version.
| Fields | |
|---|---|
name |
Output only. Identifier. The resource name of the DatasetVersion. Format: |
create_time |
Output only. Timestamp when this DatasetVersion was created. |
update_time |
Output only. Timestamp when this DatasetVersion was last updated. |
etag |
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
big_query_dataset_name |
Output only. Name of the associated BigQuery dataset. |
display_name |
The user-defined name of the DatasetVersion. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
metadata |
Required. Output only. Additional information about the DatasetVersion. |
model_reference |
Output only. Reference to the public base model last used by the dataset version. Only set for prompt dataset versions. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
DedicatedResources
A description of resources that are dedicated to a DeployedModel or DeployedIndex, and that need a higher degree of manual configuration.
| Fields | |
|---|---|
machine_spec |
Required. Immutable. The specification of a single machine being used. |
min_replica_count |
Required. Immutable. The minimum number of machine replicas that will be always deployed on. This value must be greater than or equal to 1. If traffic increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed. |
max_replica_count |
Immutable. The maximum number of replicas that may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale to that many replicas is guaranteed (barring service outages). If traffic increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type). |
required_replica_count |
Optional. Number of required available replicas for the deployment to succeed. This field is only needed when partial deployment/mutation is desired. If set, the deploy/mutate operation will succeed once available_replica_count reaches required_replica_count, and the rest of the replicas will be retried. If not set, the default required_replica_count will be min_replica_count. |
autoscaling_metric_specs[] |
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If If For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set |
spot |
Optional. If true, schedule the deployment workload on spot VMs. |
DeleteArtifactRequest
Request message for MetadataService.DeleteArtifact.
| Fields | |
|---|---|
name |
Required. The resource name of the Artifact to delete. Format: |
etag |
Optional. The etag of the Artifact to delete. If this is provided, it must match the server's etag. Otherwise, the request will fail with a FAILED_PRECONDITION. |
DeleteBatchPredictionJobRequest
Request message for JobService.DeleteBatchPredictionJob.
| Fields | |
|---|---|
name |
Required. The name of the BatchPredictionJob resource to be deleted. Format: |
DeleteCachedContentRequest
Request message for GenAiCacheService.DeleteCachedContent.
| Fields | |
|---|---|
name |
Required. The resource name referring to the cached content |
DeleteContextRequest
Request message for MetadataService.DeleteContext.
| Fields | |
|---|---|
name |
Required. The resource name of the Context to delete. Format: |
force |
The force deletion semantics is still undefined. Users should not use this field. |
etag |
Optional. The etag of the Context to delete. If this is provided, it must match the server's etag. Otherwise, the request will fail with a FAILED_PRECONDITION. |
DeleteCustomJobRequest
Request message for JobService.DeleteCustomJob.
| Fields | |
|---|---|
name |
Required. The name of the CustomJob resource to be deleted. Format: |
DeleteDatasetRequest
Request message for DatasetService.DeleteDataset.
| Fields | |
|---|---|
name |
Required. The resource name of the Dataset to delete. Format: |
DeleteDatasetVersionRequest
Request message for DatasetService.DeleteDatasetVersion.
| Fields | |
|---|---|
name |
Required. The resource name of the Dataset version to delete. Format: |
DeleteDeploymentResourcePoolRequest
Request message for DeleteDeploymentResourcePool method.
| Fields | |
|---|---|
name |
Required. The name of the DeploymentResourcePool to delete. Format: |
DeleteEndpointRequest
Request message for EndpointService.DeleteEndpoint.
| Fields | |
|---|---|
name |
Required. The name of the Endpoint resource to be deleted. Format: |
DeleteEntityTypeRequest
Request message for FeaturestoreService.DeleteEntityType.
| Fields | |
|---|---|
name |
Required. The name of the EntityType to be deleted. Format: |
force |
If set to true, any Features for this EntityType will also be deleted. (Otherwise, the request will only work if the EntityType has no Features.) |
DeleteExecutionRequest
Request message for MetadataService.DeleteExecution.
| Fields | |
|---|---|
name |
Required. The resource name of the Execution to delete. Format: |
etag |
Optional. The etag of the Execution to delete. If this is provided, it must match the server's etag. Otherwise, the request will fail with a FAILED_PRECONDITION. |
DeleteExtensionRequest
Request message for ExtensionRegistryService.DeleteExtension.
| Fields | |
|---|---|
name |
Required. The name of the Extension resource to be deleted. Format: |
DeleteFeatureGroupRequest
Request message for FeatureRegistryService.DeleteFeatureGroup.
| Fields | |
|---|---|
name |
Required. The name of the FeatureGroup to be deleted. Format: |
force |
If set to true, any Features under this FeatureGroup will also be deleted. (Otherwise, the request will only work if the FeatureGroup has no Features.) |
DeleteFeatureMonitorRequest
Request message for FeatureRegistryService.DeleteFeatureMonitor.
| Fields | |
|---|---|
name |
Required. The name of the FeatureMonitor to be deleted. Format: |
DeleteFeatureOnlineStoreRequest
Request message for FeatureOnlineStoreAdminService.DeleteFeatureOnlineStore.
| Fields | |
|---|---|
name |
Required. The name of the FeatureOnlineStore to be deleted. Format: |
force |
If set to true, any FeatureViews and Features for this FeatureOnlineStore will also be deleted. (Otherwise, the request will only work if the FeatureOnlineStore has no FeatureViews.) |
DeleteFeatureRequest
Request message for FeaturestoreService.DeleteFeature. Request message for FeatureRegistryService.DeleteFeature.
| Fields | |
|---|---|
name |
Required. The name of the Features to be deleted. Format: |
DeleteFeatureValuesOperationMetadata
Details of operations that delete Feature values.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Featurestore delete Features values. |
DeleteFeatureValuesRequest
Request message for FeaturestoreService.DeleteFeatureValues.
| Fields | |
|---|---|
entity_type |
Required. The resource name of the EntityType grouping the Features for which values are being deleted from. Format: |
Union field DeleteOption. Defines options to select feature values to be deleted. DeleteOption can be only one of the following: |
|
select_entity |
Select feature values to be deleted by specifying entities. |
select_time_range_and_feature |
Select feature values to be deleted by specifying time range and features. |
SelectEntity
Message to select entity. If an entity id is selected, all the feature values corresponding to the entity id will be deleted, including the entityId.
| Fields | |
|---|---|
entity_id_selector |
Required. Selectors choosing feature values of which entity id to be deleted from the EntityType. |
SelectTimeRangeAndFeature
Message to select time range and feature. Values of the selected feature generated within an inclusive time range will be deleted. Using this option permanently deletes the feature values from the specified feature IDs within the specified time range. This might include data from the online storage. If you want to retain any deleted historical data in the online storage, you must re-ingest it.
| Fields | |
|---|---|
time_range |
Required. Select feature generated within a half-inclusive time range. The time range is lower inclusive and upper exclusive. |
feature_selector |
Required. Selectors choosing which feature values to be deleted from the EntityType. |
skip_online_storage_delete |
If set, data will not be deleted from online storage. When time range is older than the data in online storage, setting this to be true will make the deletion have no impact on online serving. |
DeleteFeatureValuesResponse
Response message for FeaturestoreService.DeleteFeatureValues.
| Fields | |
|---|---|
Union field response. Response based on which delete option is specified in the request response can be only one of the following: |
|
select_entity |
Response for request specifying the entities to delete |
select_time_range_and_feature |
Response for request specifying time range and feature |
SelectEntity
Response message if the request uses the SelectEntity option.
| Fields | |
|---|---|
offline_storage_deleted_entity_row_count |
The count of deleted entity rows in the offline storage. Each row corresponds to the combination of an entity ID and a timestamp. One entity ID can have multiple rows in the offline storage. |
online_storage_deleted_entity_count |
The count of deleted entities in the online storage. Each entity ID corresponds to one entity. |
SelectTimeRangeAndFeature
Response message if the request uses the SelectTimeRangeAndFeature option.
| Fields | |
|---|---|
impacted_feature_count |
The count of the features or columns impacted. This is the same as the feature count in the request. |
offline_storage_modified_entity_row_count |
The count of modified entity rows in the offline storage. Each row corresponds to the combination of an entity ID and a timestamp. One entity ID can have multiple rows in the offline storage. Within each row, only the features specified in the request are deleted. |
online_storage_modified_entity_count |
The count of modified entities in the online storage. Each entity ID corresponds to one entity. Within each entity, only the features specified in the request are deleted. |
DeleteFeatureViewRequest
Request message for FeatureOnlineStoreAdminService.DeleteFeatureView.
| Fields | |
|---|---|
name |
Required. The name of the FeatureView to be deleted. Format: |
DeleteFeaturestoreRequest
Request message for FeaturestoreService.DeleteFeaturestore.
| Fields | |
|---|---|
name |
Required. The name of the Featurestore to be deleted. Format: |
force |
If set to true, any EntityTypes and Features for this Featurestore will also be deleted. (Otherwise, the request will only work if the Featurestore has no EntityTypes.) |
DeleteHyperparameterTuningJobRequest
Request message for JobService.DeleteHyperparameterTuningJob.
| Fields | |
|---|---|
name |
Required. The name of the HyperparameterTuningJob resource to be deleted. Format: |
DeleteIndexEndpointRequest
Request message for IndexEndpointService.DeleteIndexEndpoint.
| Fields | |
|---|---|
name |
Required. The name of the IndexEndpoint resource to be deleted. Format: |
DeleteIndexRequest
Request message for IndexService.DeleteIndex.
| Fields | |
|---|---|
name |
Required. The name of the Index resource to be deleted. Format: |
DeleteMetadataStoreOperationMetadata
Details of operations that perform MetadataService.DeleteMetadataStore.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for deleting a MetadataStore. |
DeleteMetadataStoreRequest
Request message for MetadataService.DeleteMetadataStore.
| Fields | |
|---|---|
name |
Required. The resource name of the MetadataStore to delete. Format: |
force |
Deprecated: Field is no longer supported. |
DeleteModelDeploymentMonitoringJobRequest
Request message for JobService.DeleteModelDeploymentMonitoringJob.
| Fields | |
|---|---|
name |
Required. The resource name of the model monitoring job to delete. Format: |
DeleteModelMonitorRequest
Request message for ModelMonitoringService.DeleteModelMonitor.
| Fields | |
|---|---|
name |
Required. The name of the ModelMonitor resource to be deleted. Format: |
force |
Optional. Force delete the model monitor with schedules. |
DeleteModelMonitoringJobRequest
Request message for ModelMonitoringService.DeleteModelMonitoringJob.
| Fields | |
|---|---|
name |
Required. The resource name of the model monitoring job to delete. Format: |
DeleteModelRequest
Request message for ModelService.DeleteModel.
| Fields | |
|---|---|
name |
Required. The name of the Model resource to be deleted. Format: |
DeleteModelVersionRequest
Request message for ModelService.DeleteModelVersion.
| Fields | |
|---|---|
name |
Required. The name of the model version to be deleted, with a version ID explicitly included. Example: |
DeleteNotebookExecutionJobRequest
Request message for [NotebookService.DeleteNotebookExecutionJob]
| Fields | |
|---|---|
name |
Required. The name of the NotebookExecutionJob resource to be deleted. |
DeleteNotebookRuntimeRequest
Request message for NotebookService.DeleteNotebookRuntime.
| Fields | |
|---|---|
name |
Required. The name of the NotebookRuntime resource to be deleted. Instead of checking whether the name is in valid NotebookRuntime resource name format, directly throw NotFound exception if there is no such NotebookRuntime in spanner. |
DeleteNotebookRuntimeTemplateRequest
Request message for NotebookService.DeleteNotebookRuntimeTemplate.
| Fields | |
|---|---|
name |
Required. The name of the NotebookRuntimeTemplate resource to be deleted. Format: |
DeleteOperationMetadata
Details of operations that perform deletes of any entities.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
DeletePersistentResourceRequest
Request message for PersistentResourceService.DeletePersistentResource.
| Fields | |
|---|---|
name |
Required. The name of the PersistentResource to be deleted. Format: |
DeletePipelineJobRequest
Request message for PipelineService.DeletePipelineJob.
| Fields | |
|---|---|
name |
Required. The name of the PipelineJob resource to be deleted. Format: |
DeleteRagCorpusRequest
Request message for VertexRagDataService.DeleteRagCorpus.
| Fields | |
|---|---|
name |
Required. The name of the RagCorpus resource to be deleted. Format: |
force |
Optional. If set to true, any RagFiles in this RagCorpus will also be deleted. Otherwise, the request will only work if the RagCorpus has no RagFiles. |
DeleteRagFileRequest
Request message for VertexRagDataService.DeleteRagFile.
| Fields | |
|---|---|
name |
Required. The name of the RagFile resource to be deleted. Format: |
DeleteReasoningEngineRequest
Request message for ReasoningEngineService.DeleteReasoningEngine.
| Fields | |
|---|---|
name |
Required. The name of the ReasoningEngine resource to be deleted. Format: |
DeleteSavedQueryRequest
Request message for DatasetService.DeleteSavedQuery.
| Fields | |
|---|---|
name |
Required. The resource name of the SavedQuery to delete. Format: |
DeleteScheduleRequest
Request message for ScheduleService.DeleteSchedule.
| Fields | |
|---|---|
name |
Required. The name of the Schedule resource to be deleted. Format: |
DeleteSpecialistPoolRequest
Request message for SpecialistPoolService.DeleteSpecialistPool.
| Fields | |
|---|---|
name |
Required. The resource name of the SpecialistPool to delete. Format: |
force |
If set to true, any specialist managers in this SpecialistPool will also be deleted. (Otherwise, the request will only work if the SpecialistPool has no specialist managers.) |
DeleteStudyRequest
Request message for VizierService.DeleteStudy.
| Fields | |
|---|---|
name |
Required. The name of the Study resource to be deleted. Format: |
DeleteTensorboardExperimentRequest
Request message for TensorboardService.DeleteTensorboardExperiment.
| Fields | |
|---|---|
name |
Required. The name of the TensorboardExperiment to be deleted. Format: |
DeleteTensorboardRequest
Request message for TensorboardService.DeleteTensorboard.
| Fields | |
|---|---|
name |
Required. The name of the Tensorboard to be deleted. Format: |
DeleteTensorboardRunRequest
Request message for TensorboardService.DeleteTensorboardRun.
| Fields | |
|---|---|
name |
Required. The name of the TensorboardRun to be deleted. Format: |
DeleteTensorboardTimeSeriesRequest
Request message for TensorboardService.DeleteTensorboardTimeSeries.
| Fields | |
|---|---|
name |
Required. The name of the TensorboardTimeSeries to be deleted. Format: |
DeleteTrainingPipelineRequest
Request message for PipelineService.DeleteTrainingPipeline.
| Fields | |
|---|---|
name |
Required. The name of the TrainingPipeline resource to be deleted. Format: |
DeleteTrialRequest
Request message for VizierService.DeleteTrial.
| Fields | |
|---|---|
name |
Required. The Trial's name. Format: |
DeployIndexOperationMetadata
Runtime operation information for IndexEndpointService.DeployIndex.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
deployed_index_id |
The unique index id specified by user |
DeployIndexRequest
Request message for IndexEndpointService.DeployIndex.
| Fields | |
|---|---|
index_endpoint |
Required. The name of the IndexEndpoint resource into which to deploy an Index. Format: |
deployed_index |
Required. The DeployedIndex to be created within the IndexEndpoint. |
DeployIndexResponse
Response message for IndexEndpointService.DeployIndex.
| Fields | |
|---|---|
deployed_index |
The DeployedIndex that had been deployed in the IndexEndpoint. |
DeployModelOperationMetadata
Runtime operation information for EndpointService.DeployModel.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
DeployModelRequest
Request message for EndpointService.DeployModel.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint resource into which to deploy a Model. Format: |
deployed_model |
Required. The DeployedModel to be created within the Endpoint. Note that |
traffic_split |
A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If this field is non-empty, then the Endpoint's If this field is empty, then the Endpoint's |
DeployModelResponse
Response message for EndpointService.DeployModel.
| Fields | |
|---|---|
deployed_model |
The DeployedModel that had been deployed in the Endpoint. |
DeployOperationMetadata
Runtime operation information for ModelGardenService.Deploy.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
publisher_model |
Output only. The name of the model resource. |
destination |
Output only. The resource name of the Location to deploy the model in. Format: |
project_number |
Output only. The project number where the deploy model request is sent. |
DeployPublisherModelOperationMetadata
Runtime operation information for ModelGardenService.DeployPublisherModel.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
publisher_model |
Output only. The name of the PublisherModel resource. Format: |
destination |
Output only. The resource name of the Location to deploy the model in. Format: |
project_number |
Output only. The project number where the deploy model request is sent. |
DeployPublisherModelRequest
Request message for ModelGardenService.DeployPublisherModel.
| Fields | |
|---|---|
model |
Required. The model to deploy. Format: 1. |
destination |
Required. The resource name of the Location to deploy the model in. Format: |
endpoint_display_name |
Optional. The user-specified display name of the endpoint. If not set, a default name will be used. |
dedicated_resources |
Optional. The dedicated resources to use for the endpoint. If not set, the default resources will be used. |
model_display_name |
Optional. The user-specified display name of the uploaded model. If not set, a default name will be used. |
hugging_face_access_token |
Optional. The Hugging Face read access token used to access the model artifacts of gated models. |
accept_eula |
Optional. Whether the user accepts the End User License Agreement (EULA) for the model. |
DeployPublisherModelResponse
Response message for ModelGardenService.DeployPublisherModel.
| Fields | |
|---|---|
publisher_model |
Output only. The name of the PublisherModel resource. Format: |
endpoint |
Output only. The name of the Endpoint created. Format: |
model |
Output only. The name of the Model created. Format: |
DeployRequest
Request message for ModelGardenService.Deploy.
| Fields | |
|---|---|
destination |
Required. The resource name of the Location to deploy the model in. Format: |
model_config |
Optional. The model config to use for the deployment. If not specified, the default model config will be used. |
endpoint_config |
Optional. The endpoint config to use for the deployment. If not specified, the default endpoint config will be used. |
deploy_config |
Optional. The deploy config to use for the deployment. If not specified, the default deploy config will be used. |
Union field artifacts. The artifacts to deploy. artifacts can be only one of the following: |
|
publisher_model_name |
The Model Garden model to deploy. Format: |
hugging_face_model_id |
The Hugging Face model to deploy. Format: Hugging Face model ID like |
DeployConfig
The deploy config to use for the deployment.
| Fields | |
|---|---|
dedicated_resources |
Optional. The dedicated resources to use for the endpoint. If not set, the default resources will be used. |
fast_tryout_enabled |
Optional. If true, enable the QMT fast tryout feature for this model if possible. |
EndpointConfig
The endpoint config to use for the deployment.
| Fields | |
|---|---|
endpoint_display_name |
Optional. The user-specified display name of the endpoint. If not set, a default name will be used. |
dedicated_endpoint_enabled |
Optional. If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitations will be removed soon. |
ModelConfig
The model config to use for the deployment.
| Fields | |
|---|---|
accept_eula |
Optional. Whether the user accepts the End User License Agreement (EULA) for the model. |
hugging_face_access_token |
Optional. The Hugging Face read access token used to access the model artifacts of gated models. |
hugging_face_cache_enabled |
Optional. If true, the model will deploy with a cached version instead of directly downloading the model artifacts from Hugging Face. This is suitable for VPC-SC users with limited internet access. |
model_display_name |
Optional. The user-specified display name of the uploaded model. If not set, a default name will be used. |
container_spec |
Optional. The specification of the container that is to be used when deploying. If not set, the default container spec will be used. |
DeployResponse
Response message for ModelGardenService.Deploy.
| Fields | |
|---|---|
publisher_model |
Output only. The name of the PublisherModel resource. Format: |
endpoint |
Output only. The name of the Endpoint created. Format: |
model |
Output only. The name of the Model created. Format: |
DeploySolverOperationMetadata
Runtime operation information for SolverService.DeploySolver.
| Fields | |
|---|---|
generic_metadata |
The generic operation information. |
DeployedIndex
A deployment of an Index. IndexEndpoints contain one or more DeployedIndexes.
| Fields | |
|---|---|
id |
Required. The user specified ID of the DeployedIndex. The ID can be up to 128 characters long and must start with a letter and only contain letters, numbers, and underscores. The ID must be unique within the project it is created in. |
index |
Required. The name of the Index this is the deployment of. We may refer to this Index as the DeployedIndex's "original" Index. |
display_name |
The display name of the DeployedIndex. If not provided upon creation, the Index's display_name is used. |
create_time |
Output only. Timestamp when the DeployedIndex was created. |
private_endpoints |
Output only. Provides paths for users to send requests directly to the deployed index services running on Cloud via private services access. This field is populated if |
index_sync_time |
Output only. The DeployedIndex may depend on various data on its original Index. Additionally when certain changes to the original Index are being done (e.g. when what the Index contains is being changed) the DeployedIndex may be asynchronously updated in the background to reflect these changes. If this timestamp's value is at least the |
automatic_resources |
Optional. A description of resources that the DeployedIndex uses, which to large degree are decided by Vertex AI, and optionally allows only a modest additional configuration. If min_replica_count is not set, the default value is 2 (we don't provide SLA when min_replica_count=1). If max_replica_count is not set, the default value is min_replica_count. The max allowed replica count is 1000. |
dedicated_resources |
Optional. A description of resources that are dedicated to the DeployedIndex, and that need a higher degree of manual configuration. The field min_replica_count must be set to a value strictly greater than 0, or else validation will fail. We don't provide SLA when min_replica_count=1. If max_replica_count is not set, the default value is min_replica_count. The max allowed replica count is 1000. Available machine types for SMALL shard: e2-standard-2 and all machine types available for MEDIUM and LARGE shard. Available machine types for MEDIUM shard: e2-standard-16 and all machine types available for LARGE shard. Available machine types for LARGE shard: e2-highmem-16, n2d-standard-32. n1-standard-16 and n1-standard-32 are still available, but we recommend e2-standard-16 and e2-highmem-16 for cost efficiency. |
enable_access_logging |
Optional. If true, private endpoint's access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each MatchRequest. Note that logs may incur a cost, especially if the deployed index receives a high queries per second rate (QPS). Estimate your costs before enabling this option. |
deployed_index_auth_config |
Optional. If set, the authentication is enabled for the private endpoint. |
reserved_ip_ranges[] |
Optional. A list of reserved ip ranges under the VPC network that can be used for this DeployedIndex. If set, we will deploy the index within the provided ip ranges. Otherwise, the index might be deployed to any ip ranges under the provided VPC network. The value should be the name of the address (https://cloud.google.com/compute/docs/reference/rest/v1/addresses) Example: ['vertex-ai-ip-range']. For more information about subnets and network IP ranges, please see https://cloud.google.com/vpc/docs/subnets#manually_created_subnet_ip_ranges. |
deployment_group |
Optional. The deployment group can be no longer than 64 characters (eg: 'test', 'prod'). If not set, we will use the 'default' deployment group. Creating Note: we only support up to 5 deployment groups(not including 'default'). |
psc_automation_configs[] |
Optional. If set for PSC deployed index, PSC connection will be automatically created after deployment is done and the endpoint information is populated in private_endpoints.psc_automated_endpoints. |
DeployedIndexAuthConfig
Used to set up the auth on the DeployedIndex's private endpoint.
| Fields | |
|---|---|
auth_provider |
Defines the authentication provider that the DeployedIndex uses. |
AuthProvider
Configuration for an authentication provider, including support for JSON Web Token (JWT).
| Fields | |
|---|---|
audiences[] |
The list of JWT audiences. that are allowed to access. A JWT containing any of these audiences will be accepted. |
allowed_issuers[] |
A list of allowed JWT issuers. Each entry must be a valid Google service account, in the following format:
|
DeployedIndexRef
Points to a DeployedIndex.
| Fields | |
|---|---|
index_endpoint |
Immutable. A resource name of the IndexEndpoint. |
deployed_index_id |
Immutable. The ID of the DeployedIndex in the above IndexEndpoint. |
display_name |
Output only. The display name of the DeployedIndex. |
DeployedModel
A deployment of a Model. Endpoints contain one or more DeployedModels.
| Fields | |
|---|---|
id |
Immutable. The ID of the DeployedModel. If not provided upon deployment, Vertex AI will generate a value for this ID. This value should be 1-10 characters, and valid characters are |
model |
Required. The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: |
model_version_id |
Output only. The version ID of the model that is deployed. |
display_name |
The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used. |
create_time |
Output only. Timestamp when the DeployedModel was created. |
explanation_spec |
Explanation configuration for this DeployedModel. When deploying a Model using |
disable_explanations |
If true, deploy the model without explainable feature, regardless the existence of |
service_account |
The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the |
enable_container_logging |
If true, the container of the DeployedModel instances will send Only supported for custom-trained Models and AutoML Tabular Models. |
enable_access_logging |
If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option. |
private_endpoints |
Output only. Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if |
faster_deployment_config |
Configuration for faster model deployment. |
rollout_options |
Options for configuring rolling deployments. |
status |
Output only. Runtime status of the deployed model. |
system_labels |
System labels to apply to Model Garden deployments. System labels are managed by Google for internal use only. |
Union field prediction_resources. The prediction (for example, the machine) resources that the DeployedModel uses. The user is billed for the resources (at least their minimal amount) even if the DeployedModel receives no traffic. Not all Models support all resources types. See Model.supported_deployment_resources_types. Required except for Large Model Deploy use cases. prediction_resources can be only one of the following: |
|
dedicated_resources |
A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. |
automatic_resources |
A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. |
shared_resources |
The resource name of the shared DeploymentResourcePool to deploy on. Format: |
Status
Runtime status of the deployed model.
| Fields | |
|---|---|
message |
Output only. The latest deployed model's status message (if any). |
last_update_time |
Output only. The time at which the status was last updated. |
available_replica_count |
Output only. The number of available replicas of the deployed model. |
DeployedModelRef
Points to a DeployedModel.
| Fields | |
|---|---|
endpoint |
Immutable. A resource name of an Endpoint. |
deployed_model_id |
Immutable. An ID of a DeployedModel in the above Endpoint. |
DeploymentResourcePool
A description of resources that can be shared by multiple DeployedModels, whose underlying specification consists of a DedicatedResources.
| Fields | |
|---|---|
name |
Immutable. The resource name of the DeploymentResourcePool. Format: |
dedicated_resources |
Required. The underlying DedicatedResources that the DeploymentResourcePool uses. |
encryption_spec |
Customer-managed encryption key spec for a DeploymentResourcePool. If set, this DeploymentResourcePool will be secured by this key. Endpoints and the DeploymentResourcePool they deploy in need to have the same EncryptionSpec. |
service_account |
The service account that the DeploymentResourcePool's container(s) run as. Specify the email address of the service account. If this service account is not specified, the container(s) run as a service account that doesn't have access to the resource project. Users deploying the Models to this DeploymentResourcePool must have the |
disable_container_logging |
If the DeploymentResourcePool is deployed with custom-trained Models or AutoML Tabular Models, the container(s) of the DeploymentResourcePool will send User can disable container logging by setting this flag to true. |
create_time |
Output only. Timestamp when this DeploymentResourcePool was created. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
DestinationFeatureSetting
| Fields | |
|---|---|
feature_id |
Required. The ID of the Feature to apply the setting to. |
destination_field |
Specify the field name in the export destination. If not specified, Feature ID is used. |
DirectPredictRequest
Request message for PredictionService.DirectPredict.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to serve the prediction. Format: |
inputs[] |
The prediction input. |
parameters |
The parameters that govern the prediction. |
DirectPredictResponse
Response message for PredictionService.DirectPredict.
| Fields | |
|---|---|
outputs[] |
The prediction output. |
parameters |
The parameters that govern the prediction. |
DirectRawPredictRequest
Request message for PredictionService.DirectRawPredict.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to serve the prediction. Format: |
method_name |
Fully qualified name of the API method being invoked to perform predictions. Format: |
input |
The prediction input. |
DirectRawPredictResponse
Response message for PredictionService.DirectRawPredict.
| Fields | |
|---|---|
output |
The prediction output. |
DirectUploadSource
This type has no fields.
The input content is encapsulated and uploaded in the request.
DiskSpec
Represents the spec of disk options.
| Fields | |
|---|---|
boot_disk_type |
Type of the boot disk (default is "pd-ssd"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive). |
boot_disk_size_gb |
Size in GB of the boot disk (default is 100GB). |
DistillationDataStats
Statistics computed for datasets used for distillation.
| Fields | |
|---|---|
training_dataset_stats |
Output only. Statistics computed for the training dataset. |
DistillationHyperParameters
Hyperparameters for Distillation.
| Fields | |
|---|---|
adapter_size |
Optional. Adapter size for distillation. |
epoch_count |
Optional. Number of complete passes the model makes over the entire training dataset during training. |
learning_rate_multiplier |
Optional. Multiplier for adjusting the default learning rate. |
DistillationSpec
Tuning Spec for Distillation.
| Fields | |
|---|---|
training_dataset_uri |
Deprecated. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file. |
hyper_parameters |
Optional. Hyperparameters for Distillation. |
student_model |
The student model that is being tuned, e.g., "google/gemma-2b-1.1-it". Deprecated. Use base_model instead. |
pipeline_root_directory |
Deprecated. A path in a Cloud Storage bucket, which will be treated as the root output directory of the distillation pipeline. It is used by the system to generate the paths of output artifacts. |
Union field teacher_model. The teacher model that is being distilled from, e.g., "gemini-1.5-pro-002". teacher_model can be only one of the following: |
|
base_teacher_model |
The base teacher model that is being distilled, e.g., "gemini-1.0-pro-002". |
tuned_teacher_model_source |
The resource name of the Tuned teacher model. Format: |
validation_dataset_uri |
Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file. |
DoubleArray
A list of double values.
| Fields | |
|---|---|
values[] |
A list of double values. |
DynamicRetrievalConfig
Describes the options to customize dynamic retrieval.
| Fields | |
|---|---|
mode |
The mode of the predictor to be used in dynamic retrieval. |
dynamic_threshold |
Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used. |
Mode
The mode of the predictor to be used in dynamic retrieval.
| Enums | |
|---|---|
MODE_UNSPECIFIED |
Always trigger retrieval. |
MODE_DYNAMIC |
Run retrieval only when system decides it is necessary. |
EncryptionSpec
Represents a customer-managed encryption key spec that can be applied to a top-level resource.
| Fields | |
|---|---|
kms_key_name |
Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: |
Endpoint
Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.
| Fields | |
|---|---|
name |
Output only. The resource name of the Endpoint. |
display_name |
Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
description |
The description of the Endpoint. |
deployed_models[] |
Output only. The models deployed in this Endpoint. To add or remove DeployedModels use |
traffic_split |
A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. |
etag |
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
create_time |
Output only. Timestamp when this Endpoint was created. |
update_time |
Output only. Timestamp when this Endpoint was last updated. |
encryption_spec |
Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key. |
network |
Optional. The full name of the Google Compute Engine network to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, Format: |
enable_private_service_connect |
Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, |
private_service_connect_config |
Optional. Configuration for private service connect.
|
model_deployment_monitoring_job |
Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by |
predict_request_response_logging_config |
Configures the request-response logging for online prediction. |
dedicated_endpoint_enabled |
If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon. |
dedicated_endpoint_dns |
Output only. DNS of the dedicated endpoint. Will only be populated if dedicated_endpoint_enabled is true. Format: |
client_connection_config |
Configurations that are applied to the endpoint for online prediction. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
EntityIdSelector
Selector for entityId. Getting ids from the given source.
| Fields | |
|---|---|
entity_id_field |
Source column that holds entity IDs. If not provided, entity IDs are extracted from the column named entity_id. |
Union field EntityIdsSource. Details about the source data, including the location of the storage and the format. EntityIdsSource can be only one of the following: |
|
csv_source |
Source of Csv |
EntityType
An entity type is a type of object in a system that needs to be modeled and have stored information about. For example, driver is an entity type, and driver0 is an instance of an entity type driver.
| Fields | |
|---|---|
name |
Immutable. Name of the EntityType. Format: The last part entity_type is assigned by the client. The entity_type can be up to 64 characters long and can consist only of ASCII Latin letters A-Z and a-z and underscore(_), and ASCII digits 0-9 starting with a letter. The value will be unique given a featurestore. |
description |
Optional. Description of the EntityType. |
create_time |
Output only. Timestamp when this EntityType was created. |
update_time |
Output only. Timestamp when this EntityType was most recently updated. |
labels |
Optional. The labels with user-defined metadata to organize your EntityTypes. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one EntityType (System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
etag |
Optional. Used to perform a consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
monitoring_config |
Optional. The default monitoring configuration for all Features with value type ( If this is populated with [FeaturestoreMonitoringConfig.monitoring_interval] specified, snapshot analysis monitoring is enabled. Otherwise, snapshot analysis monitoring is disabled. |
offline_storage_ttl_days |
Optional. Config for data retention policy in offline storage. TTL in days for feature values that will be stored in offline storage. The Feature Store offline storage periodically removes obsolete feature values older than |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
EnvVar
Represents an environment variable present in a Container or Python Module.
| Fields | |
|---|---|
name |
Required. Name of the environment variable. Must be a valid C identifier. |
value |
Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. |
ErrorAnalysisAnnotation
Model error analysis for each annotation.
| Fields | |
|---|---|
attributed_items[] |
Attributed items for a given annotation, typically representing neighbors from the training sets constrained by the query type. |
query_type |
The query type used for finding the attributed items. |
outlier_score |
The outlier score of this annotated item. Usually defined as the min of all distances from attributed items. |
outlier_threshold |
The threshold used to determine if this annotation is an outlier or not. |
AttributedItem
Attributed items for a given annotation, typically representing neighbors from the training sets constrained by the query type.
| Fields | |
|---|---|
annotation_resource_name |
The unique ID for each annotation. Used by FE to allocate the annotation in DB. |
distance |
The distance of this item to the annotation. |
QueryType
The query type used for finding the attributed items.
| Enums | |
|---|---|
QUERY_TYPE_UNSPECIFIED |
Unspecified query type for model error analysis. |
ALL_SIMILAR |
Query similar samples across all classes in the dataset. |
SAME_CLASS_SIMILAR |
Query similar samples from the same class of the input sample. |
SAME_CLASS_DISSIMILAR |
Query dissimilar samples from the same class of the input sample. |
EvaluateDatasetOperationMetadata
Operation metadata for Dataset Evaluation.
| Fields | |
|---|---|
generic_metadata |
Generic operation metadata. |
EvaluateDatasetRequest
Request message for EvaluationService.EvaluateDataset.
| Fields | |
|---|---|
location |
Required. The resource name of the Location to evaluate the dataset. Format: |
dataset |
Required. The dataset used for evaluation. |
metrics[] |
Required. The metrics used for evaluation. |
output_config |
Required. Config for evaluation output. |
autorater_config |
Optional. Autorater config used for evaluation. |
EvaluateDatasetResponse
Response in LRO for EvaluationService.EvaluateDataset.
| Fields | |
|---|---|
output_info |
Output only. Output info for EvaluationService.EvaluateDataset. |
EvaluateInstancesRequest
Request message for EvaluationService.EvaluateInstances.
| Fields | |
|---|---|
location |
Required. The resource name of the Location to evaluate the instances. Format: |
autorater_config |
Optional. Autorater config used for evaluation. |
Union field metric_inputs. Instances and specs for evaluation metric_inputs can be only one of the following: |
|
exact_match_input |
Auto metric instances. Instances and metric spec for exact match metric. |
bleu_input |
Instances and metric spec for bleu metric. |
rouge_input |
Instances and metric spec for rouge metric. |
fluency_input |
LLM-based metric instance. General text generation metrics, applicable to other categories. Input for fluency metric. |
coherence_input |
Input for coherence metric. |
safety_input |
Input for safety metric. |
groundedness_input |
Input for groundedness metric. |
fulfillment_input |
Input for fulfillment metric. |
summarization_quality_input |
Input for summarization quality metric. |
pairwise_summarization_quality_input |
Input for pairwise summarization quality metric. |
summarization_helpfulness_input |
Input for summarization helpfulness metric. |
summarization_verbosity_input |
Input for summarization verbosity metric. |
question_answering_quality_input |
Input for question answering quality metric. |
pairwise_question_answering_quality_input |
Input for pairwise question answering quality metric. |
question_answering_relevance_input |
Input for question answering relevance metric. |
question_answering_helpfulness_input |
Input for question answering helpfulness metric. |
question_answering_correctness_input |
Input for question answering correctness metric. |
pointwise_metric_input |
Input for pointwise metric. |
pairwise_metric_input |
Input for pairwise metric. |
tool_call_valid_input |
Tool call metric instances. Input for tool call valid metric. |
tool_name_match_input |
Input for tool name match metric. |
tool_parameter_key_match_input |
Input for tool parameter key match metric. |
tool_parameter_kv_match_input |
Input for tool parameter key value match metric. |
comet_input |
Translation metrics. Input for Comet metric. |
metricx_input |
Input for Metricx metric. |
trajectory_exact_match_input |
Input for trajectory exact match metric. |
trajectory_in_order_match_input |
Input for trajectory in order match metric. |
trajectory_any_order_match_input |
Input for trajectory match any order metric. |
trajectory_precision_input |
Input for trajectory precision metric. |
trajectory_recall_input |
Input for trajectory recall metric. |
trajectory_single_tool_use_input |
Input for trajectory single tool use metric. |
EvaluateInstancesResponse
Response message for EvaluationService.EvaluateInstances.
| Fields | |
|---|---|
Union field evaluation_results. Evaluation results will be served in the same order as presented in EvaluationRequest.instances. evaluation_results can be only one of the following: |
|
exact_match_results |
Auto metric evaluation results. Results for exact match metric. |
bleu_results |
Results for bleu metric. |
rouge_results |
Results for rouge metric. |
fluency_result |
LLM-based metric evaluation result. General text generation metrics, applicable to other categories. Result for fluency metric. |
coherence_result |
Result for coherence metric. |
safety_result |
Result for safety metric. |
groundedness_result |
Result for groundedness metric. |
fulfillment_result |
Result for fulfillment metric. |
summarization_quality_result |
Summarization only metrics. Result for summarization quality metric. |
pairwise_summarization_quality_result |
Result for pairwise summarization quality metric. |
summarization_helpfulness_result |
Result for summarization helpfulness metric. |
summarization_verbosity_result |
Result for summarization verbosity metric. |
question_answering_quality_result |
Question answering only metrics. Result for question answering quality metric. |
pairwise_question_answering_quality_result |
Result for pairwise question answering quality metric. |
question_answering_relevance_result |
Result for question answering relevance metric. |
question_answering_helpfulness_result |
Result for question answering helpfulness metric. |
question_answering_correctness_result |
Result for question answering correctness metric. |
pointwise_metric_result |
Generic metrics. Result for pointwise metric. |
pairwise_metric_result |
Result for pairwise metric. |
tool_call_valid_results |
Tool call metrics. Results for tool call valid metric. |
tool_name_match_results |
Results for tool name match metric. |
tool_parameter_key_match_results |
Results for tool parameter key match metric. |
tool_parameter_kv_match_results |
Results for tool parameter key value match metric. |
comet_result |
Translation metrics. Result for Comet metric. |
metricx_result |
Result for Metricx metric. |
trajectory_exact_match_results |
Result for trajectory exact match metric. |
trajectory_in_order_match_results |
Result for trajectory in order match metric. |
trajectory_any_order_match_results |
Result for trajectory any order match metric. |
trajectory_precision_results |
Result for trajectory precision metric. |
trajectory_recall_results |
Results for trajectory recall metric. |
trajectory_single_tool_use_results |
Results for trajectory single tool use metric. |
EvaluatedAnnotation
True positive, false positive, or false negative.
EvaluatedAnnotation is only available under ModelEvaluationSlice with slice of annotationSpec dimension.
| Fields | |
|---|---|
type |
Output only. Type of the EvaluatedAnnotation. |
predictions[] |
Output only. The model predicted annotations. For true positive, there is one and only one prediction, which matches the only one ground truth annotation in For false positive, there is one and only one prediction, which doesn't match any ground truth annotation of the corresponding For false negative, there are zero or more predictions which are similar to the only ground truth annotation in The schema of the prediction is stored in [ModelEvaluation.annotation_schema_uri][] |
ground_truths[] |
Output only. The ground truth Annotations, i.e. the Annotations that exist in the test data the Model is evaluated on. For true positive, there is one and only one ground truth annotation, which matches the only prediction in For false positive, there are zero or more ground truth annotations that are similar to the only prediction in For false negative, there is one and only one ground truth annotation, which doesn't match any predictions created by the model. The schema of the ground truth is stored in [ModelEvaluation.annotation_schema_uri][] |
data_item_payload |
Output only. The data item payload that the Model predicted this EvaluatedAnnotation on. |
evaluated_data_item_view_id |
Output only. ID of the EvaluatedDataItemView under the same ancestor ModelEvaluation. The EvaluatedDataItemView consists of all ground truths and predictions on |
explanations[] |
Explanations of The attributions list in the |
error_analysis_annotations[] |
Annotations of model error analysis results. |
EvaluatedAnnotationType
Describes the type of the EvaluatedAnnotation. The type is determined
| Enums | |
|---|---|
EVALUATED_ANNOTATION_TYPE_UNSPECIFIED |
Invalid value. |
TRUE_POSITIVE |
The EvaluatedAnnotation is a true positive. It has a prediction created by the Model and a ground truth Annotation which the prediction matches. |
FALSE_POSITIVE |
The EvaluatedAnnotation is false positive. It has a prediction created by the Model which does not match any ground truth annotation. |
FALSE_NEGATIVE |
The EvaluatedAnnotation is false negative. It has a ground truth annotation which is not matched by any of the model created predictions. |
EvaluatedAnnotationExplanation
Explanation result of the prediction produced by the Model.
| Fields | |
|---|---|
explanation_type |
Explanation type. For AutoML Image Classification models, possible values are:
|
explanation |
Explanation attribution response details. |
EvaluationDataset
The dataset used for evaluation.
| Fields | |
|---|---|
Union field source. The source of the dataset. source can be only one of the following: |
|
gcs_source |
Cloud storage source holds the dataset. |
bigquery_source |
BigQuery source holds the dataset. |
Event
An edge describing the relationship between an Artifact and an Execution in a lineage graph.
| Fields | |
|---|---|
artifact |
Required. The relative resource name of the Artifact in the Event. |
execution |
Output only. The relative resource name of the Execution in the Event. |
event_time |
Output only. Time the Event occurred. |
type |
Required. The type of the Event. |
labels |
The labels with user-defined metadata to annotate Events. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Event (System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
Type
Describes whether an Event's Artifact is the Execution's input or output.
| Enums | |
|---|---|
TYPE_UNSPECIFIED |
Unspecified whether input or output of the Execution. |
INPUT |
An input of the Execution. |
OUTPUT |
An output of the Execution. |
ExactMatchInput
Input for exact match metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for exact match metric. |
instances[] |
Required. Repeated exact match instances. |
ExactMatchInstance
Spec for exact match instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Required. Ground truth used to compare against the prediction. |
ExactMatchMetricValue
Exact match metric value for an instance.
| Fields | |
|---|---|
score |
Output only. Exact match score. |
ExactMatchResults
Results for exact match metric.
| Fields | |
|---|---|
exact_match_metric_values[] |
Output only. Exact match metric values. |
ExactMatchSpec
This type has no fields.
Spec for exact match metric - returns 1 if prediction and reference exactly matches, otherwise 0.
Examples
Example-based explainability that returns the nearest neighbors from the provided dataset.
| Fields | |
|---|---|
gcs_source |
The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search. |
neighbor_count |
The number of neighbors to return when querying for examples. |
Union field
|
|
example_gcs_source |
The Cloud Storage input instances. |
Union field
|
|
nearest_neighbor_search_config |
The full configuration for the generated index, the semantics are the same as |
presets |
Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality. |
ExampleGcsSource
The Cloud Storage input instances.
| Fields | |
|---|---|
data_format |
The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported. |
gcs_source |
The Cloud Storage location for the input instances. |
DataFormat
The format of the input example instances.
| Enums | |
|---|---|
DATA_FORMAT_UNSPECIFIED |
Format unspecified, used when unset. |
JSONL |
Examples are stored in JSONL files. |
ExamplesOverride
Overrides for example-based explanations.
| Fields | |
|---|---|
neighbor_count |
The number of neighbors to return. |
crowding_count |
The number of neighbors to return that have the same crowding tag. |
restrictions[] |
Restrict the resulting nearest neighbors to respect these constraints. |
return_embeddings |
If true, return the embeddings instead of neighbors. |
data_format |
The format of the data being provided with each call. |
DataFormat
Data format enum.
| Enums | |
|---|---|
DATA_FORMAT_UNSPECIFIED |
Unspecified format. Must not be used. |
INSTANCES |
Provided data is a set of model inputs. |
EMBEDDINGS |
Provided data is a set of embeddings. |
ExamplesRestrictionsNamespace
Restrictions namespace for example-based explanations overrides.
| Fields | |
|---|---|
namespace_name |
The namespace name. |
allow[] |
The list of allowed tags. |
deny[] |
The list of deny tags. |
ExecutableCode
Code generated by the model that is meant to be executed, and the result returned to the model.
Generated when using the [FunctionDeclaration] tool and [FunctionCallingConfig] mode is set to [Mode.CODE].
| Fields | |
|---|---|
language |
Required. Programming language of the |
code |
Required. The code to be executed. |
Language
Supported programming languages for the generated code.
| Enums | |
|---|---|
LANGUAGE_UNSPECIFIED |
Unspecified language. This value should not be used. |
PYTHON |
Python >= 3.10, with numpy and simpy available. |
ExecuteExtensionRequest
Request message for ExtensionExecutionService.ExecuteExtension.
| Fields | |
|---|---|
name |
Required. Name (identifier) of the extension; Format: |
operation_id |
Required. The desired ID of the operation to be executed in this extension as defined in |
operation_params |
Optional. Request parameters that will be used for executing this operation. The struct should be in a form of map with param name as the key and actual param value as the value. E.g. If this operation requires a param "name" to be set to "abc". you can set this to something like {"name": "abc"}. |
runtime_auth_config |
Optional. Auth config provided at runtime to override the default value in [Extension.manifest.auth_config][]. The AuthConfig.auth_type should match the value in [Extension.manifest.auth_config][]. |
ExecuteExtensionResponse
Response message for ExtensionExecutionService.ExecuteExtension.
| Fields | |
|---|---|
content |
Response content from the extension. The content should be conformant to the response.content schema in the extension's manifest/OpenAPI spec. |
Execution
Instance of a general execution.
| Fields | |
|---|---|
name |
Output only. The resource name of the Execution. |
display_name |
User provided display name of the Execution. May be up to 128 Unicode characters. |
state |
The state of this Execution. This is a property of the Execution, and does not imply or capture any ongoing process. This property is managed by clients (such as Vertex AI Pipelines) and the system does not prescribe or check the validity of state transitions. |
etag |
An eTag used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
The labels with user-defined metadata to organize your Executions. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Execution (System labels are excluded). |
create_time |
Output only. Timestamp when this Execution was created. |
update_time |
Output only. Timestamp when this Execution was last updated. |
schema_title |
The title of the schema describing the metadata. Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store. |
schema_version |
The version of the schema in Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store. |
metadata |
Properties of the Execution. Top level metadata keys' heading and trailing spaces will be trimmed. The size of this field should not exceed 200KB. |
description |
Description of the Execution |
State
Describes the state of the Execution.
| Enums | |
|---|---|
STATE_UNSPECIFIED |
Unspecified Execution state |
NEW |
The Execution is new |
RUNNING |
The Execution is running |
COMPLETE |
The Execution has finished running |
FAILED |
The Execution has failed |
CACHED |
The Execution completed through Cache hit. |
CANCELLED |
The Execution was cancelled. |
ExplainRequest
Request message for PredictionService.Explain.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to serve the explanation. Format: |
instances[] |
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' |
parameters |
The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' |
explanation_spec_override |
If specified, overrides the |
concurrent_explanation_spec_override |
Optional. This field is the same as the one above, but supports multiple explanations to occur in parallel. The key can be any string. Each override will be run against the model, then its explanations will be grouped together. Note - these explanations are run In Addition to the default Explanation in the deployed model. |
deployed_model_id |
If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding |
ExplainResponse
Response message for PredictionService.Explain.
| Fields | |
|---|---|
explanations[] |
The explanations of the Model's It has the same number of elements as |
concurrent_explanations |
This field stores the results of the explanations run in parallel with The default explanation strategy/method. |
deployed_model_id |
ID of the Endpoint's DeployedModel that served this explanation. |
predictions[] |
The predictions that are the output of the predictions call. Same as |
ConcurrentExplanation
This message is a wrapper grouping Concurrent Explanations.
| Fields | |
|---|---|
explanations[] |
The explanations of the Model's It has the same number of elements as |
Explanation
Explanation of a prediction (provided in PredictResponse.predictions) produced by the Model on a given instance.
| Fields | |
|---|---|
attributions[] |
Output only. Feature attributions grouped by predicted outputs. For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of If users set |
neighbors[] |
Output only. List of the nearest neighbors for example-based explanations. For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated. |
ExplanationMetadata
Metadata describing the Model's input and output for explanation.
| Fields | |
|---|---|
inputs |
Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, For custom images, the key must match with the key in |
outputs |
Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed. |
feature_attributions_schema_uri |
Points to a YAML file stored on Google Cloud Storage describing the format of the |
latent_space_source |
Name of the source to generate embeddings for example based explanations. |
InputMetadata
Metadata of the input of a feature.
Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
| Fields | |
|---|---|
input_baselines[] |
Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the |
input_tensor_name |
Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow. |
encoding |
Defines how the feature is encoded into the input tensor. Defaults to IDENTITY. |
modality |
Modality of the feature. Valid values are: numeric, image. Defaults to numeric. |
feature_value_domain |
The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized. |
indices_tensor_name |
Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor. |
dense_shape_tensor_name |
Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor. |
index_feature_mapping[] |
A list of feature names for each index in the input tensor. Required when the input |
encoded_tensor_name |
Encoded tensor is a transformation of the input tensor. Must be provided if choosing An encoded tensor is generated if the input tensor is encoded by a lookup table. |
encoded_baselines[] |
A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor. |
visualization |
Visualization configurations for image explanation. |
group_name |
Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in |
Encoding
Defines how a feature is encoded. Defaults to IDENTITY.
| Enums | |
|---|---|
ENCODING_UNSPECIFIED |
Default value. This is the same as IDENTITY. |
IDENTITY |
The tensor represents one feature. |
BAG_OF_FEATURES |
The tensor represents a bag of features where each index maps to a feature. |
BAG_OF_FEATURES_SPARSE |
The tensor represents a bag of features where each index maps to a feature. Zero values in the tensor indicates feature being non-existent. |
INDICATOR |
The tensor is a list of binaries representing whether a feature exists or not (1 indicates existence). |
COMBINED_EMBEDDING |
The tensor is encoded into a 1-dimensional array represented by an encoded tensor. |
CONCAT_EMBEDDING |
Select this encoding when the input tensor is encoded into a 2-dimensional array represented by an encoded tensor. |
FeatureValueDomain
Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained.
| Fields | |
|---|---|
min_value |
The minimum permissible value for this feature. |
max_value |
The maximum permissible value for this feature. |
original_mean |
If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization. |
original_stddev |
If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization. |
Visualization
Visualization configurations for image explanation.
| Fields | |
|---|---|
type |
Type of the image visualization. Only applicable to |
polarity |
Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE. |
color_map |
The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Defaults to VIRIDIS for |
clip_percent_upperbound |
Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9. |
clip_percent_lowerbound |
Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62. |
overlay_type |
How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE. |
ColorMap
The color scheme used for highlighting areas.
| Enums | |
|---|---|
COLOR_MAP_UNSPECIFIED |
Should not be used. |
PINK_GREEN |
Positive: green. Negative: pink. |
VIRIDIS |
Viridis color map: A perceptually uniform color mapping which is easier to see by those with colorblindness and progresses from yellow to green to blue. Positive: yellow. Negative: blue. |
RED |
Positive: red. Negative: red. |
GREEN |
Positive: green. Negative: green. |
RED_GREEN |
Positive: green. Negative: red. |
PINK_WHITE_GREEN |
PiYG palette. |
OverlayType
How the original image is displayed in the visualization.
| Enums | |
|---|---|
OVERLAY_TYPE_UNSPECIFIED |
Default value. This is the same as NONE. |
NONE |
No overlay. |
ORIGINAL |
The attributions are shown on top of the original image. |
GRAYSCALE |
The attributions are shown on top of grayscaled version of the original image. |
MASK_BLACK |
The attributions are used as a mask to reveal predictive parts of the image and hide the un-predictive parts. |
Polarity
Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
| Enums | |
|---|---|
POLARITY_UNSPECIFIED |
Default value. This is the same as POSITIVE. |
POSITIVE |
Highlights the pixels/outlines that were most influential to the model's prediction. |
NEGATIVE |
Setting polarity to negative highlights areas that does not lead to the models's current prediction. |
BOTH |
Shows both positive and negative attributions. |
Type
Type of the image visualization. Only applicable to Integrated Gradients attribution.
| Enums | |
|---|---|
TYPE_UNSPECIFIED |
Should not be used. |
PIXELS |
Shows which pixel contributed to the image prediction. |
OUTLINES |
Shows which region contributed to the image prediction by outlining the region. |
OutputMetadata
Metadata of the prediction output to be explained.
| Fields | |
|---|---|
output_tensor_name |
Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow. |
Union field If neither of the fields are specified, |
|
index_display_name_mapping |
Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The |
display_name_mapping_key |
Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by |
ExplanationMetadataOverride
The ExplanationMetadata entries that can be overridden at online explanation time.
| Fields | |
|---|---|
inputs |
Required. Overrides the |
InputMetadataOverride
The input metadata entries to be overridden.
| Fields | |
|---|---|
input_baselines[] |
Baseline inputs for this feature. This overrides the |
ExplanationParameters
Parameters to configure explaining for Model's predictions.
| Fields | |
|---|---|
top_k |
If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs. |
output_indices |
If populated, only returns attributions that have If not populated, returns attributions for Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes). |
Union field
|
|
sampled_shapley_attribution |
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265. |
integrated_gradients_attribution |
An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 |
xrai_attribution |
An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead. |
examples |
Example-based explanations that returns the nearest neighbors from the provided dataset. |
ExplanationSpec
Specification of Model explanation.
| Fields | |
|---|---|
parameters |
Required. Parameters that configure explaining of the Model's predictions. |
metadata |
Optional. Metadata describing the Model's input and output for explanation. |
ExplanationSpecOverride
The ExplanationSpec entries that can be overridden at online explanation time.
| Fields | |
|---|---|
parameters |
The parameters to be overridden. Note that the attribution method cannot be changed. If not specified, no parameter is overridden. |
metadata |
The metadata to be overridden. If not specified, no metadata is overridden. |
examples_override |
The example-based explanations parameter overrides. |
ExportDataConfig
Describes what part of the Dataset is to be exported, the destination of the export and how to export.
| Fields | |
|---|---|
annotations_filter |
An expression for filtering what part of the Dataset is to be exported. Only Annotations that match this filter will be exported. The filter syntax is the same as in |
Union field destination. The destination of the output. destination can be only one of the following: |
|
gcs_destination |
The Google Cloud Storage location where the output is to be written to. In the given directory a new directory will be created with name: |
Union field split. The instructions how the export data should be split between the training, validation and test sets. split can be only one of the following: |
|
fraction_split |
Split based on fractions defining the size of each set. |
ExportDataOperationMetadata
Runtime operation information for DatasetService.ExportData.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
gcs_output_directory |
A Google Cloud Storage directory which path ends with '/'. The exported data is stored in the directory. |
ExportDataRequest
Request message for DatasetService.ExportData.
| Fields | |
|---|---|
name |
Required. The name of the Dataset resource. Format: |
export_config |
Required. The desired output location. |
ExportDataResponse
Response message for DatasetService.ExportData.
| Fields | |
|---|---|
exported_files[] |
All of the files that are exported in this export operation. For custom code training export, only three (training, validation and test) Cloud Storage paths in wildcard format are populated (for example, gs://.../training-*). |
ExportFeatureValuesOperationMetadata
Details of operations that exports Features values.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Featurestore export Feature values. |
ExportFeatureValuesRequest
Request message for FeaturestoreService.ExportFeatureValues.
| Fields | |
|---|---|
entity_type |
Required. The resource name of the EntityType from which to export Feature values. Format: |
destination |
Required. Specifies destination location and format. |
feature_selector |
Required. Selects Features to export values of. |
settings[] |
Per-Feature export settings. |
Union field mode. Required. The mode in which Feature values are exported. mode can be only one of the following: |
|
snapshot_export |
Exports the latest Feature values of all entities of the EntityType within a time range. |
full_export |
Exports all historical values of all entities of the EntityType within a time range |
FullExport
Describes exporting all historical Feature values of all entities of the EntityType between [start_time, end_time].
| Fields | |
|---|---|
start_time |
Excludes Feature values with feature generation timestamp before this timestamp. If not set, retrieve oldest values kept in Feature Store. Timestamp, if present, must not have higher than millisecond precision. |
end_time |
Exports Feature values as of this timestamp. If not set, retrieve values as of now. Timestamp, if present, must not have higher than millisecond precision. |
SnapshotExport
Describes exporting the latest Feature values of all entities of the EntityType between [start_time, snapshot_time].
| Fields | |
|---|---|
snapshot_time |
Exports Feature values as of this timestamp. If not set, retrieve values as of now. Timestamp, if present, must not have higher than millisecond precision. |
start_time |
Excludes Feature values with feature generation timestamp before this timestamp. If not set, retrieve oldest values kept in Feature Store. Timestamp, if present, must not have higher than millisecond precision. |
ExportFeatureValuesResponse
This type has no fields.
Response message for FeaturestoreService.ExportFeatureValues.
ExportFractionSplit
Assigns the input data to training, validation, and test sets as per the given fractions. Any of training_fraction, validation_fraction and test_fraction may optionally be provided, they must sum to up to 1. If the provided ones sum to less than 1, the remainder is assigned to sets as decided by Vertex AI. If none of the fractions are set, by default roughly 80% of data is used for training, 10% for validation, and 10% for test.
| Fields | |
|---|---|
training_fraction |
The fraction of the input data that is to be used to train the Model. |
validation_fraction |
The fraction of the input data that is to be used to validate the Model. |
test_fraction |
The fraction of the input data that is to be used to evaluate the Model. |
ExportModelOperationMetadata
Details of ModelService.ExportModel operation.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
output_info |
Output only. Information further describing the output of this Model export. |
OutputInfo
Further describes the output of the ExportModel. Supplements ExportModelRequest.OutputConfig.
| Fields | |
|---|---|
artifact_output_uri |
Output only. If the Model artifact is being exported to Google Cloud Storage this is the full path of the directory created, into which the Model files are being written to. |
image_output_uri |
Output only. If the Model image is being exported to Google Container Registry or Artifact Registry this is the full path of the image created. |
ExportModelRequest
Request message for ModelService.ExportModel.
| Fields | |
|---|---|
name |
Required. The resource name of the Model to export. The resource name may contain version id or version alias to specify the version, if no version is specified, the default version will be exported. |
output_config |
Required. The desired output location and configuration. |
OutputConfig
Output configuration for the Model export.
| Fields | |
|---|---|
export_format_id |
The ID of the format in which the Model must be exported. Each Model lists the |
artifact_destination |
The Cloud Storage location where the Model artifact is to be written to. Under the directory given as the destination a new one with name " |
image_destination |
The Google Container Registry or Artifact Registry uri where the Model container image will be copied to. This field should only be set when the |
ExportModelResponse
This type has no fields.
Response message of ModelService.ExportModel operation.
ExportPublisherModelResponse
Response message for ModelGardenService.ExportPublisherModel.
| Fields | |
|---|---|
publisher_model |
The name of the PublisherModel resource. Format: |
destination_uri |
The destination uri of the model weights. |
ExportTensorboardTimeSeriesDataRequest
Request message for TensorboardService.ExportTensorboardTimeSeriesData.
| Fields | |
|---|---|
tensorboard_time_series |
Required. The resource name of the TensorboardTimeSeries to export data from. Format: |
filter |
Exports the TensorboardTimeSeries' data that match the filter expression. |
page_size |
The maximum number of data points to return per page. The default page_size is 1000. Values must be between 1 and 10000. Values above 10000 are coerced to 10000. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
Field to use to sort the TensorboardTimeSeries' data. By default, TensorboardTimeSeries' data is returned in a pseudo random order. |
ExportTensorboardTimeSeriesDataResponse
Response message for TensorboardService.ExportTensorboardTimeSeriesData.
| Fields | |
|---|---|
time_series_data_points[] |
The returned time series data points. |
next_page_token |
A token, which can be sent as |
Extension
Extensions are tools for large language models to access external data, run computations, etc.
| Fields | |
|---|---|
name |
Identifier. The resource name of the Extension. |
display_name |
Required. The display name of the Extension. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
description |
Optional. The description of the Extension. |
create_time |
Output only. Timestamp when this Extension was created. |
update_time |
Output only. Timestamp when this Extension was most recently updated. |
etag |
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
manifest |
Required. Manifest of the Extension. |
extension_operations[] |
Output only. Supported operations. |
runtime_config |
Optional. Runtime config controlling the runtime behavior of this Extension. |
tool_use_examples[] |
Optional. Examples to illustrate the usage of the extension as a tool. |
private_service_connect_config |
Optional. The PrivateServiceConnect config for the extension. If specified, the service endpoints associated with the Extension should be registered with private network access in the provided Service Directory. If the service contains more than one endpoint with a network, the service will arbitrarilty choose one of the endpoints to use for extension execution. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
ExtensionManifest
Manifest spec of an Extension needed for runtime execution.
| Fields | |
|---|---|
name |
Required. Extension name shown to the LLM. The name can be up to 128 characters long. |
description |
Required. The natural language description shown to the LLM. It should describe the usage of the extension, and is essential for the LLM to perform reasoning. e.g., if the extension is a data store, you can let the LLM know what data it contains. |
api_spec |
Required. Immutable. The API specification shown to the LLM. |
auth_config |
Required. Immutable. Type of auth supported by this extension. |
ApiSpec
The API specification shown to the LLM.
| Fields | |
|---|---|
Union field
|
|
open_api_yaml |
The API spec in Open API standard and YAML format. |
open_api_gcs_uri |
Cloud Storage URI pointing to the OpenAPI spec. |
ExtensionOperation
Operation of an extension.
| Fields | |
|---|---|
operation_id |
Operation ID that uniquely identifies the operations among the extension. See: "Operation Object" in https://swagger.io/specification/. This field is parsed from the OpenAPI spec. For HTTP extensions, if it does not exist in the spec, we will generate one from the HTTP method and path. |
function_declaration |
Output only. Structured representation of a function declaration as defined by the OpenAPI Spec. |
ExtensionPrivateServiceConnectConfig
PrivateExtensionConfig configuration for the extension.
| Fields | |
|---|---|
service_directory |
Required. The Service Directory resource name in which the service endpoints associated to the extension are registered. Format:
|
Fact
The fact used in grounding.
| Fields | |
|---|---|
query |
Query that is used to retrieve this fact. |
title |
If present, it refers to the title of this fact. |
uri |
If present, this uri links to the source of the fact. |
summary |
If present, the summary/snippet of the fact. |
vector_distance |
If present, the distance between the query vector and this fact vector. |
score |
If present, according to the underlying Vector DB and the selected metric type, the score can be either the distance or the similarity between the query and the fact and its range depends on the metric type. For example, if the metric type is COSINE_DISTANCE, it represents the distance between the query and the fact. The larger the distance, the less relevant the fact is to the query. The range is [0, 2], while 0 means the most relevant and 2 means the least relevant. |
FasterDeploymentConfig
Configuration for faster model deployment.
| Fields | |
|---|---|
fast_tryout_enabled |
If true, enable fast tryout feature for this deployed model. |
Feature
Feature Metadata information. For example, color is a feature that describes an apple.
| Fields | |
|---|---|
name |
Immutable. Name of the Feature. Format: The last part feature is assigned by the client. The feature can be up to 64 characters long and can consist only of ASCII Latin letters A-Z and a-z, underscore(_), and ASCII digits 0-9 starting with a letter. The value will be unique given an entity type. |
description |
Description of the Feature. |
value_type |
Immutable. Only applicable for Vertex AI Feature Store (Legacy). Type of Feature value. |
create_time |
Output only. Only applicable for Vertex AI Feature Store (Legacy). Timestamp when this EntityType was created. |
update_time |
Output only. Only applicable for Vertex AI Feature Store (Legacy). Timestamp when this EntityType was most recently updated. |
labels |
Optional. The labels with user-defined metadata to organize your Features. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one Feature (System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
etag |
Used to perform a consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
monitoring_config |
Optional. Only applicable for Vertex AI Feature Store (Legacy). Deprecated: The custom monitoring configuration for this Feature, if not set, use the monitoring_config defined for the EntityType this Feature belongs to. Only Features with type ( If this is populated with [FeaturestoreMonitoringConfig.disabled][] = true, snapshot analysis monitoring is disabled; if [FeaturestoreMonitoringConfig.monitoring_interval][] specified, snapshot analysis monitoring is enabled. Otherwise, snapshot analysis monitoring config is same as the EntityType's this Feature belongs to. |
disable_monitoring |
Optional. Only applicable for Vertex AI Feature Store (Legacy). If not set, use the monitoring_config defined for the EntityType this Feature belongs to. Only Features with type ( If set to true, all types of data monitoring are disabled despite the config on EntityType. |
monitoring_stats[] |
Output only. Only applicable for Vertex AI Feature Store (Legacy). A list of historical |
monitoring_stats_anomalies[] |
Output only. Only applicable for Vertex AI Feature Store (Legacy). The list of historical stats and anomalies with specified objectives. |
feature_stats_and_anomaly[] |
Output only. Only applicable for Vertex AI Feature Store. The list of historical stats and anomalies. |
version_column_name |
Only applicable for Vertex AI Feature Store. The name of the BigQuery Table/View column hosting data for this version. If no value is provided, will use feature_id. |
point_of_contact |
Entity responsible for maintaining this feature. Can be comma separated list of email addresses or URIs. |
MonitoringStatsAnomaly
A list of historical SnapshotAnalysis or ImportFeaturesAnalysis stats requested by user, sorted by FeatureStatsAnomaly.start_time descending.
| Fields | |
|---|---|
objective |
Output only. The objective for each stats. |
feature_stats_anomaly |
Output only. The stats and anomalies generated at specific timestamp. |
Objective
If the objective in the request is both Import Feature Analysis and Snapshot Analysis, this objective could be one of them. Otherwise, this objective should be the same as the objective in the request.
| Enums | |
|---|---|
OBJECTIVE_UNSPECIFIED |
If it's OBJECTIVE_UNSPECIFIED, monitoring_stats will be empty. |
IMPORT_FEATURE_ANALYSIS |
Stats are generated by Import Feature Analysis. |
SNAPSHOT_ANALYSIS |
Stats are generated by Snapshot Analysis. |
ValueType
Only applicable for Vertex AI Legacy Feature Store. An enum representing the value type of a feature.
| Enums | |
|---|---|
VALUE_TYPE_UNSPECIFIED |
The value type is unspecified. |
BOOL |
Used for Feature that is a boolean. |
BOOL_ARRAY |
Used for Feature that is a list of boolean. |
DOUBLE |
Used for Feature that is double. |
DOUBLE_ARRAY |
Used for Feature that is a list of double. |
INT64 |
Used for Feature that is INT64. |
INT64_ARRAY |
Used for Feature that is a list of INT64. |
STRING |
Used for Feature that is string. |
STRING_ARRAY |
Used for Feature that is a list of String. |
BYTES |
Used for Feature that is bytes. |
STRUCT |
Used for Feature that is struct. |
FeatureGroup
Vertex AI Feature Group.
| Fields | |
|---|---|
name |
Identifier. Name of the FeatureGroup. Format: |
create_time |
Output only. Timestamp when this FeatureGroup was created. |
update_time |
Output only. Timestamp when this FeatureGroup was last updated. |
etag |
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
Optional. The labels with user-defined metadata to organize your FeatureGroup. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one FeatureGroup(System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
description |
Optional. Description of the FeatureGroup. |
service_agent_type |
Optional. Service agent type used during jobs under a FeatureGroup. By default, the Vertex AI Service Agent is used. When using an IAM Policy to isolate this FeatureGroup within a project, a separate service account should be provisioned by setting this field to |
service_account_email |
Output only. A Service Account unique to this FeatureGroup. The role bigquery.dataViewer should be granted to this service account to allow Vertex AI Feature Store to access source data while running jobs under this FeatureGroup. |
Union field
|
|
big_query |
Indicates that features for this group come from BigQuery Table/View. By default treats the source as a sparse time series source. The BigQuery source table or view must have at least one entity ID column and a column named |
BigQuery
Input source type for BigQuery Tables and Views.
| Fields | |
|---|---|
big_query_source |
Required. Immutable. The BigQuery source URI that points to either a BigQuery Table or View. |
entity_id_columns[] |
Optional. Columns to construct entity_id / row keys. If not provided defaults to |
static_data_source |
Optional. Set if the data source is not a time-series. |
time_series |
Optional. If the source is a time-series source, this can be set to control how downstream sources (ex: |
dense |
Optional. If set, all feature values will be fetched from a single row per unique entityId including nulls. If not set, will collapse all rows for each unique entityId into a singe row with any non-null values if present, if no non-null values are present will sync null. ex: If source has schema |
TimeSeries
| Fields | |
|---|---|
timestamp_column |
Optional. Column hosting timestamp values for a time-series source. Will be used to determine the latest |
ServiceAgentType
Service agent type used during jobs under a FeatureGroup.
| Enums | |
|---|---|
SERVICE_AGENT_TYPE_UNSPECIFIED |
By default, the project-level Vertex AI Service Agent is enabled. |
SERVICE_AGENT_TYPE_PROJECT |
Specifies the project-level Vertex AI Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). |
SERVICE_AGENT_TYPE_FEATURE_GROUP |
Enable a FeatureGroup service account to be created by Vertex AI and output in the field service_account_email. This service account will be used to read from the source BigQuery table during jobs under a FeatureGroup. |
FeatureMonitor
Vertex AI Feature Monitor.
| Fields | |
|---|---|
name |
Identifier. Name of the FeatureMonitor. Format: |
create_time |
Output only. Timestamp when this FeatureMonitor was created. |
update_time |
Output only. Timestamp when this FeatureMonitor was last updated. |
etag |
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
Optional. The labels with user-defined metadata to organize your FeatureMonitor. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one FeatureMonitor(System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
description |
Optional. Description of the FeatureMonitor. |
schedule_config |
Required. Schedule config for the FeatureMonitor. |
feature_selection_config |
Required. Feature selection config for the FeatureMonitor. |
FeatureMonitorJob
Vertex AI Feature Monitor Job.
| Fields | |
|---|---|
name |
Identifier. Name of the FeatureMonitorJob. Format: |
create_time |
Output only. Timestamp when this FeatureMonitorJob was created. Creation of a FeatureMonitorJob means that the job is pending / waiting for sufficient resources but may not have started running yet. |
final_status |
Output only. Final status of the FeatureMonitorJob. |
job_summary |
Output only. Summary from the FeatureMonitorJob. |
labels |
Optional. The labels with user-defined metadata to organize your FeatureMonitorJob. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one FeatureMonitor(System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
description |
Optional. Description of the FeatureMonitor. |
drift_base_feature_monitor_job_id |
Output only. FeatureMonitorJob ID comparing to which the drift is calculated. |
drift_base_snapshot_time |
Output only. Data snapshot time comparing to which the drift is calculated. |
feature_selection_config |
Output only. Feature selection config used when creating FeatureMonitorJob. |
trigger_type |
Output only. Trigger type of the Feature Monitor Job. |
FeatureMonitorJobTrigger
Choices of the trigger type.
| Enums | |
|---|---|
FEATURE_MONITOR_JOB_TRIGGER_UNSPECIFIED |
Trigger type unspecified. |
FEATURE_MONITOR_JOB_TRIGGER_PERIODIC |
Triggered by periodic schedule. |
FEATURE_MONITOR_JOB_TRIGGER_ON_DEMAND |
Triggered on demand by CreateFeatureMonitorJob request. |
JobSummary
Summary from the FeatureMonitorJob.
| Fields | |
|---|---|
total_slot_ms |
Output only. BigQuery slot milliseconds consumed. |
feature_stats_and_anomalies[] |
Output only. Features and their stats and anomalies |
FeatureNoiseSigma
Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients.
| Fields | |
|---|---|
noise_sigma[] |
Noise sigma per feature. No noise is added to features that are not set. |
NoiseSigmaForFeature
Noise sigma for a single feature.
| Fields | |
|---|---|
name |
The name of the input feature for which noise sigma is provided. The features are defined in |
sigma |
This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to |
FeatureOnlineStore
Vertex AI Feature Online Store provides a centralized repository for serving ML features and embedding indexes at low latency. The Feature Online Store is a top-level container.
| Fields | |
|---|---|
name |
Identifier. Name of the FeatureOnlineStore. Format: |
create_time |
Output only. Timestamp when this FeatureOnlineStore was created. |
update_time |
Output only. Timestamp when this FeatureOnlineStore was last updated. |
etag |
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
Optional. The labels with user-defined metadata to organize your FeatureOnlineStore. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one FeatureOnlineStore(System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
state |
Output only. State of the featureOnlineStore. |
dedicated_serving_endpoint |
Optional. The dedicated serving endpoint for this FeatureOnlineStore, which is different from common Vertex service endpoint. |
embedding_management |
Optional. Deprecated: This field is no longer needed anymore and embedding management is automatically enabled when specifying Optimized storage type. |
encryption_spec |
Optional. Customer-managed encryption key spec for data storage. If set, online store will be secured by this key. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
Union field
|
|
bigtable |
Contains settings for the Cloud Bigtable instance that will be created to serve featureValues for all FeatureViews under this FeatureOnlineStore. |
optimized |
Contains settings for the Optimized store that will be created to serve featureValues for all FeatureViews under this FeatureOnlineStore. When choose Optimized storage type, need to set |
Bigtable
| Fields | |
|---|---|
auto_scaling |
Required. Autoscaling config applied to Bigtable Instance. |
AutoScaling
| Fields | |
|---|---|
min_node_count |
Required. The minimum number of nodes to scale down to. Must be greater than or equal to 1. |
max_node_count |
Required. The maximum number of nodes to scale up to. Must be greater than or equal to min_node_count, and less than or equal to 10 times of 'min_node_count'. |
cpu_utilization_target |
Optional. A percentage of the cluster's CPU capacity. Can be from 10% to 80%. When a cluster's CPU utilization exceeds the target that you have set, Bigtable immediately adds nodes to the cluster. When CPU utilization is substantially lower than the target, Bigtable removes nodes. If not set will default to 50%. |
DedicatedServingEndpoint
The dedicated serving endpoint for this FeatureOnlineStore. Only need to set when you choose Optimized storage type. Public endpoint is provisioned by default.
| Fields | |
|---|---|
public_endpoint_domain_name |
Output only. This field will be populated with the domain name to use for this FeatureOnlineStore |
private_service_connect_config |
Optional. Private service connect config. The private service connection is available only for Optimized storage type, not for embedding management now. If |
service_attachment |
Output only. The name of the service attachment resource. Populated if private service connect is enabled and after FeatureViewSync is created. |
EmbeddingManagement
Deprecated: This sub message is no longer needed anymore and embedding management is automatically enabled when specifying Optimized storage type. Contains settings for embedding management.
| Fields | |
|---|---|
enabled |
Optional. Immutable. Whether to enable embedding management in this FeatureOnlineStore. It's immutable after creation to ensure the FeatureOnlineStore availability. |
Optimized
This type has no fields.
Optimized storage type
State
Possible states a featureOnlineStore can have.
| Enums | |
|---|---|
STATE_UNSPECIFIED |
Default value. This value is unused. |
STABLE |
State when the featureOnlineStore configuration is not being updated and the fields reflect the current configuration of the featureOnlineStore. The featureOnlineStore is usable in this state. |
UPDATING |
The state of the featureOnlineStore configuration when it is being updated. During an update, the fields reflect either the original configuration or the updated configuration of the featureOnlineStore. The featureOnlineStore is still usable in this state. |
FeatureSelectionConfig
Feature selection configuration for the FeatureMonitor.
| Fields | |
|---|---|
feature_configs[] |
Optional. A list of features to be monitored and each feature's drift threshold. |
FeatureConfig
Feature configuration.
| Fields | |
|---|---|
feature_id |
Required. The ID of the feature resource. Final component of the Feature's resource name. |
drift_threshold |
Optional. Drift threshold. If calculated difference with baseline data larger than threshold, it will be considered as the feature has drift. If not present, the threshold will be default to 0.3. |
FeatureSelector
Selector for Features of an EntityType.
| Fields | |
|---|---|
id_matcher |
Required. Matches Features based on ID. |
FeatureStatsAndAnomaly
Stats and Anomaly generated by FeatureMonitorJobs. Anomaly only includes Drift.
| Fields | |
|---|---|
feature_id |
Feature Id. |
feature_stats |
Feature stats. e.g. histogram buckets. In the format of tensorflow.metadata.v0.DatasetFeatureStatistics. |
distribution_deviation |
Deviation from the current stats to baseline stats. 1. For categorical feature, the distribution distance is calculated by L-inifinity norm. 2. For numerical feature, the distribution distance is calculated by Jensen–Shannon divergence. |
drift_detection_threshold |
This is the threshold used when detecting drifts, which is set in FeatureMonitor.FeatureSelectionConfig.FeatureConfig.drift_threshold |
drift_detected |
If set to true, indicates current stats is detected as and comparing with baseline stats. |
stats_time |
The timestamp we take snapshot for feature values to generate stats. |
feature_monitor_job_id |
The ID of the FeatureMonitorJob that generated this FeatureStatsAndAnomaly. |
feature_monitor_id |
The ID of the FeatureMonitor that this FeatureStatsAndAnomaly generated according to. |
FeatureStatsAndAnomalySpec
Defines how to select FeatureStatsAndAnomaly to be populated in response. If set, retrieves FeatureStatsAndAnomaly generated by FeatureMonitors based on this spec.
| Fields | |
|---|---|
stats_time_range |
Optional. If set, return all stats generated between [start_time, end_time). If latest_stats_count is set, return the most recent count of stats within the stats_time_range. |
latest_stats_count |
Optional. If set, returns the most recent count of stats. Valid value is [0, 100]. If stats_time_range is set, return most recent count of stats within the stats_time_range. |
FeatureStatsAnomaly
Stats and Anomaly generated at specific timestamp for specific Feature. The start_time and end_time are used to define the time range of the dataset that current stats belongs to, e.g. prediction traffic is bucketed into prediction datasets by time window. If the Dataset is not defined by time window, start_time = end_time. Timestamp of the stats and anomalies always refers to end_time. Raw stats and anomalies are stored in stats_uri or anomaly_uri in the tensorflow defined protos. Field data_stats contains almost identical information with the raw stats in Vertex AI defined proto, for UI to display.
| Fields | |
|---|---|
score |
Feature importance score, only populated when cross-feature monitoring is enabled. For now only used to represent feature attribution score within range [0, 1] for |
stats_uri |
Path of the stats file for current feature values in Cloud Storage bucket. Format: gs:// |
anomaly_uri |
Path of the anomaly file for current feature values in Cloud Storage bucket. Format: gs:// |
distribution_deviation |
Deviation from the current stats to baseline stats. 1. For categorical feature, the distribution distance is calculated by L-inifinity norm. 2. For numerical feature, the distribution distance is calculated by Jensen–Shannon divergence. |
anomaly_detection_threshold |
This is the threshold used when detecting anomalies. The threshold can be changed by user, so this one might be different from |
start_time |
The start timestamp of window where stats were generated. For objectives where time window doesn't make sense (e.g. Featurestore Snapshot Monitoring), start_time is only used to indicate the monitoring intervals, so it always equals to (end_time - monitoring_interval). |
end_time |
The end timestamp of window where stats were generated. For objectives where time window doesn't make sense (e.g. Featurestore Snapshot Monitoring), end_time indicates the timestamp of the data used to generate stats (e.g. timestamp we take snapshots for feature values). |
FeatureValue
Value for a feature.
| Fields | |
|---|---|
metadata |
Metadata of feature value. |
Union field value. Value for the feature. value can be only one of the following: |
|
bool_value |
Bool type feature value. |
double_value |
Double type feature value. |
int64_value |
Int64 feature value. |
string_value |
String feature value. |
bool_array_value |
A list of bool type feature value. |
double_array_value |
A list of double type feature value. |
int64_array_value |
A list of int64 type feature value. |
string_array_value |
A list of string type feature value. |
bytes_value |
Bytes feature value. |
struct_value |
A struct type feature value. |
Metadata
Metadata of feature value.
| Fields | |
|---|---|
generate_time |
Feature generation timestamp. Typically, it is provided by user at feature ingestion time. If not, feature store will use the system timestamp when the data is ingested into feature store. For streaming ingestion, the time, aligned by days, must be no older than five years (1825 days) and no later than one year (366 days) in the future. |
FeatureValueDestination
A destination location for Feature values and format.
| Fields | |
|---|---|
Union field
|
|
bigquery_destination |
Output in BigQuery format. |
tfrecord_destination |
Output in TFRecord format. Below are the mapping from Feature value type in Featurestore to Feature value type in TFRecord: |
csv_destination |
Output in CSV format. Array Feature value types are not allowed in CSV format. |
FeatureValueList
Container for list of values.
| Fields | |
|---|---|
values[] |
A list of feature values. All of them should be the same data type. |
FeatureView
FeatureView is representation of values that the FeatureOnlineStore will serve based on its syncConfig.
| Fields | |
|---|---|
name |
Identifier. Name of the FeatureView. Format: |
create_time |
Output only. Timestamp when this FeatureView was created. |
update_time |
Output only. Timestamp when this FeatureView was last updated. |
etag |
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
Optional. The labels with user-defined metadata to organize your FeatureViews. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one FeatureOnlineStore(System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
sync_config |
Configures when data is to be synced/updated for this FeatureView. At the end of the sync the latest featureValues for each entityId of this FeatureView are made ready for online serving. |
vector_search_config |
Optional. Deprecated: please use |
index_config |
Optional. Configuration for index preparation for vector search. It contains the required configurations to create an index from source data, so that approximate nearest neighbor (a.k.a ANN) algorithms search can be performed during online serving. |
optimized_config |
Optional. Configuration for FeatureView created under Optimized FeatureOnlineStore. |
service_agent_type |
Optional. Service agent type used during data sync. By default, the Vertex AI Service Agent is used. When using an IAM Policy to isolate this FeatureView within a project, a separate service account should be provisioned by setting this field to |
service_account_email |
Output only. A Service Account unique to this FeatureView. The role bigquery.dataViewer should be granted to this service account to allow Vertex AI Feature Store to sync data to the online store. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
Union field
|
|
big_query_source |
Optional. Configures how data is supposed to be extracted from a BigQuery source to be loaded onto the FeatureOnlineStore. |
feature_registry_source |
Optional. Configures the features from a Feature Registry source that need to be loaded onto the FeatureOnlineStore. |
vertex_rag_source |
Optional. The Vertex RAG Source that the FeatureView is linked to. |
BigQuerySource
| Fields | |
|---|---|
uri |
Required. The BigQuery view URI that will be materialized on each sync trigger based on FeatureView.SyncConfig. |
entity_id_columns[] |
Required. Columns to construct entity_id / row keys. |
FeatureRegistrySource
A Feature Registry source for features that need to be synced to Online Store.
| Fields | |
|---|---|
feature_groups[] |
Required. List of features that need to be synced to Online Store. |
project_number |
Optional. The project number of the parent project of the Feature Groups. |
FeatureGroup
Features belonging to a single feature group that will be synced to Online Store.
| Fields | |
|---|---|
feature_group_id |
Required. Identifier of the feature group. |
feature_ids[] |
Required. Identifiers of features under the feature group. |
IndexConfig
Configuration for vector indexing.
| Fields | |
|---|---|
embedding_column |
Optional. Column of embedding. This column contains the source data to create index for vector search. embedding_column must be set when using vector search. |
filter_columns[] |
Optional. Columns of features that're used to filter vector search results. |
crowding_column |
Optional. Column of crowding. This column contains crowding attribute which is a constraint on a neighbor list produced by |
distance_measure_type |
Optional. The distance measure used in nearest neighbor search. |
Union field algorithm_config. The configuration with regard to the algorithms used for efficient search. algorithm_config can be only one of the following: |
|
tree_ah_config |
Optional. Configuration options for the tree-AH algorithm (Shallow tree + Asymmetric Hashing). Please refer to this paper for more details: https://arxiv.org/abs/1908.10396 |
brute_force_config |
Optional. Configuration options for using brute force search, which simply implements the standard linear search in the database for each query. It is primarily meant for benchmarking and to generate the ground truth for approximate search. |
embedding_dimension |
Optional. The number of dimensions of the input embedding. |
BruteForceConfig
This type has no fields.
Configuration options for using brute force search.
DistanceMeasureType
The distance measure used in nearest neighbor search.
| Enums | |
|---|---|
DISTANCE_MEASURE_TYPE_UNSPECIFIED |
Should not be set. |
SQUARED_L2_DISTANCE |
Euclidean (L_2) Distance. |
COSINE_DISTANCE |
Cosine Distance. Defined as 1 - cosine similarity. We strongly suggest using DOT_PRODUCT_DISTANCE + UNIT_L2_NORM instead of COSINE distance. Our algorithms have been more optimized for DOT_PRODUCT distance which, when combined with UNIT_L2_NORM, is mathematically equivalent to COSINE distance and results in the same ranking. |
DOT_PRODUCT_DISTANCE |
Dot Product Distance. Defined as a negative of the dot product. |
TreeAHConfig
Configuration options for the tree-AH algorithm.
| Fields | |
|---|---|
leaf_node_embedding_count |
Optional. Number of embeddings on each leaf node. The default value is 1000 if not set. |
OptimizedConfig
Configuration for FeatureViews created in Optimized FeatureOnlineStore.
| Fields | |
|---|---|
automatic_resources |
Optional. A description of resources that the FeatureView uses, which to large degree are decided by Vertex AI, and optionally allows only a modest additional configuration. If min_replica_count is not set, the default value is 2. If max_replica_count is not set, the default value is 6. The max allowed replica count is 1000. |
ServiceAgentType
Service agent type used during data sync.
| Enums | |
|---|---|
SERVICE_AGENT_TYPE_UNSPECIFIED |
By default, the project-level Vertex AI Service Agent is enabled. |
SERVICE_AGENT_TYPE_PROJECT |
Indicates the project-level Vertex AI Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) will be used during sync jobs. |
SERVICE_AGENT_TYPE_FEATURE_VIEW |
Enable a FeatureView service account to be created by Vertex AI and output in the field service_account_email. This service account will be used to read from the source BigQuery table during sync. |
SyncConfig
Configuration for Sync. Only one option is set.
| Fields | |
|---|---|
cron |
Cron schedule (https://en.wikipedia.org/wiki/Cron) to launch scheduled runs. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: "CRON_TZ=${IANA_TIME_ZONE}" or "TZ=${IANA_TIME_ZONE}". The ${IANA_TIME_ZONE} may only be a valid string from IANA time zone database. For example, "CRON_TZ=America/New_York 1 * * * *", or "TZ=America/New_York 1 * * * *". |
continuous |
Optional. If true, syncs the FeatureView in a continuous manner to Online Store. |
VectorSearchConfig
Deprecated. Use IndexConfig instead.
| Fields | |
|---|---|
embedding_column |
Optional. Column of embedding. This column contains the source data to create index for vector search. embedding_column must be set when using vector search. |
filter_columns[] |
Optional. Columns of features that're used to filter vector search results. |
crowding_column |
Optional. Column of crowding. This column contains crowding attribute which is a constraint on a neighbor list produced by |
distance_measure_type |
Optional. The distance measure used in nearest neighbor search. |
Union field algorithm_config. The configuration with regard to the algorithms used for efficient search. algorithm_config can be only one of the following: |
|
tree_ah_config |
Optional. Configuration options for the tree-AH algorithm (Shallow tree + Asymmetric Hashing). Please refer to this paper for more details: https://arxiv.org/abs/1908.10396 |
brute_force_config |
Optional. Configuration options for using brute force search, which simply implements the standard linear search in the database for each query. It is primarily meant for benchmarking and to generate the ground truth for approximate search. |
embedding_dimension |
Optional. The number of dimensions of the input embedding. |
BruteForceConfig
This type has no fields.
DistanceMeasureType
| Enums | |
|---|---|
DISTANCE_MEASURE_TYPE_UNSPECIFIED |
Should not be set. |
SQUARED_L2_DISTANCE |
Euclidean (L_2) Distance. |
COSINE_DISTANCE |
Cosine Distance. Defined as 1 - cosine similarity. We strongly suggest using DOT_PRODUCT_DISTANCE + UNIT_L2_NORM instead of COSINE distance. Our algorithms have been more optimized for DOT_PRODUCT distance which, when combined with UNIT_L2_NORM, is mathematically equivalent to COSINE distance and results in the same ranking. |
DOT_PRODUCT_DISTANCE |
Dot Product Distance. Defined as a negative of the dot product. |
TreeAHConfig
| Fields | |
|---|---|
leaf_node_embedding_count |
Optional. Number of embeddings on each leaf node. The default value is 1000 if not set. |
VertexRagSource
A Vertex Rag source for features that need to be synced to Online Store.
| Fields | |
|---|---|
uri |
Required. The BigQuery view/table URI that will be materialized on each manual sync trigger. The table/view is expected to have the following columns and types at least: - |
rag_corpus_id |
Optional. The RAG corpus id corresponding to this FeatureView. |
FeatureViewDataFormat
Format of the data in the Feature View.
| Enums | |
|---|---|
FEATURE_VIEW_DATA_FORMAT_UNSPECIFIED |
Not set. Will be treated as the KeyValue format. |
KEY_VALUE |
Return response data in key-value format. |
PROTO_STRUCT |
Return response data in proto Struct format. |
FeatureViewDataKey
Lookup key for a feature view.
| Fields | |
|---|---|
Union field
|
|
key |
String key to use for lookup. |
composite_key |
The actual Entity ID will be composed from this struct. This should match with the way ID is defined in the FeatureView spec. |
CompositeKey
ID that is comprised from several parts (columns).
| Fields | |
|---|---|
parts[] |
Parts to construct Entity ID. Should match with the same ID columns as defined in FeatureView in the same order. |
FeatureViewSync
FeatureViewSync is a representation of sync operation which copies data from data source to Feature View in Online Store.
| Fields | |
|---|---|
name |
Identifier. Name of the FeatureViewSync. Format: |
create_time |
Output only. Time when this FeatureViewSync is created. Creation of a FeatureViewSync means that the job is pending / waiting for sufficient resources but may not have started the actual data transfer yet. |
run_time |
Output only. Time when this FeatureViewSync is finished. |
final_status |
Output only. Final status of the FeatureViewSync. |
sync_summary |
Output only. Summary of the sync job. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
SyncSummary
Summary from the Sync job. For continuous syncs, the summary is updated periodically. For batch syncs, it gets updated on completion of the sync.
| Fields | |
|---|---|
row_synced |
Output only. Total number of rows synced. |
total_slot |
Output only. BigQuery slot milliseconds consumed for the sync job. |
system_watermark_time |
Lower bound of the system time watermark for the sync job. This is only set for continuously syncing feature views. |
Featurestore
Vertex AI Feature Store provides a centralized repository for organizing, storing, and serving ML features. The Featurestore is a top-level container for your features and their values.
| Fields | |
|---|---|
name |
Output only. Name of the Featurestore. Format: |
create_time |
Output only. Timestamp when this Featurestore was created. |
update_time |
Output only. Timestamp when this Featurestore was last updated. |
etag |
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
Optional. The labels with user-defined metadata to organize your Featurestore. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one Featurestore(System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
online_serving_config |
Optional. Config for online storage resources. The field should not co-exist with the field of |
state |
Output only. State of the featurestore. |
online_storage_ttl_days |
Optional. TTL in days for feature values that will be stored in online serving storage. The Feature Store online storage periodically removes obsolete feature values older than |
encryption_spec |
Optional. Customer-managed encryption key spec for data storage. If set, both of the online and offline data storage will be secured by this key. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
OnlineServingConfig
OnlineServingConfig specifies the details for provisioning online serving resources.
| Fields | |
|---|---|
fixed_node_count |
The number of nodes for the online store. The number of nodes doesn't scale automatically, but you can manually update the number of nodes. If set to 0, the featurestore will not have an online store and cannot be used for online serving. |
scaling |
Online serving scaling configuration. Only one of |
Scaling
Online serving scaling configuration. If min_node_count and max_node_count are set to the same value, the cluster will be configured with the fixed number of node (no auto-scaling).
| Fields | |
|---|---|
min_node_count |
Required. The minimum number of nodes to scale down to. Must be greater than or equal to 1. |
max_node_count |
The maximum number of nodes to scale up to. Must be greater than min_node_count, and less than or equal to 10 times of 'min_node_count'. |
cpu_utilization_target |
Optional. The cpu utilization that the Autoscaler should be trying to achieve. This number is on a scale from 0 (no utilization) to 100 (total utilization), and is limited between 10 and 80. When a cluster's CPU utilization exceeds the target that you have set, Bigtable immediately adds nodes to the cluster. When CPU utilization is substantially lower than the target, Bigtable removes nodes. If not set or set to 0, default to 50. |
State
Possible states a featurestore can have.
| Enums | |
|---|---|
STATE_UNSPECIFIED |
Default value. This value is unused. |
STABLE |
State when the featurestore configuration is not being updated and the fields reflect the current configuration of the featurestore. The featurestore is usable in this state. |
UPDATING |
The state of the featurestore configuration when it is being updated. During an update, the fields reflect either the original configuration or the updated configuration of the featurestore. For example, online_serving_config.fixed_node_count can take minutes to update. While the update is in progress, the featurestore is in the UPDATING state, and the value of fixed_node_count can be the original value or the updated value, depending on the progress of the operation. Until the update completes, the actual number of nodes can still be the original value of fixed_node_count. The featurestore is still usable in this state. |
FeaturestoreMonitoringConfig
Configuration of how features in Featurestore are monitored.
| Fields | |
|---|---|
snapshot_analysis |
The config for Snapshot Analysis Based Feature Monitoring. |
import_features_analysis |
The config for ImportFeatures Analysis Based Feature Monitoring. |
numerical_threshold_config |
Threshold for numerical features of anomaly detection. This is shared by all objectives of Featurestore Monitoring for numerical features (i.e. Features with type ( |
categorical_threshold_config |
Threshold for categorical features of anomaly detection. This is shared by all types of Featurestore Monitoring for categorical features (i.e. Features with type ( |
ImportFeaturesAnalysis
Configuration of the Featurestore's ImportFeature Analysis Based Monitoring. This type of analysis generates statistics for values of each Feature imported by every ImportFeatureValues operation.
| Fields | |
|---|---|
state |
Whether to enable / disable / inherite default hebavior for import features analysis. |
anomaly_detection_baseline |
The baseline used to do anomaly detection for the statistics generated by import features analysis. |
Baseline
Defines the baseline to do anomaly detection for feature values imported by each ImportFeatureValues operation.
| Enums | |
|---|---|
BASELINE_UNSPECIFIED |
Should not be used. |
LATEST_STATS |
Choose the later one statistics generated by either most recent snapshot analysis or previous import features analysis. If non of them exists, skip anomaly detection and only generate a statistics. |
MOST_RECENT_SNAPSHOT_STATS |
Use the statistics generated by the most recent snapshot analysis if exists. |
PREVIOUS_IMPORT_FEATURES_STATS |
Use the statistics generated by the previous import features analysis if exists. |
State
The state defines whether to enable ImportFeature analysis.
| Enums | |
|---|---|
STATE_UNSPECIFIED |
Should not be used. |
DEFAULT |
The default behavior of whether to enable the monitoring. EntityType-level config: disabled. Feature-level config: inherited from the configuration of EntityType this Feature belongs to. |
ENABLED |
Explicitly enables import features analysis. EntityType-level config: by default enables import features analysis for all Features under it. Feature-level config: enables import features analysis regardless of the EntityType-level config. |
DISABLED |
Explicitly disables import features analysis. EntityType-level config: by default disables import features analysis for all Features under it. Feature-level config: disables import features analysis regardless of the EntityType-level config. |
SnapshotAnalysis
Configuration of the Featurestore's Snapshot Analysis Based Monitoring. This type of analysis generates statistics for each Feature based on a snapshot of the latest feature value of each entities every monitoring_interval.
| Fields | |
|---|---|
disabled |
The monitoring schedule for snapshot analysis. For EntityType-level config: unset / disabled = true indicates disabled by default for Features under it; otherwise by default enable snapshot analysis monitoring with monitoring_interval for Features under it. Feature-level config: disabled = true indicates disabled regardless of the EntityType-level config; unset monitoring_interval indicates going with EntityType-level config; otherwise run snapshot analysis monitoring with monitoring_interval regardless of the EntityType-level config. Explicitly Disable the snapshot analysis based monitoring. |
monitoring_interval |
Configuration of the snapshot analysis based monitoring pipeline running interval. The value is rolled up to full day. If both |
monitoring_interval_days |
Configuration of the snapshot analysis based monitoring pipeline running interval. The value indicates number of days. |
staleness_days |
Customized export features time window for snapshot analysis. Unit is one day. Default value is 3 weeks. Minimum value is 1 day. Maximum value is 4000 days. |
ThresholdConfig
The config for Featurestore Monitoring threshold.
| Fields | |
|---|---|
Union field
|
|
value |
Specify a threshold value that can trigger the alert. 1. For categorical feature, the distribution distance is calculated by L-inifinity norm. 2. For numerical feature, the distribution distance is calculated by Jensen–Shannon divergence. Each feature must have a non-zero threshold if they need to be monitored. Otherwise no alert will be triggered for that feature. |
FetchFeatureValuesRequest
Request message for FeatureOnlineStoreService.FetchFeatureValues. All the features under the requested feature view will be returned.
| Fields | |
|---|---|
feature_view |
Required. FeatureView resource format |
data_key |
Optional. The request key to fetch feature values for. |
data_format |
Optional. Response data format. If not set, |
format |
Specify response data format. If not set, KeyValue format will be used. Deprecated. Use |
Union field entity_id. Entity ID to fetch feature values for. Deprecated. Use FetchFeatureValuesRequest.data_key. entity_id can be only one of the following: |
|
id |
Simple ID. The whole string will be used as is to identify Entity to fetch feature values for. |
Format
Format of the response data.
| Enums | |
|---|---|
FORMAT_UNSPECIFIED |
Not set. Will be treated as the KeyValue format. |
KEY_VALUE |
Return response data in key-value format. |
PROTO_STRUCT |
Return response data in proto Struct format. |
FetchFeatureValuesResponse
Response message for FeatureOnlineStoreService.FetchFeatureValues
| Fields | |
|---|---|
data_key |
The data key associated with this response. Will only be populated for |
Union field
|
|
key_values |
Feature values in KeyValue format. |
proto_struct |
Feature values in proto Struct format. |
FeatureNameValuePairList
Response structure in the format of key (feature name) and (feature) value pair.
| Fields | |
|---|---|
features[] |
List of feature names and values. |
FeatureNameValuePair
Feature name & value pair.
| Fields | |
|---|---|
name |
Feature short name. |
Union field
|
|
value |
Feature value. |
FileData
URI based data.
| Fields | |
|---|---|
mime_type |
Required. The IANA standard MIME type of the source data. |
file_uri |
Required. URI. |
FileStatus
RagFile status.
| Fields | |
|---|---|
state |
Output only. RagFile state. |
error_status |
Output only. Only when the |
State
RagFile state.
| Enums | |
|---|---|
STATE_UNSPECIFIED |
RagFile state is unspecified. |
ACTIVE |
RagFile resource has been created and indexed successfully. |
ERROR |
RagFile resource is in a problematic state. See error_message field for details. |
FilterSplit
Assigns input data to training, validation, and test sets based on the given filters, data pieces not matched by any filter are ignored. Currently only supported for Datasets containing DataItems. If any of the filters in this message are to match nothing, then they can be set as '-' (the minus sign).
Supported only for unstructured Datasets.
| Fields | |
|---|---|
training_filter |
Required. A filter on DataItems of the Dataset. DataItems that match this filter are used to train the Model. A filter with same syntax as the one used in |
validation_filter |
Required. A filter on DataItems of the Dataset. DataItems that match this filter are used to validate the Model. A filter with same syntax as the one used in |
test_filter |
Required. A filter on DataItems of the Dataset. DataItems that match this filter are used to test the Model. A filter with same syntax as the one used in |
FluencyInput
Input for fluency metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for fluency score metric. |
instance |
Required. Fluency instance. |
FluencyInstance
Spec for fluency instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
FluencyResult
Spec for fluency result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for fluency score. |
score |
Output only. Fluency score. |
confidence |
Output only. Confidence for fluency score. |
FluencySpec
Spec for fluency score metric.
| Fields | |
|---|---|
version |
Optional. Which version to use for evaluation. |
FractionSplit
Assigns the input data to training, validation, and test sets as per the given fractions. Any of training_fraction, validation_fraction and test_fraction may optionally be provided, they must sum to up to 1. If the provided ones sum to less than 1, the remainder is assigned to sets as decided by Vertex AI. If none of the fractions are set, by default roughly 80% of data is used for training, 10% for validation, and 10% for test.
| Fields | |
|---|---|
training_fraction |
The fraction of the input data that is to be used to train the Model. |
validation_fraction |
The fraction of the input data that is to be used to validate the Model. |
test_fraction |
The fraction of the input data that is to be used to evaluate the Model. |
FulfillmentInput
Input for fulfillment metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for fulfillment score metric. |
instance |
Required. Fulfillment instance. |
FulfillmentInstance
Spec for fulfillment instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
instruction |
Required. Inference instruction prompt to compare prediction with. |
FulfillmentResult
Spec for fulfillment result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for fulfillment score. |
score |
Output only. Fulfillment score. |
confidence |
Output only. Confidence for fulfillment score. |
FulfillmentSpec
Spec for fulfillment metric.
| Fields | |
|---|---|
version |
Optional. Which version to use for evaluation. |
FunctionCall
A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values.
| Fields | |
|---|---|
name |
Required. The name of the function to call. Matches [FunctionDeclaration.name]. |
args |
Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. |
FunctionCallingConfig
Function calling config.
| Fields | |
|---|---|
mode |
Optional. Function calling mode. |
allowed_function_names[] |
Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. |
Mode
Function calling mode.
| Enums | |
|---|---|
MODE_UNSPECIFIED |
Unspecified function calling mode. This value should not be used. |
AUTO |
Default model behavior, model decides to predict either function calls or natural language response. |
ANY |
Model is constrained to always predicting function calls only. If "allowed_function_names" are set, the predicted function calls will be limited to any one of "allowed_function_names", else the predicted function calls will be any one of the provided "function_declarations". |
NONE |
Model will not predict any function calls. Model behavior is same as when not passing any function declarations. |
FunctionDeclaration
Structured representation of a function declaration as defined by the OpenAPI 3.0 specification. Included in this declaration are the function name, description, parameters and response type. This FunctionDeclaration is a representation of a block of code that can be used as a Tool by the model and executed by the client.
| Fields | |
|---|---|
name |
Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. |
description |
Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. |
parameters |
Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 |
response |
Optional. Describes the output from this function in JSON Schema format. Reflects the Open API 3.03 Response Object. The Schema defines the type used for the response value of the function. |
FunctionResponse
The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction.
| Fields | |
|---|---|
name |
Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. |
response |
Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output. |
GcsDestination
The Google Cloud Storage location where the output is to be written to.
| Fields | |
|---|---|
output_uri_prefix |
Required. Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist. |
GcsSource
The Google Cloud Storage location for the input content.
| Fields | |
|---|---|
uris[] |
Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames. |
GenerateContentRequest
Request message for [PredictionService.GenerateContent].
| Fields | |
|---|---|
model |
Required. The fully qualified name of the publisher model or tuned model endpoint to use. Publisher model format: Tuned model endpoint format: |
contents[] |
Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request. |
cached_content |
Optional. The name of the cached content used as context to serve the prediction. Note: only used in explicit caching, where users can have control over caching (e.g. what content to cache) and enjoy guaranteed cost savings. Format: |
tools[] |
Optional. A list of A |
tool_config |
Optional. Tool config. This config is shared for all tools provided in the request. |
labels |
Optional. The labels with user-defined metadata for the request. It is used for billing and reporting only. Label keys and values can be no longer than 63 characters (Unicode codepoints) and can only contain lowercase letters, numeric characters, underscores, and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter. |
safety_settings[] |
Optional. Per request settings for blocking unsafe content. Enforced on GenerateContentResponse.candidates. |
generation_config |
Optional. Generation config. |
system_instruction |
Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. |
GenerateContentResponse
Response message for [PredictionService.GenerateContent].
| Fields | |
|---|---|
candidates[] |
Output only. Generated candidates. |
model_version |
Output only. The model version used to generate the response. |
create_time |
Output only. Timestamp when the request is made to the server. |
response_id |
Output only. response_id is used to identify each response. It is the encoding of the event_id. |
prompt_feedback |
Output only. Content filter results for a prompt sent in the request. Note: Sent only in the first stream chunk. Only happens when no candidates were generated due to content violations. |
usage_metadata |
Usage metadata about the response(s). |
PromptFeedback
Content filter results for a prompt sent in the request.
| Fields | |
|---|---|
block_reason |
Output only. Blocked reason. |
safety_ratings[] |
Output only. Safety ratings. |
block_reason_message |
Output only. A readable block reason message. |
BlockedReason
Blocked reason enumeration.
| Enums | |
|---|---|
BLOCKED_REASON_UNSPECIFIED |
Unspecified blocked reason. |
SAFETY |
Candidates blocked due to safety. |
OTHER |
Candidates blocked due to other reason. |
BLOCKLIST |
Candidates blocked due to the terms which are included from the terminology blocklist. |
PROHIBITED_CONTENT |
Candidates blocked due to prohibited content. |
UsageMetadata
Usage metadata about response(s).
| Fields | |
|---|---|
prompt_token_count |
Number of tokens in the request. When |
candidates_token_count |
Number of tokens in the response(s). |
total_token_count |
Total token count for prompt, response candidates, and tool-use prompts (if present). |
cached_content_token_count |
Output only. Number of tokens in the cached part in the input (the cached content). |
prompt_tokens_details[] |
Output only. List of modalities that were processed in the request input. |
cache_tokens_details[] |
Output only. List of modalities of the cached content in the request input. |
candidates_tokens_details[] |
Output only. List of modalities that were returned in the response. |
GenerateVideoResponse
Generate video response.
| Fields | |
|---|---|
generated_samples[] |
The cloud storage uris of the generated videos. |
rai_media_filtered_reasons[] |
Returns rai failure reasons if any. |
rai_media_filtered_count |
Returns if any videos were filtered due to RAI policies. |
GenerationConfig
Generation config.
| Fields | |
|---|---|
stop_sequences[] |
Optional. Stop sequences. |
response_mime_type |
Optional. Output response mimetype of the generated candidate text. Supported mimetype: - |
response_modalities[] |
Optional. The modalities of the response. |
temperature |
Optional. Controls the randomness of predictions. |
top_p |
Optional. If specified, nucleus sampling will be used. |
top_k |
Optional. If specified, top-k sampling will be used. |
candidate_count |
Optional. Number of candidates to generate. |
max_output_tokens |
Optional. The maximum number of output tokens to generate per message. |
response_logprobs |
Optional. If true, export the logprobs results in response. |
logprobs |
Optional. Logit probabilities. |
presence_penalty |
Optional. Positive penalties. |
frequency_penalty |
Optional. Frequency penalties. |
seed |
Optional. Seed. |
response_schema |
Optional. The |
routing_config |
Optional. Routing configuration. |
audio_timestamp |
Optional. If enabled, audio timestamp will be included in the request to the model. |
media_resolution |
Optional. If specified, the media resolution specified will be used. |
speech_config |
Optional. The speech generation config. |
MediaResolution
Media resolution for the input media.
| Enums | |
|---|---|
MEDIA_RESOLUTION_UNSPECIFIED |
Media resolution has not been set. |
MEDIA_RESOLUTION_LOW |
Media resolution set to low (64 tokens). |
MEDIA_RESOLUTION_MEDIUM |
Media resolution set to medium (256 tokens). |
MEDIA_RESOLUTION_HIGH |
Media resolution set to high (zoomed reframing with 256 tokens). |
Modality
The modalities of the response.
| Enums | |
|---|---|
MODALITY_UNSPECIFIED |
Unspecified modality. Will be processed as text. |
TEXT |
Text modality. |
IMAGE |
Image modality. |
AUDIO |
Audio modality. |
RoutingConfig
The configuration for routing the request to a specific model.
| Fields | |
|---|---|
Union field routing_config. Routing mode. routing_config can be only one of the following: |
|
auto_mode |
Automated routing. |
manual_mode |
Manual routing. |
AutoRoutingMode
When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference.
| Fields | |
|---|---|
model_routing_preference |
The model routing preference. |
ModelRoutingPreference
The model routing preference.
| Enums | |
|---|---|
UNKNOWN |
Unspecified model routing preference. |
PRIORITIZE_QUALITY |
Prefer higher quality over low cost. |
BALANCED |
Balanced model routing preference. |
PRIORITIZE_COST |
Prefer lower cost over higher quality. |
ManualRoutingMode
When manual routing is set, the specified model will be used directly.
| Fields | |
|---|---|
model_name |
The model name to use. Only the public LLM models are accepted. e.g. 'gemini-1.5-pro-001'. |
GenericOperationMetadata
Generic Metadata shared by all operations.
| Fields | |
|---|---|
partial_failures[] |
Output only. Partial failures encountered. E.g. single files that couldn't be read. This field should never exceed 20 entries. Status details field will contain standard Google Cloud error details. |
create_time |
Output only. Time when the operation was created. |
update_time |
Output only. Time when the operation was updated for the last time. If the operation has finished (successfully or not), this is the finish time. |
GenieSource
Contains information about the source of the models generated from Generative AI Studio.
| Fields | |
|---|---|
base_model_uri |
Required. The public base model URI. |
GetAnnotationSpecRequest
Request message for DatasetService.GetAnnotationSpec.
| Fields | |
|---|---|
name |
Required. The name of the AnnotationSpec resource. Format: |
read_mask |
Mask specifying which fields to read. |
GetArtifactRequest
Request message for MetadataService.GetArtifact.
| Fields | |
|---|---|
name |
Required. The resource name of the Artifact to retrieve. Format: |
GetBatchPredictionJobRequest
Request message for JobService.GetBatchPredictionJob.
| Fields | |
|---|---|
name |
Required. The name of the BatchPredictionJob resource. Format: |
GetCachedContentRequest
Request message for GenAiCacheService.GetCachedContent.
| Fields | |
|---|---|
name |
Required. The resource name referring to the cached content |
GetContextRequest
Request message for MetadataService.GetContext.
| Fields | |
|---|---|
name |
Required. The resource name of the Context to retrieve. Format: |
GetCustomJobRequest
Request message for JobService.GetCustomJob.
| Fields | |
|---|---|
name |
Required. The name of the CustomJob resource. Format: |
GetDatasetRequest
Request message for DatasetService.GetDataset. Next ID: 4
| Fields | |
|---|---|
name |
Required. The name of the Dataset resource. |
read_mask |
Mask specifying which fields to read. |
GetDatasetVersionRequest
Request message for DatasetService.GetDatasetVersion. Next ID: 4
| Fields | |
|---|---|
name |
Required. The resource name of the Dataset version to delete. Format: |
read_mask |
Mask specifying which fields to read. |
GetDeploymentResourcePoolRequest
Request message for GetDeploymentResourcePool method.
| Fields | |
|---|---|
name |
Required. The name of the DeploymentResourcePool to retrieve. Format: |
GetEndpointRequest
Request message for EndpointService.GetEndpoint
| Fields | |
|---|---|
name |
Required. The name of the Endpoint resource. Format: |
GetEntityTypeRequest
Request message for FeaturestoreService.GetEntityType.
| Fields | |
|---|---|
name |
Required. The name of the EntityType resource. Format: |
GetExecutionRequest
Request message for MetadataService.GetExecution.
| Fields | |
|---|---|
name |
Required. The resource name of the Execution to retrieve. Format: |
GetExtensionRequest
Request message for ExtensionRegistryService.GetExtension.
| Fields | |
|---|---|
name |
Required. The name of the Extension resource. Format: |
GetFeatureGroupRequest
Request message for FeatureRegistryService.GetFeatureGroup.
| Fields | |
|---|---|
name |
Required. The name of the FeatureGroup resource. |
GetFeatureMonitorJobRequest
Request message for FeatureRegistryService.GetFeatureMonitorJob.
| Fields | |
|---|---|
name |
Required. The name of the FeatureMonitorJob resource. Format: |
GetFeatureMonitorRequest
Request message for FeatureRegistryService.GetFeatureMonitor.
| Fields | |
|---|---|
name |
Required. The name of the FeatureMonitor resource. |
GetFeatureOnlineStoreRequest
Request message for FeatureOnlineStoreAdminService.GetFeatureOnlineStore.
| Fields | |
|---|---|
name |
Required. The name of the FeatureOnlineStore resource. |
GetFeatureRequest
Request message for FeaturestoreService.GetFeature. Request message for FeatureRegistryService.GetFeature.
| Fields | |
|---|---|
name |
Required. The name of the Feature resource. Format for entity_type as parent: |
feature_stats_and_anomaly_spec |
Optional. Only applicable for Vertex AI Feature Store. If set, retrieves FeatureStatsAndAnomaly generated by FeatureMonitors based on this spec. |
GetFeatureViewRequest
Request message for FeatureOnlineStoreAdminService.GetFeatureView.
| Fields | |
|---|---|
name |
Required. The name of the FeatureView resource. Format: |
GetFeatureViewSyncRequest
Request message for FeatureOnlineStoreAdminService.GetFeatureViewSync.
| Fields | |
|---|---|
name |
Required. The name of the FeatureViewSync resource. Format: |
GetFeaturestoreRequest
Request message for FeaturestoreService.GetFeaturestore.
| Fields | |
|---|---|
name |
Required. The name of the Featurestore resource. |
GetHyperparameterTuningJobRequest
Request message for JobService.GetHyperparameterTuningJob.
| Fields | |
|---|---|
name |
Required. The name of the HyperparameterTuningJob resource. Format: |
GetIndexEndpointRequest
Request message for IndexEndpointService.GetIndexEndpoint
| Fields | |
|---|---|
name |
Required. The name of the IndexEndpoint resource. Format: |
GetIndexRequest
Request message for IndexService.GetIndex
| Fields | |
|---|---|
name |
Required. The name of the Index resource. Format: |
GetMetadataSchemaRequest
Request message for MetadataService.GetMetadataSchema.
| Fields | |
|---|---|
name |
Required. The resource name of the MetadataSchema to retrieve. Format: |
GetMetadataStoreRequest
Request message for MetadataService.GetMetadataStore.
| Fields | |
|---|---|
name |
Required. The resource name of the MetadataStore to retrieve. Format: |
GetModelDeploymentMonitoringJobRequest
Request message for JobService.GetModelDeploymentMonitoringJob.
| Fields | |
|---|---|
name |
Required. The resource name of the ModelDeploymentMonitoringJob. Format: |
GetModelEvaluationRequest
Request message for ModelService.GetModelEvaluation.
| Fields | |
|---|---|
name |
Required. The name of the ModelEvaluation resource. Format: |
GetModelEvaluationSliceRequest
Request message for ModelService.GetModelEvaluationSlice.
| Fields | |
|---|---|
name |
Required. The name of the ModelEvaluationSlice resource. Format: |
GetModelMonitorRequest
Request message for ModelMonitoringService.GetModelMonitor.
| Fields | |
|---|---|
name |
Required. The name of the ModelMonitor resource. Format: |
GetModelMonitoringJobRequest
Request message for ModelMonitoringService.GetModelMonitoringJob.
| Fields | |
|---|---|
name |
Required. The resource name of the ModelMonitoringJob. Format: |
GetModelRequest
Request message for ModelService.GetModel.
| Fields | |
|---|---|
name |
Required. The name of the Model resource. Format: In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: |
GetNotebookExecutionJobRequest
Request message for [NotebookService.GetNotebookExecutionJob]
| Fields | |
|---|---|
name |
Required. The name of the NotebookExecutionJob resource. |
view |
Optional. The NotebookExecutionJob view. Defaults to BASIC. |
GetNotebookRuntimeRequest
Request message for NotebookService.GetNotebookRuntime
| Fields | |
|---|---|
name |
Required. The name of the NotebookRuntime resource. Instead of checking whether the name is in valid NotebookRuntime resource name format, directly throw NotFound exception if there is no such NotebookRuntime in spanner. |
GetNotebookRuntimeTemplateRequest
Request message for NotebookService.GetNotebookRuntimeTemplate
| Fields | |
|---|---|
name |
Required. The name of the NotebookRuntimeTemplate resource. Format: |
GetPersistentResourceRequest
Request message for PersistentResourceService.GetPersistentResource.
| Fields | |
|---|---|
name |
Required. The name of the PersistentResource resource. Format: |
GetPipelineJobRequest
Request message for PipelineService.GetPipelineJob.
| Fields | |
|---|---|
name |
Required. The name of the PipelineJob resource. Format: |
GetPublisherModelRequest
Request message for ModelGardenService.GetPublisherModel
| Fields | |
|---|---|
name |
Required. The name of the PublisherModel resource. Format: |
language_code |
Optional. The IETF BCP-47 language code representing the language in which the publisher model's text information should be written in. |
view |
Optional. PublisherModel view specifying which fields to read. |
is_hugging_face_model |
Optional. Boolean indicates whether the requested model is a Hugging Face model. |
hugging_face_token |
Optional. Token used to access Hugging Face gated models. |
GetRagCorpusRequest
Request message for VertexRagDataService.GetRagCorpus
| Fields | |
|---|---|
name |
Required. The name of the RagCorpus resource. Format: |
GetRagFileRequest
Request message for VertexRagDataService.GetRagFile
| Fields | |
|---|---|
name |
Required. The name of the RagFile resource. Format: |
GetReasoningEngineRequest
Request message for ReasoningEngineService.GetReasoningEngine.
| Fields | |
|---|---|
name |
Required. The name of the ReasoningEngine resource. Format: |
GetScheduleRequest
Request message for ScheduleService.GetSchedule.
| Fields | |
|---|---|
name |
Required. The name of the Schedule resource. Format: |
GetSpecialistPoolRequest
Request message for SpecialistPoolService.GetSpecialistPool.
| Fields | |
|---|---|
name |
Required. The name of the SpecialistPool resource. The form is |
GetStudyRequest
Request message for VizierService.GetStudy.
| Fields | |
|---|---|
name |
Required. The name of the Study resource. Format: |
GetTensorboardExperimentRequest
Request message for TensorboardService.GetTensorboardExperiment.
| Fields | |
|---|---|
name |
Required. The name of the TensorboardExperiment resource. Format: |
GetTensorboardRequest
Request message for TensorboardService.GetTensorboard.
| Fields | |
|---|---|
name |
Required. The name of the Tensorboard resource. Format: |
GetTensorboardRunRequest
Request message for TensorboardService.GetTensorboardRun.
| Fields | |
|---|---|
name |
Required. The name of the TensorboardRun resource. Format: |
GetTensorboardTimeSeriesRequest
Request message for TensorboardService.GetTensorboardTimeSeries.
| Fields | |
|---|---|
name |
Required. The name of the TensorboardTimeSeries resource. Format: |
GetTrainingPipelineRequest
Request message for PipelineService.GetTrainingPipeline.
| Fields | |
|---|---|
name |
Required. The name of the TrainingPipeline resource. Format: |
GetTrialRequest
Request message for VizierService.GetTrial.
| Fields | |
|---|---|
name |
Required. The name of the Trial resource. Format: |
GetTuningJobRequest
Request message for GenAiTuningService.GetTuningJob.
| Fields | |
|---|---|
name |
Required. The name of the TuningJob resource. Format: |
GoogleDriveSource
The Google Drive location for the input content.
| Fields | |
|---|---|
resource_ids[] |
Required. Google Drive resource IDs. |
ResourceId
The type and ID of the Google Drive resource.
| Fields | |
|---|---|
resource_type |
Required. The type of the Google Drive resource. |
resource_id |
Required. The ID of the Google Drive resource. |
ResourceType
The type of the Google Drive resource.
| Enums | |
|---|---|
RESOURCE_TYPE_UNSPECIFIED |
Unspecified resource type. |
RESOURCE_TYPE_FILE |
File resource type. |
RESOURCE_TYPE_FOLDER |
Folder resource type. |
GoogleSearchRetrieval
Tool to retrieve public web data for grounding, powered by Google.
| Fields | |
|---|---|
dynamic_retrieval_config |
Specifies the dynamic retrieval configuration for the given source. |
GroundednessInput
Input for groundedness metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for groundedness metric. |
instance |
Required. Groundedness instance. |
GroundednessInstance
Spec for groundedness instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
context |
Required. Background information provided in context used to compare against the prediction. |
GroundednessResult
Spec for groundedness result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for groundedness score. |
score |
Output only. Groundedness score. |
confidence |
Output only. Confidence for groundedness score. |
GroundednessSpec
Spec for groundedness metric.
| Fields | |
|---|---|
version |
Optional. Which version to use for evaluation. |
GroundingChunk
Grounding chunk.
| Fields | |
|---|---|
Union field chunk_type. Chunk type. chunk_type can be only one of the following: |
|
web |
Grounding chunk from the web. |
retrieved_context |
Grounding chunk from context retrieved by the retrieval tools. |
RetrievedContext
Chunk from context retrieved by the retrieval tools.
| Fields | |
|---|---|
uri |
URI reference of the attribution. |
title |
Title of the attribution. |
text |
Text of the attribution. |
Web
Chunk from the web.
| Fields | |
|---|---|
uri |
URI reference of the chunk. |
title |
Title of the chunk. |
GroundingMetadata
Metadata returned to client when grounding is enabled.
| Fields | |
|---|---|
web_search_queries[] |
Optional. Web search queries for the following-up web search. |
retrieval_queries[] |
Optional. Queries executed by the retrieval tools. |
grounding_chunks[] |
List of supporting references retrieved from specified grounding source. |
grounding_supports[] |
Optional. List of grounding support. |
search_entry_point |
Optional. Google search entry for the following-up web searches. |
retrieval_metadata |
Optional. Output only. Retrieval metadata. |
GroundingSupport
Grounding support.
| Fields | |
|---|---|
grounding_chunk_indices[] |
A list of indices (into 'grounding_chunk') specifying the citations associated with the claim. For instance [1,3,4] means that grounding_chunk[1], grounding_chunk[3], grounding_chunk[4] are the retrieved content attributed to the claim. |
confidence_scores[] |
Confidence score of the support references. Ranges from 0 to 1. 1 is the most confident. This list must have the same size as the grounding_chunk_indices. |
segment |
Segment of the content this support belongs to. |
HarmCategory
Harm categories that will block the content.
| Enums | |
|---|---|
HARM_CATEGORY_UNSPECIFIED |
The harm category is unspecified. |
HARM_CATEGORY_HATE_SPEECH |
The harm category is hate speech. |
HARM_CATEGORY_DANGEROUS_CONTENT |
The harm category is dangerous content. |
HARM_CATEGORY_HARASSMENT |
The harm category is harassment. |
HARM_CATEGORY_SEXUALLY_EXPLICIT |
The harm category is sexually explicit content. |
HARM_CATEGORY_CIVIC_INTEGRITY |
The harm category is civic integrity. |
HttpElementLocation
Enum of location an HTTP element can be.
| Enums | |
|---|---|
HTTP_IN_UNSPECIFIED |
|
HTTP_IN_QUERY |
Element is in the HTTP request query. |
HTTP_IN_HEADER |
Element is in the HTTP request header. |
HTTP_IN_PATH |
Element is in the HTTP request path. |
HTTP_IN_BODY |
Element is in the HTTP request body. |
HTTP_IN_COOKIE |
Element is in the HTTP request cookie. |
HyperparameterTuningJob
Represents a HyperparameterTuningJob. A HyperparameterTuningJob has a Study specification and multiple CustomJobs with identical CustomJob specification.
| Fields | |
|---|---|
name |
Output only. Resource name of the HyperparameterTuningJob. |
display_name |
Required. The display name of the HyperparameterTuningJob. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
study_spec |
Required. Study configuration of the HyperparameterTuningJob. |
max_trial_count |
Required. The desired total number of Trials. |
parallel_trial_count |
Required. The desired number of Trials to run in parallel. |
max_failed_trial_count |
The number of failed Trials that need to be seen before failing the HyperparameterTuningJob. If set to 0, Vertex AI decides how many Trials must fail before the whole job fails. |
trial_job_spec |
Required. The spec of a trial job. The same spec applies to the CustomJobs created in all the trials. |
trials[] |
Output only. Trials of the HyperparameterTuningJob. |
state |
Output only. The detailed state of the job. |
create_time |
Output only. Time when the HyperparameterTuningJob was created. |
start_time |
Output only. Time when the HyperparameterTuningJob for the first time entered the |
end_time |
Output only. Time when the HyperparameterTuningJob entered any of the following states: |
update_time |
Output only. Time when the HyperparameterTuningJob was most recently updated. |
error |
Output only. Only populated when job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED. |
labels |
The labels with user-defined metadata to organize HyperparameterTuningJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
encryption_spec |
Customer-managed encryption key options for a HyperparameterTuningJob. If this is set, then all resources created by the HyperparameterTuningJob will be encrypted with the provided encryption key. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
IdMatcher
Matcher for Features of an EntityType by Feature ID.
| Fields | |
|---|---|
ids[] |
Required. The following are accepted as
|
ImportDataConfig
Describes the location from where we import data into a Dataset, together with the labels that will be applied to the DataItems and the Annotations.
| Fields | |
|---|---|
data_item_labels |
Labels that will be applied to newly imported DataItems. If an identical DataItem as one being imported already exists in the Dataset, then these labels will be appended to these of the already existing one, and if labels with identical key is imported before, the old label value will be overwritten. If two DataItems are identical in the same import data operation, the labels will be combined and if key collision happens in this case, one of the values will be picked randomly. Two DataItems are considered identical if their content bytes are identical (e.g. image bytes or pdf bytes). These labels will be overridden by Annotation labels specified inside index file referenced by |
annotation_labels |
Labels that will be applied to newly imported Annotations. If two Annotations are identical, one of them will be deduped. Two Annotations are considered identical if their |
import_schema_uri |
Required. Points to a YAML file stored on Google Cloud Storage describing the import format. Validation will be done against the schema. The schema is defined as an OpenAPI 3.0.2 Schema Object. |
Union field source. The source of the input. source can be only one of the following: |
|
gcs_source |
The Google Cloud Storage location for the input content. |
ImportDataOperationMetadata
Runtime operation information for DatasetService.ImportData.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
ImportDataRequest
Request message for DatasetService.ImportData.
| Fields | |
|---|---|
name |
Required. The name of the Dataset resource. Format: |
import_configs[] |
Required. The desired input locations. The contents of all input locations will be imported in one batch. |
ImportDataResponse
This type has no fields.
Response message for DatasetService.ImportData.
ImportExtensionOperationMetadata
Details of ExtensionRegistryService.ImportExtension operation.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
ImportExtensionRequest
Request message for ExtensionRegistryService.ImportExtension.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to import the Extension in. Format: |
extension |
Required. The Extension to import. |
ImportFeatureValuesOperationMetadata
Details of operations that perform import Feature values.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Featurestore import Feature values. |
imported_entity_count |
Number of entities that have been imported by the operation. |
imported_feature_value_count |
Number of Feature values that have been imported by the operation. |
source_uris[] |
The source URI from where Feature values are imported. |
invalid_row_count |
The number of rows in input source that weren't imported due to either * Not having any featureValues. * Having a null entityId. * Having a null timestamp. * Not being parsable (applicable for CSV sources). |
timestamp_outside_retention_rows_count |
The number rows that weren't ingested due to having timestamps outside the retention boundary. |
blocking_operation_ids[] |
List of ImportFeatureValues operations running under a single EntityType that are blocking this operation. |
ImportFeatureValuesRequest
Request message for FeaturestoreService.ImportFeatureValues.
| Fields | |
|---|---|
entity_type |
Required. The resource name of the EntityType grouping the Features for which values are being imported. Format: |
entity_id_field |
Source column that holds entity IDs. If not provided, entity IDs are extracted from the column named entity_id. |
feature_specs[] |
Required. Specifications defining which Feature values to import from the entity. The request fails if no feature_specs are provided, and having multiple feature_specs for one Feature is not allowed. |
disable_online_serving |
If set, data will not be imported for online serving. This is typically used for backfilling, where Feature generation timestamps are not in the timestamp range needed for online serving. |
worker_count |
Specifies the number of workers that are used to write data to the Featurestore. Consider the online serving capacity that you require to achieve the desired import throughput without interfering with online serving. The value must be positive, and less than or equal to 100. If not set, defaults to using 1 worker. The low count ensures minimal impact on online serving performance. |
disable_ingestion_analysis |
If true, API doesn't start ingestion analysis pipeline. |
Union field source. Details about the source data, including the location of the storage and the format. source can be only one of the following: |
|
avro_source |
|
bigquery_source |
|
csv_source |
|
Union field feature_time_source. Source of Feature timestamp for all Feature values of each entity. Timestamps must be millisecond-aligned. feature_time_source can be only one of the following: |
|
feature_time_field |
Source column that holds the Feature timestamp for all Feature values in each entity. |
feature_time |
Single Feature timestamp for all entities being imported. The timestamp must not have higher than millisecond precision. |
FeatureSpec
Defines the Feature value(s) to import.
| Fields | |
|---|---|
id |
Required. ID of the Feature to import values of. This Feature must exist in the target EntityType, or the request will fail. |
source_field |
Source column to get the Feature values from. If not set, uses the column with the same name as the Feature ID. |
ImportFeatureValuesResponse
Response message for FeaturestoreService.ImportFeatureValues.
| Fields | |
|---|---|
imported_entity_count |
Number of entities that have been imported by the operation. |
imported_feature_value_count |
Number of Feature values that have been imported by the operation. |
invalid_row_count |
The number of rows in input source that weren't imported due to either * Not having any featureValues. * Having a null entityId. * Having a null timestamp. * Not being parsable (applicable for CSV sources). |
timestamp_outside_retention_rows_count |
The number rows that weren't ingested due to having feature timestamps outside the retention boundary. |
ImportModelEvaluationRequest
Request message for ModelService.ImportModelEvaluation
| Fields | |
|---|---|
parent |
Required. The name of the parent model resource. Format: |
model_evaluation |
Required. Model evaluation resource to be imported. |
ImportRagFilesConfig
Config for importing RagFiles.
| Fields | |
|---|---|
rag_file_chunking_config |
Specifies the size and overlap of chunks after importing RagFiles. |
rag_file_transformation_config |
Specifies the transformation config for RagFiles. |
rag_file_parsing_config |
Optional. Specifies the parsing config for RagFiles. RAG will use the default parser if this field is not set. |
max_embedding_requests_per_min |
Optional. The max number of queries per minute that this job is allowed to make to the embedding model specified on the corpus. This value is specific to this job and not shared across other import jobs. Consult the Quotas page on the project to set an appropriate value here. If unspecified, a default value of 1,000 QPM would be used. |
Union field import_source. The source of the import. import_source can be only one of the following: |
|
gcs_source |
Google Cloud Storage location. Supports importing individual files as well as entire Google Cloud Storage directories. Sample formats: - |
google_drive_source |
Google Drive location. Supports importing individual files as well as Google Drive folders. |
slack_source |
Slack channels with their corresponding access tokens. |
jira_source |
Jira queries with their corresponding authentication. |
share_point_sources |
SharePoint sources. |
Union field partial_failure_sink. Optional. If provided, all partial failures are written to the sink. Deprecated. Prefer to use the import_result_sink. partial_failure_sink can be only one of the following: |
|
partial_failure_gcs_sink |
The Cloud Storage path to write partial failures to. Deprecated. Prefer to use |
partial_failure_bigquery_sink |
The BigQuery destination to write partial failures to. It should be a bigquery table resource name (e.g. "bq://projectId.bqDatasetId.bqTableId"). The dataset must exist. If the table does not exist, it will be created with the expected schema. If the table exists, the schema will be validated and data will be added to this existing table. Deprecated. Prefer to use |
ImportRagFilesOperationMetadata
Runtime operation information for VertexRagDataService.ImportRagFiles.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
rag_corpus_id |
The resource ID of RagCorpus that this operation is executed on. |
import_rag_files_config |
Output only. The config that was passed in the ImportRagFilesRequest. |
progress_percentage |
The progress percentage of the operation. Value is in the range [0, 100]. This percentage is calculated as follows: progress_percentage = 100 * (successes + failures + skips) / total |
ImportRagFilesRequest
Request message for VertexRagDataService.ImportRagFiles.
| Fields | |
|---|---|
parent |
Required. The name of the RagCorpus resource into which to import files. Format: |
import_rag_files_config |
Required. The config for the RagFiles to be synced and imported into the RagCorpus. |
ImportRagFilesResponse
Response message for VertexRagDataService.ImportRagFiles.
| Fields | |
|---|---|
imported_rag_files_count |
The number of RagFiles that had been imported into the RagCorpus. |
failed_rag_files_count |
The number of RagFiles that had failed while importing into the RagCorpus. |
skipped_rag_files_count |
The number of RagFiles that was skipped while importing into the RagCorpus. |
Union field partial_failure_sink. The location into which the partial failures were written. partial_failure_sink can be only one of the following: |
|
partial_failures_gcs_path |
The Google Cloud Storage path into which the partial failures were written. |
partial_failures_bigquery_table |
The BigQuery table into which the partial failures were written. |
Index
A representation of a collection of database items organized in a way that allows for approximate nearest neighbor (a.k.a ANN) algorithms search.
| Fields | |
|---|---|
name |
Output only. The resource name of the Index. |
display_name |
Required. The display name of the Index. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
description |
The description of the Index. |
metadata_schema_uri |
Immutable. Points to a YAML file stored on Google Cloud Storage describing additional information about the Index, that is specific to it. Unset if the Index does not have any additional information. The schema is defined as an OpenAPI 3.0.2 Schema Object. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access. |
metadata |
An additional information about the Index; the schema of the metadata can be found in |
deployed_indexes[] |
Output only. The pointers to DeployedIndexes created from this Index. An Index can be only deleted if all its DeployedIndexes had been undeployed first. |
etag |
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
The labels with user-defined metadata to organize your Indexes. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
create_time |
Output only. Timestamp when this Index was created. |
update_time |
Output only. Timestamp when this Index was most recently updated. This also includes any update to the contents of the Index. Note that Operations working on this Index may have their |
index_stats |
Output only. Stats of the index resource. |
index_update_method |
Immutable. The update method to use with this Index. If not set, BATCH_UPDATE will be used by default. |
encryption_spec |
Immutable. Customer-managed encryption key spec for an Index. If set, this Index and all sub-resources of this Index will be secured by this key. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
IndexUpdateMethod
The update method of an Index.
| Enums | |
|---|---|
INDEX_UPDATE_METHOD_UNSPECIFIED |
Should not be used. |
BATCH_UPDATE |
BatchUpdate: user can call UpdateIndex with files on Cloud Storage of Datapoints to update. |
STREAM_UPDATE |
StreamUpdate: user can call UpsertDatapoints/DeleteDatapoints to update the Index and the updates will be applied in corresponding DeployedIndexes in nearly real-time. |
IndexDatapoint
A datapoint of Index.
| Fields | |
|---|---|
datapoint_id |
Required. Unique identifier of the datapoint. |
feature_vector[] |
Required. Feature embedding vector for dense index. An array of numbers with the length of [NearestNeighborSearchConfig.dimensions]. |
sparse_embedding |
Optional. Feature embedding vector for sparse index. |
restricts[] |
Optional. List of Restrict of the datapoint, used to perform "restricted searches" where boolean rule are used to filter the subset of the database eligible for matching. This uses categorical tokens. See: https://cloud.google.com/vertex-ai/docs/matching-engine/filtering |
numeric_restricts[] |
Optional. List of Restrict of the datapoint, used to perform "restricted searches" where boolean rule are used to filter the subset of the database eligible for matching. This uses numeric comparisons. |
crowding_tag |
Optional. CrowdingTag of the datapoint, the number of neighbors to return in each crowding can be configured during query. |
CrowdingTag
Crowding tag is a constraint on a neighbor list produced by nearest neighbor search requiring that no more than some value k' of the k neighbors returned have the same value of crowding_attribute.
| Fields | |
|---|---|
crowding_attribute |
The attribute value used for crowding. The maximum number of neighbors to return per crowding attribute value (per_crowding_attribute_num_neighbors) is configured per-query. This field is ignored if per_crowding_attribute_num_neighbors is larger than the total number of neighbors to return for a given query. |
NumericRestriction
This field allows restricts to be based on numeric comparisons rather than categorical tokens.
| Fields | |
|---|---|
namespace |
The namespace of this restriction. e.g.: cost. |
op |
This MUST be specified for queries and must NOT be specified for datapoints. |
Union field Value. The type of Value must be consistent for all datapoints with a given namespace name. This is verified at runtime. Value can be only one of the following: |
|
value_int |
Represents 64 bit integer. |
value_float |
Represents 32 bit float. |
value_double |
Represents 64 bit float. |
Operator
Which comparison operator to use. Should be specified for queries only; specifying this for a datapoint is an error.
Datapoints for which Operator is true relative to the query's Value field will be allowlisted.
| Enums | |
|---|---|
OPERATOR_UNSPECIFIED |
Default value of the enum. |
LESS |
Datapoints are eligible iff their value is < the query's. |
LESS_EQUAL |
Datapoints are eligible iff their value is <= the query's. |
EQUAL |
Datapoints are eligible iff their value is == the query's. |
GREATER_EQUAL |
Datapoints are eligible iff their value is >= the query's. |
GREATER |
Datapoints are eligible iff their value is > the query's. |
NOT_EQUAL |
Datapoints are eligible iff their value is != the query's. |
Restriction
Restriction of a datapoint which describe its attributes(tokens) from each of several attribute categories(namespaces).
| Fields | |
|---|---|
namespace |
The namespace of this restriction. e.g.: color. |
allow_list[] |
The attributes to allow in this namespace. e.g.: 'red' |
deny_list[] |
The attributes to deny in this namespace. e.g.: 'blue' |
SparseEmbedding
Feature embedding vector for sparse index. An array of numbers whose values are located in the specified dimensions.
| Fields | |
|---|---|
values[] |
Required. The list of embedding values of the sparse vector. |
dimensions[] |
Required. The list of indexes for the embedding values of the sparse vector. |
IndexEndpoint
Indexes are deployed into it. An IndexEndpoint can have multiple DeployedIndexes.
| Fields | |
|---|---|
name |
Output only. The resource name of the IndexEndpoint. |
display_name |
Required. The display name of the IndexEndpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
description |
The description of the IndexEndpoint. |
deployed_indexes[] |
Output only. The indexes deployed in this endpoint. |
etag |
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
The labels with user-defined metadata to organize your IndexEndpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
create_time |
Output only. Timestamp when this IndexEndpoint was created. |
update_time |
Output only. Timestamp when this IndexEndpoint was last updated. This timestamp is not updated when the endpoint's DeployedIndexes are updated, e.g. due to updates of the original Indexes they are the deployments of. |
network |
Optional. The full name of the Google Compute Engine network to which the IndexEndpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network.
Format: |
enable_private_service_connect |
Optional. Deprecated: If true, expose the IndexEndpoint via private service connect. Only one of the fields, |
private_service_connect_config |
Optional. Configuration for private service connect.
|
public_endpoint_enabled |
Optional. If true, the deployed index will be accessible through public endpoint. |
public_endpoint_domain_name |
Output only. If |
encryption_spec |
Immutable. Customer-managed encryption key spec for an IndexEndpoint. If set, this IndexEndpoint and all sub-resources of this IndexEndpoint will be secured by this key. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
IndexPrivateEndpoints
IndexPrivateEndpoints proto is used to provide paths for users to send requests via private endpoints (e.g. private service access, private service connect). To send request via private service access, use match_grpc_address. To send request via private service connect, use service_attachment.
| Fields | |
|---|---|
match_grpc_address |
Output only. The ip address used to send match gRPC requests. |
service_attachment |
Output only. The name of the service attachment resource. Populated if private service connect is enabled. |
psc_automated_endpoints[] |
Output only. PscAutomatedEndpoints is populated if private service connect is enabled if PscAutomatedConfig is set. |
IndexStats
Stats of the Index.
| Fields | |
|---|---|
vectors_count |
Output only. The number of dense vectors in the Index. |
sparse_vectors_count |
Output only. The number of sparse vectors in the Index. |
shards_count |
Output only. The number of shards in the Index. |
InputDataConfig
Specifies Vertex AI owned input data to be used for training, and possibly evaluating, the Model.
| Fields | |
|---|---|
dataset_id |
Required. The ID of the Dataset in the same Project and Location which data will be used to train the Model. The Dataset must use schema compatible with Model being trained, and what is compatible should be described in the used TrainingPipeline's |
annotations_filter |
Applicable only to Datasets that have DataItems and Annotations. A filter on Annotations of the Dataset. Only Annotations that both match this filter and belong to DataItems not ignored by the split method are used in respectively training, validation or test role, depending on the role of the DataItem they are on (for the auto-assigned that role is decided by Vertex AI). A filter with same syntax as the one used in |
annotation_schema_uri |
Applicable only to custom training with Datasets that have DataItems and Annotations. Cloud Storage URI that points to a YAML file describing the annotation schema. The schema is defined as an OpenAPI 3.0.2 Schema Object. The schema files that can be used here are found in gs://google-cloud-aiplatform/schema/dataset/annotation/ , note that the chosen schema must be consistent with Only Annotations that both match this schema and belong to DataItems not ignored by the split method are used in respectively training, validation or test role, depending on the role of the DataItem they are on. When used in conjunction with |
saved_query_id |
Only applicable to Datasets that have SavedQueries. The ID of a SavedQuery (annotation set) under the Dataset specified by Only Annotations that are associated with this SavedQuery are used in respectively training. When used in conjunction with Only one of |
persist_ml_use_assignment |
Whether to persist the ML use assignment to data item system labels. |
Union field split. The instructions how the input data should be split between the training, validation and test sets. If no split type is provided, the fraction_split is used by default. split can be only one of the following: |
|
fraction_split |
Split based on fractions defining the size of each set. |
filter_split |
Split based on the provided filters for each set. |
predefined_split |
Supported only for tabular Datasets. Split based on a predefined key. |
timestamp_split |
Supported only for tabular Datasets. Split based on the timestamp of the input data pieces. |
stratified_split |
Supported only for tabular Datasets. Split based on the distribution of the specified column. |
Union field The destination of the training data to be written to. Supported destination file formats: * For non-tabular data: "jsonl". * For tabular data: "csv" and "bigquery". The following Vertex AI environment variables are passed to containers or python modules of the training task when this field is set:
|
|
gcs_destination |
The Cloud Storage location where the training data is to be written to. In the given directory a new directory is created with name: The Vertex AI environment variables representing Cloud Storage data URIs are represented in the Cloud Storage wildcard format to support sharded data. e.g.: "gs://.../training-*.jsonl"
|
bigquery_destination |
Only applicable to custom training with tabular Dataset with BigQuery source. The BigQuery project location where the training data is to be written to. In the given project a new dataset is created with name
|
Int64Array
A list of int64 values.
| Fields | |
|---|---|
values[] |
A list of int64 values. |
IntegratedGradientsAttribution
An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
| Fields | |
|---|---|
step_count |
Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively. |
smooth_grad_config |
Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf |
blur_baseline_config |
Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 |
JiraSource
The Jira source for the ImportRagFilesRequest.
| Fields | |
|---|---|
jira_queries[] |
Required. The Jira queries. |
JiraQueries
JiraQueries contains the Jira queries and corresponding authentication.
| Fields | |
|---|---|
projects[] |
A list of Jira projects to import in their entirety. |
custom_queries[] |
A list of custom Jira queries to import. For information about JQL (Jira Query Language), see https://support.atlassian.com/jira-service-management-cloud/docs/use-advanced-search-with-jira-query-language-jql/ |
email |
Required. The Jira email address. |
server_uri |
Required. The Jira server URI. |
api_key_config |
Required. The SecretManager secret version resource name (e.g. projects/{project}/secrets/{secret}/versions/{version}) storing the Jira API key. See Manage API tokens for your Atlassian account. |
JobState
Describes the state of a job.
| Enums | |
|---|---|
JOB_STATE_UNSPECIFIED |
The job state is unspecified. |
JOB_STATE_QUEUED |
The job has been just created or resumed and processing has not yet begun. |
JOB_STATE_PENDING |
The service is preparing to run the job. |
JOB_STATE_RUNNING |
The job is in progress. |
JOB_STATE_SUCCEEDED |
The job completed successfully. |
JOB_STATE_FAILED |
The job failed. |
JOB_STATE_CANCELLING |
The job is being cancelled. From this state the job may only go to either JOB_STATE_SUCCEEDED, JOB_STATE_FAILED or JOB_STATE_CANCELLED. |
JOB_STATE_CANCELLED |
The job has been cancelled. |
JOB_STATE_PAUSED |
The job has been stopped, and can be resumed. |
JOB_STATE_EXPIRED |
The job has expired. |
JOB_STATE_UPDATING |
The job is being updated. Only jobs in the RUNNING state can be updated. After updating, the job goes back to the RUNNING state. |
JOB_STATE_PARTIALLY_SUCCEEDED |
The job is partially succeeded, some results may be missing due to errors. |
LargeModelReference
Contains information about the Large Model.
| Fields | |
|---|---|
name |
Required. The unique name of the large Foundation or pre-built model. Like "chat-bison", "text-bison". Or model name with version ID, like "chat-bison@001", "text-bison@005", etc. |
LineageSubgraph
A subgraph of the overall lineage graph. Event edges connect Artifact and Execution nodes.
| Fields | |
|---|---|
artifacts[] |
The Artifact nodes in the subgraph. |
executions[] |
The Execution nodes in the subgraph. |
events[] |
The Event edges between Artifacts and Executions in the subgraph. |
ListAnnotationsRequest
Request message for DatasetService.ListAnnotations.
| Fields | |
|---|---|
parent |
Required. The resource name of the DataItem to list Annotations from. Format: |
filter |
The standard list filter. |
page_size |
The standard list page size. |
page_token |
The standard list page token. |
read_mask |
Mask specifying which fields to read. |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. |
ListAnnotationsResponse
Response message for DatasetService.ListAnnotations.
| Fields | |
|---|---|
annotations[] |
A list of Annotations that matches the specified filter in the request. |
next_page_token |
The standard List next-page token. |
ListArtifactsRequest
Request message for MetadataService.ListArtifacts.
| Fields | |
|---|---|
parent |
Required. The MetadataStore whose Artifacts should be listed. Format: |
page_size |
The maximum number of Artifacts to return. The service may return fewer. Must be in range 1-1000, inclusive. Defaults to 100. |
page_token |
A page token, received from a previous When paginating, all other provided parameters must match the call that provided the page token. (Otherwise the request will fail with INVALID_ARGUMENT error.) |
filter |
Filter specifying the boolean condition for the Artifacts to satisfy in order to be part of the result set. The syntax to define filter query is based on https://google.aip.dev/160. The supported set of filters include the following:
Each of the above supported filter types can be combined together using logical operators ( For example: |
order_by |
How the list of messages is ordered. Specify the values to order by and an ordering operation. The default sorting order is ascending. To specify descending order for a field, users append a " desc" suffix; for example: "foo desc, bar". Subfields are specified with a |
ListArtifactsResponse
Response message for MetadataService.ListArtifacts.
| Fields | |
|---|---|
artifacts[] |
The Artifacts retrieved from the MetadataStore. |
next_page_token |
A token, which can be sent as |
ListBatchPredictionJobsRequest
Request message for JobService.ListBatchPredictionJobs.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the BatchPredictionJobs from. Format: |
filter |
The standard list filter. Supported fields:
Some examples of using the filter are:
|
page_size |
The standard list page size. |
page_token |
The standard list page token. Typically obtained via |
read_mask |
Mask specifying which fields to read. |
ListBatchPredictionJobsResponse
Response message for JobService.ListBatchPredictionJobs
| Fields | |
|---|---|
batch_prediction_jobs[] |
List of BatchPredictionJobs in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListCachedContentsRequest
Request to list CachedContents.
| Fields | |
|---|---|
parent |
Required. The parent, which owns this collection of cached contents. |
page_size |
Optional. The maximum number of cached contents to return. The service may return fewer than this value. If unspecified, some default (under maximum) number of items will be returned. The maximum value is 1000; values above 1000 will be coerced to 1000. |
page_token |
Optional. A page token, received from a previous When paginating, all other parameters provided to |
ListCachedContentsResponse
Response with a list of CachedContents.
| Fields | |
|---|---|
cached_contents[] |
List of cached contents. |
next_page_token |
A token, which can be sent as |
ListContextsRequest
Request message for MetadataService.ListContexts
| Fields | |
|---|---|
parent |
Required. The MetadataStore whose Contexts should be listed. Format: |
page_size |
The maximum number of Contexts to return. The service may return fewer. Must be in range 1-1000, inclusive. Defaults to 100. |
page_token |
A page token, received from a previous When paginating, all other provided parameters must match the call that provided the page token. (Otherwise the request will fail with INVALID_ARGUMENT error.) |
filter |
Filter specifying the boolean condition for the Contexts to satisfy in order to be part of the result set. The syntax to define filter query is based on https://google.aip.dev/160. Following are the supported set of filters:
Each of the above supported filters can be combined together using logical operators ( For example: |
order_by |
How the list of messages is ordered. Specify the values to order by and an ordering operation. The default sorting order is ascending. To specify descending order for a field, users append a " desc" suffix; for example: "foo desc, bar". Subfields are specified with a |
ListContextsResponse
Response message for MetadataService.ListContexts.
| Fields | |
|---|---|
contexts[] |
The Contexts retrieved from the MetadataStore. |
next_page_token |
A token, which can be sent as |
ListCustomJobsRequest
Request message for JobService.ListCustomJobs.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the CustomJobs from. Format: |
filter |
The standard list filter. Supported fields:
Some examples of using the filter are:
|
page_size |
The standard list page size. |
page_token |
The standard list page token. Typically obtained via |
read_mask |
Mask specifying which fields to read. |
ListCustomJobsResponse
Response message for JobService.ListCustomJobs
| Fields | |
|---|---|
custom_jobs[] |
List of CustomJobs in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListDataItemsRequest
Request message for DatasetService.ListDataItems.
| Fields | |
|---|---|
parent |
Required. The resource name of the Dataset to list DataItems from. Format: |
filter |
The standard list filter. |
page_size |
The standard list page size. |
page_token |
The standard list page token. |
read_mask |
Mask specifying which fields to read. |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. |
ListDataItemsResponse
Response message for DatasetService.ListDataItems.
| Fields | |
|---|---|
data_items[] |
A list of DataItems that matches the specified filter in the request. |
next_page_token |
The standard List next-page token. |
ListDatasetVersionsRequest
Request message for DatasetService.ListDatasetVersions.
| Fields | |
|---|---|
parent |
Required. The resource name of the Dataset to list DatasetVersions from. Format: |
filter |
Optional. The standard list filter. |
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. |
read_mask |
Optional. Mask specifying which fields to read. |
order_by |
Optional. A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. |
ListDatasetVersionsResponse
Response message for DatasetService.ListDatasetVersions.
| Fields | |
|---|---|
dataset_versions[] |
A list of DatasetVersions that matches the specified filter in the request. |
next_page_token |
The standard List next-page token. |
ListDatasetsRequest
Request message for DatasetService.ListDatasets.
| Fields | |
|---|---|
parent |
Required. The name of the Dataset's parent resource. Format: |
filter |
An expression for filtering the results of the request. For field names both snake_case and camelCase are supported.
Some examples:
|
page_size |
The standard list page size. |
page_token |
The standard list page token. |
read_mask |
Mask specifying which fields to read. |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields:
|
ListDatasetsResponse
Response message for DatasetService.ListDatasets.
| Fields | |
|---|---|
datasets[] |
A list of Datasets that matches the specified filter in the request. |
next_page_token |
The standard List next-page token. |
ListDeploymentResourcePoolsRequest
Request message for ListDeploymentResourcePools method.
| Fields | |
|---|---|
parent |
Required. The parent Location which owns this collection of DeploymentResourcePools. Format: |
page_size |
The maximum number of DeploymentResourcePools to return. The service may return fewer than this value. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
ListDeploymentResourcePoolsResponse
Response message for ListDeploymentResourcePools method.
| Fields | |
|---|---|
deployment_resource_pools[] |
The DeploymentResourcePools from the specified location. |
next_page_token |
A token, which can be sent as |
ListEndpointsRequest
Request message for EndpointService.ListEndpoints.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location from which to list the Endpoints. Format: |
filter |
Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported.
Some examples:
|
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. Typically obtained via |
read_mask |
Optional. Mask specifying which fields to read. |
ListEndpointsResponse
Response message for EndpointService.ListEndpoints.
| Fields | |
|---|---|
endpoints[] |
List of Endpoints in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListEntityTypesRequest
Request message for FeaturestoreService.ListEntityTypes.
| Fields | |
|---|---|
parent |
Required. The resource name of the Featurestore to list EntityTypes. Format: |
filter |
Lists the EntityTypes that match the filter expression. The following filters are supported:
Examples:
|
page_size |
The maximum number of EntityTypes to return. The service may return fewer than this value. If unspecified, at most 1000 EntityTypes will be returned. The maximum value is 1000; any value greater than 1000 will be coerced to 1000. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields:
|
read_mask |
Mask specifying which fields to read. |
ListEntityTypesResponse
Response message for FeaturestoreService.ListEntityTypes.
| Fields | |
|---|---|
entity_types[] |
The EntityTypes matching the request. |
next_page_token |
A token, which can be sent as |
ListExecutionsRequest
Request message for MetadataService.ListExecutions.
| Fields | |
|---|---|
parent |
Required. The MetadataStore whose Executions should be listed. Format: |
page_size |
The maximum number of Executions to return. The service may return fewer. Must be in range 1-1000, inclusive. Defaults to 100. |
page_token |
A page token, received from a previous When paginating, all other provided parameters must match the call that provided the page token. (Otherwise the request will fail with an INVALID_ARGUMENT error.) |
filter |
Filter specifying the boolean condition for the Executions to satisfy in order to be part of the result set. The syntax to define filter query is based on https://google.aip.dev/160. Following are the supported set of filters:
Each of the above supported filters can be combined together using logical operators ( For example: |
order_by |
How the list of messages is ordered. Specify the values to order by and an ordering operation. The default sorting order is ascending. To specify descending order for a field, users append a " desc" suffix; for example: "foo desc, bar". Subfields are specified with a |
ListExecutionsResponse
Response message for MetadataService.ListExecutions.
| Fields | |
|---|---|
executions[] |
The Executions retrieved from the MetadataStore. |
next_page_token |
A token, which can be sent as |
ListExtensionsRequest
Request message for ExtensionRegistryService.ListExtensions.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the Extensions from. Format: |
filter |
Optional. The standard list filter. Supported fields: * More detail in AIP-160. |
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. |
order_by |
Optional. A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields: * Example: |
ListExtensionsResponse
Response message for ExtensionRegistryService.ListExtensions
| Fields | |
|---|---|
extensions[] |
List of Extension in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListFeatureGroupsRequest
Request message for FeatureRegistryService.ListFeatureGroups.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list FeatureGroups. Format: |
filter |
Lists the FeatureGroups that match the filter expression. The following fields are supported:
Examples:
|
page_size |
The maximum number of FeatureGroups to return. The service may return fewer than this value. If unspecified, at most 100 FeatureGroups will be returned. The maximum value is 100; any value greater than 100 will be coerced to 100. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported Fields:
|
ListFeatureGroupsResponse
Response message for FeatureRegistryService.ListFeatureGroups.
| Fields | |
|---|---|
feature_groups[] |
The FeatureGroups matching the request. |
next_page_token |
A token, which can be sent as |
ListFeatureMonitorJobsRequest
Request message for FeatureRegistryService.ListFeatureMonitorJobs.
| Fields | |
|---|---|
parent |
Required. The resource name of the FeatureMonitor to list FeatureMonitorJobs. Format: |
filter |
Optional. Lists the FeatureMonitorJobs that match the filter expression. The following fields are supported:
Examples:
|
page_size |
Optional. The maximum number of FeatureMonitorJobs to return. The service may return fewer than this value. If unspecified, at most 100 FeatureMonitorJobs will be returned. The maximum value is 100; any value greater than 100 will be coerced to 100. |
page_token |
Optional. A page token, received from a previous When paginating, all other parameters provided to |
order_by |
Optional. A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported Fields:
|
ListFeatureMonitorJobsResponse
Response message for FeatureRegistryService.ListFeatureMonitorJobs.
| Fields | |
|---|---|
feature_monitor_jobs[] |
The FeatureMonitorJobs matching the request. |
next_page_token |
A token, which can be sent as |
ListFeatureMonitorsRequest
Request message for FeatureRegistryService.ListFeatureMonitors.
| Fields | |
|---|---|
parent |
Required. The resource name of the FeatureGroup to list FeatureMonitors. Format: |
filter |
Optional. Lists the FeatureMonitors that match the filter expression. The following fields are supported:
Examples:
|
page_size |
Optional. The maximum number of FeatureGroups to return. The service may return fewer than this value. If unspecified, at most 100 FeatureMonitors will be returned. The maximum value is 100; any value greater than 100 will be coerced to 100. |
page_token |
Optional. A page token, received from a previous When paginating, all other parameters provided to |
order_by |
Optional. A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported Fields:
|
ListFeatureMonitorsResponse
Response message for FeatureRegistryService.ListFeatureMonitors.
| Fields | |
|---|---|
feature_monitors[] |
The FeatureMonitors matching the request. |
next_page_token |
A token, which can be sent as |
ListFeatureOnlineStoresRequest
Request message for FeatureOnlineStoreAdminService.ListFeatureOnlineStores.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list FeatureOnlineStores. Format: |
filter |
Lists the FeatureOnlineStores that match the filter expression. The following fields are supported:
Examples:
|
page_size |
The maximum number of FeatureOnlineStores to return. The service may return fewer than this value. If unspecified, at most 100 FeatureOnlineStores will be returned. The maximum value is 100; any value greater than 100 will be coerced to 100. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported Fields:
|
ListFeatureOnlineStoresResponse
Response message for FeatureOnlineStoreAdminService.ListFeatureOnlineStores.
| Fields | |
|---|---|
feature_online_stores[] |
The FeatureOnlineStores matching the request. |
next_page_token |
A token, which can be sent as |
ListFeatureViewSyncsRequest
Request message for FeatureOnlineStoreAdminService.ListFeatureViewSyncs.
| Fields | |
|---|---|
parent |
Required. The resource name of the FeatureView to list FeatureViewSyncs. Format: |
filter |
Lists the FeatureViewSyncs that match the filter expression. The following filters are supported:
Examples:
|
page_size |
The maximum number of FeatureViewSyncs to return. The service may return fewer than this value. If unspecified, at most 1000 FeatureViewSyncs will be returned. The maximum value is 1000; any value greater than 1000 will be coerced to 1000. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields:
|
ListFeatureViewSyncsResponse
Response message for FeatureOnlineStoreAdminService.ListFeatureViewSyncs.
| Fields | |
|---|---|
feature_view_syncs[] |
The FeatureViewSyncs matching the request. |
next_page_token |
A token, which can be sent as |
ListFeatureViewsRequest
Request message for FeatureOnlineStoreAdminService.ListFeatureViews.
| Fields | |
|---|---|
parent |
Required. The resource name of the FeatureOnlineStore to list FeatureViews. Format: |
filter |
Lists the FeatureViews that match the filter expression. The following filters are supported:
Examples:
|
page_size |
The maximum number of FeatureViews to return. The service may return fewer than this value. If unspecified, at most 1000 FeatureViews will be returned. The maximum value is 1000; any value greater than 1000 will be coerced to 1000. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields:
|
ListFeatureViewsResponse
Response message for FeatureOnlineStoreAdminService.ListFeatureViews.
| Fields | |
|---|---|
feature_views[] |
The FeatureViews matching the request. |
next_page_token |
A token, which can be sent as |
ListFeaturesRequest
Request message for FeaturestoreService.ListFeatures. Request message for FeatureRegistryService.ListFeatures.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list Features. Format for entity_type as parent: |
filter |
Lists the Features that match the filter expression. The following filters are supported:
Examples:
|
page_size |
The maximum number of Features to return. The service may return fewer than this value. If unspecified, at most 1000 Features will be returned. The maximum value is 1000; any value greater than 1000 will be coerced to 1000. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields:
|
read_mask |
Mask specifying which fields to read. |
latest_stats_count |
Only applicable for Vertex AI Feature Store (Legacy). If set, return the most recent |
ListFeaturesResponse
Response message for FeaturestoreService.ListFeatures. Response message for FeatureRegistryService.ListFeatures.
| Fields | |
|---|---|
features[] |
The Features matching the request. |
next_page_token |
A token, which can be sent as |
ListFeaturestoresRequest
Request message for FeaturestoreService.ListFeaturestores.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list Featurestores. Format: |
filter |
Lists the featurestores that match the filter expression. The following fields are supported:
Examples:
|
page_size |
The maximum number of Featurestores to return. The service may return fewer than this value. If unspecified, at most 100 Featurestores will be returned. The maximum value is 100; any value greater than 100 will be coerced to 100. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported Fields:
|
read_mask |
Mask specifying which fields to read. |
ListFeaturestoresResponse
Response message for FeaturestoreService.ListFeaturestores.
| Fields | |
|---|---|
featurestores[] |
The Featurestores matching the request. |
next_page_token |
A token, which can be sent as |
ListHyperparameterTuningJobsRequest
Request message for JobService.ListHyperparameterTuningJobs.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the HyperparameterTuningJobs from. Format: |
filter |
The standard list filter. Supported fields:
Some examples of using the filter are:
|
page_size |
The standard list page size. |
page_token |
The standard list page token. Typically obtained via |
read_mask |
Mask specifying which fields to read. |
ListHyperparameterTuningJobsResponse
Response message for JobService.ListHyperparameterTuningJobs
| Fields | |
|---|---|
hyperparameter_tuning_jobs[] |
List of HyperparameterTuningJobs in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListIndexEndpointsRequest
Request message for IndexEndpointService.ListIndexEndpoints.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location from which to list the IndexEndpoints. Format: |
filter |
Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported.
Some examples: * |
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. Typically obtained via |
read_mask |
Optional. Mask specifying which fields to read. |
ListIndexEndpointsResponse
Response message for IndexEndpointService.ListIndexEndpoints.
| Fields | |
|---|---|
index_endpoints[] |
List of IndexEndpoints in the requested page. |
next_page_token |
A token to retrieve next page of results. Pass to |
ListIndexesRequest
Request message for IndexService.ListIndexes.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location from which to list the Indexes. Format: |
filter |
The standard list filter. |
page_size |
The standard list page size. |
page_token |
The standard list page token. Typically obtained via |
read_mask |
Mask specifying which fields to read. |
ListIndexesResponse
Response message for IndexService.ListIndexes.
| Fields | |
|---|---|
indexes[] |
List of indexes in the requested page. |
next_page_token |
A token to retrieve next page of results. Pass to |
ListMetadataSchemasRequest
Request message for MetadataService.ListMetadataSchemas.
| Fields | |
|---|---|
parent |
Required. The MetadataStore whose MetadataSchemas should be listed. Format: |
page_size |
The maximum number of MetadataSchemas to return. The service may return fewer. Must be in range 1-1000, inclusive. Defaults to 100. |
page_token |
A page token, received from a previous When paginating, all other provided parameters must match the call that provided the page token. (Otherwise the request will fail with INVALID_ARGUMENT error.) |
filter |
A query to filter available MetadataSchemas for matching results. |
ListMetadataSchemasResponse
Response message for MetadataService.ListMetadataSchemas.
| Fields | |
|---|---|
metadata_schemas[] |
The MetadataSchemas found for the MetadataStore. |
next_page_token |
A token, which can be sent as |
ListMetadataStoresRequest
Request message for MetadataService.ListMetadataStores.
| Fields | |
|---|---|
parent |
Required. The Location whose MetadataStores should be listed. Format: |
page_size |
The maximum number of Metadata Stores to return. The service may return fewer. Must be in range 1-1000, inclusive. Defaults to 100. |
page_token |
A page token, received from a previous When paginating, all other provided parameters must match the call that provided the page token. (Otherwise the request will fail with INVALID_ARGUMENT error.) |
ListMetadataStoresResponse
Response message for MetadataService.ListMetadataStores.
| Fields | |
|---|---|
metadata_stores[] |
The MetadataStores found for the Location. |
next_page_token |
A token, which can be sent as |
ListModelDeploymentMonitoringJobsRequest
Request message for JobService.ListModelDeploymentMonitoringJobs.
| Fields | |
|---|---|
parent |
Required. The parent of the ModelDeploymentMonitoringJob. Format: |
filter |
The standard list filter. Supported fields:
Some examples of using the filter are:
|
page_size |
The standard list page size. |
page_token |
The standard list page token. |
read_mask |
Mask specifying which fields to read |
ListModelDeploymentMonitoringJobsResponse
Response message for JobService.ListModelDeploymentMonitoringJobs.
| Fields | |
|---|---|
model_deployment_monitoring_jobs[] |
A list of ModelDeploymentMonitoringJobs that matches the specified filter in the request. |
next_page_token |
The standard List next-page token. |
ListModelEvaluationSlicesRequest
Request message for ModelService.ListModelEvaluationSlices.
| Fields | |
|---|---|
parent |
Required. The resource name of the ModelEvaluation to list the ModelEvaluationSlices from. Format: |
filter |
The standard list filter.
|
page_size |
The standard list page size. |
page_token |
The standard list page token. Typically obtained via |
read_mask |
Mask specifying which fields to read. |
ListModelEvaluationSlicesResponse
Response message for ModelService.ListModelEvaluationSlices.
| Fields | |
|---|---|
model_evaluation_slices[] |
List of ModelEvaluations in the requested page. |
next_page_token |
A token to retrieve next page of results. Pass to |
ListModelEvaluationsRequest
Request message for ModelService.ListModelEvaluations.
| Fields | |
|---|---|
parent |
Required. The resource name of the Model to list the ModelEvaluations from. Format: |
filter |
The standard list filter. |
page_size |
The standard list page size. |
page_token |
The standard list page token. Typically obtained via |
read_mask |
Mask specifying which fields to read. |
ListModelEvaluationsResponse
Response message for ModelService.ListModelEvaluations.
| Fields | |
|---|---|
model_evaluations[] |
List of ModelEvaluations in the requested page. |
next_page_token |
A token to retrieve next page of results. Pass to |
ListModelMonitoringJobsRequest
Request message for ModelMonitoringService.ListModelMonitoringJobs.
| Fields | |
|---|---|
parent |
Required. The parent of the ModelMonitoringJob. Format: |
filter |
The standard list filter. More detail in AIP-160. |
page_size |
The standard list page size. |
page_token |
The standard list page token. |
read_mask |
Mask specifying which fields to read |
ListModelMonitoringJobsResponse
Response message for ModelMonitoringService.ListModelMonitoringJobs.
| Fields | |
|---|---|
model_monitoring_jobs[] |
A list of ModelMonitoringJobs that matches the specified filter in the request. |
next_page_token |
The standard List next-page token. |
ListModelMonitorsRequest
Request message for ModelMonitoringService.ListModelMonitors.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the ModelMonitors from. Format: |
filter |
The standard list filter. More detail in AIP-160. |
page_size |
The standard list page size. |
page_token |
The standard list page token. |
read_mask |
Mask specifying which fields to read. |
ListModelMonitorsResponse
Response message for ModelMonitoringService.ListModelMonitors
| Fields | |
|---|---|
model_monitors[] |
List of ModelMonitor in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListModelVersionCheckpointsRequest
Request message for ModelService.ListModelVersionCheckpoints.
| Fields | |
|---|---|
name |
Required. The name of the model version to list checkpoints for. |
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. Typically obtained via |
ListModelVersionCheckpointsResponse
Response message for ModelService.ListModelVersionCheckpoints
| Fields | |
|---|---|
checkpoints[] |
List of Model Version checkpoints. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListModelVersionsRequest
Request message for ModelService.ListModelVersions.
| Fields | |
|---|---|
name |
Required. The name of the model to list versions for. |
page_size |
The standard list page size. |
page_token |
The standard list page token. Typically obtained via |
filter |
An expression for filtering the results of the request. For field names both snake_case and camelCase are supported.
Some examples:
|
read_mask |
Mask specifying which fields to read. |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields:
Example: |
ListModelVersionsResponse
Response message for ModelService.ListModelVersions
| Fields | |
|---|---|
models[] |
List of Model versions in the requested page. In the returned Model name field, version ID instead of regvision tag will be included. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListModelsRequest
Request message for ModelService.ListModels.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the Models from. Format: |
filter |
An expression for filtering the results of the request. For field names both snake_case and camelCase are supported.
Some examples:
|
page_size |
The standard list page size. |
page_token |
The standard list page token. Typically obtained via |
read_mask |
Mask specifying which fields to read. |
ListModelsResponse
Response message for ModelService.ListModels
| Fields | |
|---|---|
models[] |
List of Models in the requested page. |
next_page_token |
A token to retrieve next page of results. Pass to |
ListNotebookExecutionJobsRequest
Request message for [NotebookService.ListNotebookExecutionJobs]
| Fields | |
|---|---|
parent |
Required. The resource name of the Location from which to list the NotebookExecutionJobs. Format: |
filter |
Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported.
Some examples: * |
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. Typically obtained via |
order_by |
Optional. A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields:
Example: |
view |
Optional. The NotebookExecutionJob view. Defaults to BASIC. |
ListNotebookExecutionJobsResponse
Response message for [NotebookService.CreateNotebookExecutionJob]
| Fields | |
|---|---|
notebook_execution_jobs[] |
List of NotebookExecutionJobs in the requested page. |
next_page_token |
A token to retrieve next page of results. Pass to |
ListNotebookRuntimeTemplatesRequest
Request message for NotebookService.ListNotebookRuntimeTemplates.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location from which to list the NotebookRuntimeTemplates. Format: |
filter |
Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported.
Some examples:
|
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. Typically obtained via |
read_mask |
Optional. Mask specifying which fields to read. |
order_by |
Optional. A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields:
Example: |
ListNotebookRuntimeTemplatesResponse
Response message for NotebookService.ListNotebookRuntimeTemplates.
| Fields | |
|---|---|
notebook_runtime_templates[] |
List of NotebookRuntimeTemplates in the requested page. |
next_page_token |
A token to retrieve next page of results. Pass to |
ListNotebookRuntimesRequest
Request message for NotebookService.ListNotebookRuntimes.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location from which to list the NotebookRuntimes. Format: |
filter |
Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported.
Some examples:
|
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. Typically obtained via |
read_mask |
Optional. Mask specifying which fields to read. |
order_by |
Optional. A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields:
Example: |
ListNotebookRuntimesResponse
Response message for NotebookService.ListNotebookRuntimes.
| Fields | |
|---|---|
notebook_runtimes[] |
List of NotebookRuntimes in the requested page. |
next_page_token |
A token to retrieve next page of results. Pass to |
ListOptimalTrialsRequest
Request message for VizierService.ListOptimalTrials.
| Fields | |
|---|---|
parent |
Required. The name of the Study that the optimal Trial belongs to. |
ListOptimalTrialsResponse
Response message for VizierService.ListOptimalTrials.
| Fields | |
|---|---|
optimal_trials[] |
The pareto-optimal Trials for multiple objective Study or the optimal trial for single objective Study. The definition of pareto-optimal can be checked in wiki page. https://en.wikipedia.org/wiki/Pareto_efficiency |
ListPersistentResourcesRequest
Request message for PersistentResourceService.ListPersistentResources.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the PersistentResources from. Format: |
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. Typically obtained via |
ListPersistentResourcesResponse
Response message for PersistentResourceService.ListPersistentResources
| Fields | |
|---|---|
persistent_resources[] |
|
next_page_token |
A token to retrieve next page of results. Pass to |
ListPipelineJobsRequest
Request message for PipelineService.ListPipelineJobs.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the PipelineJobs from. Format: |
filter |
Lists the PipelineJobs that match the filter expression. The following fields are supported:
Filter expressions can be combined together using logical operators ( The syntax to define filter expression is based on https://google.aip.dev/160. Examples:
|
page_size |
The standard list page size. |
page_token |
The standard list page token. Typically obtained via |
order_by |
A comma-separated list of fields to order by. The default sort order is in ascending order. Use "desc" after a field name for descending. You can have multiple order_by fields provided e.g. "create_time desc, end_time", "end_time, start_time, update_time" For example, using "create_time desc, end_time" will order results by create time in descending order, and if there are multiple jobs having the same create time, order them by the end time in ascending order. if order_by is not specified, it will order by default order is create time in descending order. Supported fields:
|
read_mask |
Mask specifying which fields to read. |
ListPipelineJobsResponse
Response message for PipelineService.ListPipelineJobs
| Fields | |
|---|---|
pipeline_jobs[] |
List of PipelineJobs in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListPublisherModelsRequest
Request message for ModelGardenService.ListPublisherModels.
| Fields | |
|---|---|
parent |
Required. The name of the Publisher from which to list the PublisherModels. Format: |
filter |
Optional. The standard list filter. |
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. Typically obtained via |
view |
Optional. PublisherModel view specifying which fields to read. |
order_by |
Optional. A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. |
language_code |
Optional. The IETF BCP-47 language code representing the language in which the publisher models' text information should be written in. If not set, by default English (en). |
list_all_versions |
Optional. List all publisher model versions if the flag is set to true. |
ListPublisherModelsResponse
Response message for ModelGardenService.ListPublisherModels.
| Fields | |
|---|---|
publisher_models[] |
List of PublisherModels in the requested page. |
next_page_token |
A token to retrieve next page of results. Pass to [ListPublisherModels.page_token][] to obtain that page. |
ListRagCorporaRequest
Request message for VertexRagDataService.ListRagCorpora.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location from which to list the RagCorpora. Format: |
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. Typically obtained via |
ListRagCorporaResponse
Response message for VertexRagDataService.ListRagCorpora.
| Fields | |
|---|---|
rag_corpora[] |
List of RagCorpora in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListRagFilesRequest
Request message for VertexRagDataService.ListRagFiles.
| Fields | |
|---|---|
parent |
Required. The resource name of the RagCorpus from which to list the RagFiles. Format: |
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. Typically obtained via |
ListRagFilesResponse
Response message for VertexRagDataService.ListRagFiles.
| Fields | |
|---|---|
rag_files[] |
List of RagFiles in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListReasoningEnginesRequest
Request message for ReasoningEngineService.ListReasoningEngines.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the ReasoningEngines from. Format: |
filter |
Optional. The standard list filter. More detail in AIP-160. |
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. |
ListReasoningEnginesResponse
Response message for ReasoningEngineService.ListReasoningEngines
| Fields | |
|---|---|
reasoning_engines[] |
List of ReasoningEngines in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListSavedQueriesRequest
Request message for DatasetService.ListSavedQueries.
| Fields | |
|---|---|
parent |
Required. The resource name of the Dataset to list SavedQueries from. Format: |
filter |
The standard list filter. |
page_size |
The standard list page size. |
page_token |
The standard list page token. |
read_mask |
Mask specifying which fields to read. |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. |
ListSavedQueriesResponse
Response message for DatasetService.ListSavedQueries.
| Fields | |
|---|---|
saved_queries[] |
A list of SavedQueries that match the specified filter in the request. |
next_page_token |
The standard List next-page token. |
ListSchedulesRequest
Request message for ScheduleService.ListSchedules.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the Schedules from. Format: |
filter |
Lists the Schedules that match the filter expression. The following fields are supported:
Filter expressions can be combined together using logical operators ( Examples:
|
page_size |
The standard list page size. Default to 100 if not specified. |
page_token |
The standard list page token. Typically obtained via |
order_by |
A comma-separated list of fields to order by. The default sort order is in ascending order. Use "desc" after a field name for descending. You can have multiple order_by fields provided. For example, using "create_time desc, end_time" will order results by create time in descending order, and if there are multiple schedules having the same create time, order them by the end time in ascending order. If order_by is not specified, it will order by default with create_time in descending order. Supported fields:
|
ListSchedulesResponse
Response message for ScheduleService.ListSchedules
| Fields | |
|---|---|
schedules[] |
List of Schedules in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListSpecialistPoolsRequest
Request message for SpecialistPoolService.ListSpecialistPools.
| Fields | |
|---|---|
parent |
Required. The name of the SpecialistPool's parent resource. Format: |
page_size |
The standard list page size. |
page_token |
The standard list page token. Typically obtained by |
read_mask |
Mask specifying which fields to read. FieldMask represents a set of |
ListSpecialistPoolsResponse
Response message for SpecialistPoolService.ListSpecialistPools.
| Fields | |
|---|---|
specialist_pools[] |
A list of SpecialistPools that matches the specified filter in the request. |
next_page_token |
The standard List next-page token. |
ListStudiesRequest
Request message for VizierService.ListStudies.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the Study from. Format: |
page_token |
Optional. A page token to request the next page of results. If unspecified, there are no subsequent pages. |
page_size |
Optional. The maximum number of studies to return per "page" of results. If unspecified, service will pick an appropriate default. |
ListStudiesResponse
Response message for VizierService.ListStudies.
| Fields | |
|---|---|
studies[] |
The studies associated with the project. |
next_page_token |
Passes this token as the |
ListTensorboardExperimentsRequest
Request message for TensorboardService.ListTensorboardExperiments.
| Fields | |
|---|---|
parent |
Required. The resource name of the Tensorboard to list TensorboardExperiments. Format: |
filter |
Lists the TensorboardExperiments that match the filter expression. |
page_size |
The maximum number of TensorboardExperiments to return. The service may return fewer than this value. If unspecified, at most 50 TensorboardExperiments are returned. The maximum value is 1000; values above 1000 are coerced to 1000. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
Field to use to sort the list. |
read_mask |
Mask specifying which fields to read. |
ListTensorboardExperimentsResponse
Response message for TensorboardService.ListTensorboardExperiments.
| Fields | |
|---|---|
tensorboard_experiments[] |
The TensorboardExperiments mathching the request. |
next_page_token |
A token, which can be sent as |
ListTensorboardRunsRequest
Request message for TensorboardService.ListTensorboardRuns.
| Fields | |
|---|---|
parent |
Required. The resource name of the TensorboardExperiment to list TensorboardRuns. Format: |
filter |
Lists the TensorboardRuns that match the filter expression. |
page_size |
The maximum number of TensorboardRuns to return. The service may return fewer than this value. If unspecified, at most 50 TensorboardRuns are returned. The maximum value is 1000; values above 1000 are coerced to 1000. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
Field to use to sort the list. |
read_mask |
Mask specifying which fields to read. |
ListTensorboardRunsResponse
Response message for TensorboardService.ListTensorboardRuns.
| Fields | |
|---|---|
tensorboard_runs[] |
The TensorboardRuns mathching the request. |
next_page_token |
A token, which can be sent as |
ListTensorboardTimeSeriesRequest
Request message for TensorboardService.ListTensorboardTimeSeries.
| Fields | |
|---|---|
parent |
Required. The resource name of the TensorboardRun to list TensorboardTimeSeries. Format: |
filter |
Lists the TensorboardTimeSeries that match the filter expression. |
page_size |
The maximum number of TensorboardTimeSeries to return. The service may return fewer than this value. If unspecified, at most 50 TensorboardTimeSeries are returned. The maximum value is 1000; values above 1000 are coerced to 1000. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
Field to use to sort the list. |
read_mask |
Mask specifying which fields to read. |
ListTensorboardTimeSeriesResponse
Response message for TensorboardService.ListTensorboardTimeSeries.
| Fields | |
|---|---|
tensorboard_time_series[] |
The TensorboardTimeSeries mathching the request. |
next_page_token |
A token, which can be sent as |
ListTensorboardsRequest
Request message for TensorboardService.ListTensorboards.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list Tensorboards. Format: |
filter |
Lists the Tensorboards that match the filter expression. |
page_size |
The maximum number of Tensorboards to return. The service may return fewer than this value. If unspecified, at most 100 Tensorboards are returned. The maximum value is 100; values above 100 are coerced to 100. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
order_by |
Field to use to sort the list. |
read_mask |
Mask specifying which fields to read. |
ListTensorboardsResponse
Response message for TensorboardService.ListTensorboards.
| Fields | |
|---|---|
tensorboards[] |
The Tensorboards mathching the request. |
next_page_token |
A token, which can be sent as |
ListTrainingPipelinesRequest
Request message for PipelineService.ListTrainingPipelines.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the TrainingPipelines from. Format: |
filter |
The standard list filter. Supported fields:
Some examples of using the filter are:
|
page_size |
The standard list page size. |
page_token |
The standard list page token. Typically obtained via |
read_mask |
Mask specifying which fields to read. |
ListTrainingPipelinesResponse
Response message for PipelineService.ListTrainingPipelines
| Fields | |
|---|---|
training_pipelines[] |
List of TrainingPipelines in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
ListTrialsRequest
Request message for VizierService.ListTrials.
| Fields | |
|---|---|
parent |
Required. The resource name of the Study to list the Trial from. Format: |
page_token |
Optional. A page token to request the next page of results. If unspecified, there are no subsequent pages. |
page_size |
Optional. The number of Trials to retrieve per "page" of results. If unspecified, the service will pick an appropriate default. |
ListTrialsResponse
Response message for VizierService.ListTrials.
| Fields | |
|---|---|
trials[] |
The Trials associated with the Study. |
next_page_token |
Pass this token as the |
ListTuningJobsRequest
Request message for GenAiTuningService.ListTuningJobs.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to list the TuningJobs from. Format: |
filter |
Optional. The standard list filter. |
page_size |
Optional. The standard list page size. |
page_token |
Optional. The standard list page token. Typically obtained via |
ListTuningJobsResponse
Response message for GenAiTuningService.ListTuningJobs
| Fields | |
|---|---|
tuning_jobs[] |
List of TuningJobs in the requested page. |
next_page_token |
A token to retrieve the next page of results. Pass to |
LogprobsResult
Logprobs Result
| Fields | |
|---|---|
top_candidates[] |
Length = total number of decoding steps. |
chosen_candidates[] |
Length = total number of decoding steps. The chosen candidates may or may not be in top_candidates. |
Candidate
Candidate for the logprobs token and score.
| Fields | |
|---|---|
token |
The candidate's token string value. |
token_id |
The candidate's token id value. |
log_probability |
The candidate's log probability. |
TopCandidates
Candidates with top log probabilities at each decoding step.
| Fields | |
|---|---|
candidates[] |
Sorted by log probability in descending order. |
LookupStudyRequest
Request message for VizierService.LookupStudy.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location to get the Study from. Format: |
display_name |
Required. The user-defined display name of the Study |
MachineSpec
Specification of a single machine.
| Fields | |
|---|---|
machine_type |
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For |
accelerator_type |
Immutable. The type of accelerator(s) that may be attached to the machine as per |
accelerator_count |
The number of accelerators to attach to the machine. |
tpu_topology |
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1"). |
reservation_affinity |
Optional. Immutable. Configuration controlling how this resource pool consumes reservation. |
ManualBatchTuningParameters
Manual batch tuning parameters.
| Fields | |
|---|---|
batch_size |
Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64. |
Measurement
A message representing a Measurement of a Trial. A Measurement contains the Metrics got by executing a Trial using suggested hyperparameter values.
| Fields | |
|---|---|
elapsed_duration |
Output only. Time that the Trial has been running at the point of this Measurement. |
step_count |
Output only. The number of steps the machine learning model has been trained for. Must be non-negative. |
metrics[] |
Output only. A list of metrics got by evaluating the objective functions using suggested Parameter values. |
Metric
A message representing a metric in the measurement.
| Fields | |
|---|---|
metric_id |
Output only. The ID of the Metric. The Metric should be defined in |
value |
Output only. The value for this metric. |
MergeVersionAliasesRequest
Request message for ModelService.MergeVersionAliases.
| Fields | |
|---|---|
name |
Required. The name of the model version to merge aliases, with a version ID explicitly included. Example: |
version_aliases[] |
Required. The set of version aliases to merge. The alias should be at most 128 characters, and match There is NO ordering in aliases, which means 1) The aliases returned from GetModel API might not have the exactly same order from this MergeVersionAliases API. 2) Adding and deleting the same alias in the request is not recommended, and the 2 operations will be cancelled out. |
MetadataSchema
Instance of a general MetadataSchema.
| Fields | |
|---|---|
name |
Output only. The resource name of the MetadataSchema. |
schema_version |
The version of the MetadataSchema. The version's format must match the following regular expression: |
schema |
Required. The raw YAML string representation of the MetadataSchema. The combination of [MetadataSchema.version] and the schema name given by The schema is defined as an OpenAPI 3.0.2 MetadataSchema Object |
schema_type |
The type of the MetadataSchema. This is a property that identifies which metadata types will use the MetadataSchema. |
create_time |
Output only. Timestamp when this MetadataSchema was created. |
description |
Description of the Metadata Schema |
MetadataSchemaType
Describes the type of the MetadataSchema.
| Enums | |
|---|---|
METADATA_SCHEMA_TYPE_UNSPECIFIED |
Unspecified type for the MetadataSchema. |
ARTIFACT_TYPE |
A type indicating that the MetadataSchema will be used by Artifacts. |
EXECUTION_TYPE |
A typee indicating that the MetadataSchema will be used by Executions. |
CONTEXT_TYPE |
A state indicating that the MetadataSchema will be used by Contexts. |
MetadataStore
Instance of a metadata store. Contains a set of metadata that can be queried.
| Fields | |
|---|---|
name |
Output only. The resource name of the MetadataStore instance. |
create_time |
Output only. Timestamp when this MetadataStore was created. |
update_time |
Output only. Timestamp when this MetadataStore was last updated. |
encryption_spec |
Customer-managed encryption key spec for a Metadata Store. If set, this Metadata Store and all sub-resources of this Metadata Store are secured using this key. |
description |
Description of the MetadataStore. |
state |
Output only. State information of the MetadataStore. |
dataplex_config |
Optional. Dataplex integration settings. |
DataplexConfig
Represents Dataplex integration settings.
| Fields | |
|---|---|
enabled_pipelines_lineage |
Optional. Whether or not Data Lineage synchronization is enabled for Vertex Pipelines. |
MetadataStoreState
Represents state information for a MetadataStore.
| Fields | |
|---|---|
disk_utilization_bytes |
The disk utilization of the MetadataStore in bytes. |
Metric
The metric used for dataset level evaluation.
| Fields | |
|---|---|
aggregation_metrics[] |
Optional. The aggregation metrics to use. |
Union field metric_spec. The metric spec used for evaluation. metric_spec can be only one of the following: |
|
pointwise_metric_spec |
Spec for pointwise metric. |
pairwise_metric_spec |
Spec for pairwise metric. |
exact_match_spec |
Spec for exact match metric. |
bleu_spec |
Spec for bleu metric. |
rouge_spec |
Spec for rouge metric. |
AggregationMetric
The aggregation metrics supported by EvaluationService.EvaluateDataset.
| Enums | |
|---|---|
AGGREGATION_METRIC_UNSPECIFIED |
Unspecified aggregation metric. |
AVERAGE |
Average aggregation metric. |
MODE |
Mode aggregation metric. |
STANDARD_DEVIATION |
Standard deviation aggregation metric. |
VARIANCE |
Variance aggregation metric. |
MINIMUM |
Minimum aggregation metric. |
MAXIMUM |
Maximum aggregation metric. |
MEDIAN |
Median aggregation metric. |
PERCENTILE_P90 |
90th percentile aggregation metric. |
PERCENTILE_P95 |
95th percentile aggregation metric. |
PERCENTILE_P99 |
99th percentile aggregation metric. |
MetricxInput
Input for MetricX metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for Metricx metric. |
instance |
Required. Metricx instance. |
MetricxInstance
Spec for MetricX instance - The fields used for evaluation are dependent on the MetricX version.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Optional. Ground truth used to compare against the prediction. |
source |
Optional. Source text in original language. |
MetricxResult
Spec for MetricX result - calculates the MetricX score for the given instance using the version specified in the spec.
| Fields | |
|---|---|
score |
Output only. MetricX score. Range depends on version. |
MetricxSpec
Spec for MetricX metric.
| Fields | |
|---|---|
source_language |
Optional. Source language in BCP-47 format. |
target_language |
Optional. Target language in BCP-47 format. Covers both prediction and reference. |
version |
Required. Which version to use for evaluation. |
MetricxVersion
MetricX Version options.
| Enums | |
|---|---|
METRICX_VERSION_UNSPECIFIED |
MetricX version unspecified. |
METRICX_24_REF |
MetricX 2024 (2.6) for translation + reference (reference-based). |
METRICX_24_SRC |
MetricX 2024 (2.6) for translation + source (QE). |
METRICX_24_SRC_REF |
MetricX 2024 (2.6) for translation + source + reference (source-reference-combined). |
MigratableResource
Represents one resource that exists in automl.googleapis.com, datalabeling.googleapis.com or ml.googleapis.com.
| Fields | |
|---|---|
last_migrate_time |
Output only. Timestamp when the last migration attempt on this MigratableResource started. Will not be set if there's no migration attempt on this MigratableResource. |
last_update_time |
Output only. Timestamp when this MigratableResource was last updated. |
Union field
|
|
ml_engine_model_version |
Output only. Represents one Version in ml.googleapis.com. |
automl_model |
Output only. Represents one Model in automl.googleapis.com. |
automl_dataset |
Output only. Represents one Dataset in automl.googleapis.com. |
data_labeling_dataset |
Output only. Represents one Dataset in datalabeling.googleapis.com. |
AutomlDataset
Represents one Dataset in automl.googleapis.com.
| Fields | |
|---|---|
dataset |
Full resource name of automl Dataset. Format: |
dataset_display_name |
The Dataset's display name in automl.googleapis.com. |
AutomlModel
Represents one Model in automl.googleapis.com.
| Fields | |
|---|---|
model |
Full resource name of automl Model. Format: |
model_display_name |
The Model's display name in automl.googleapis.com. |
DataLabelingDataset
Represents one Dataset in datalabeling.googleapis.com.
| Fields | |
|---|---|
dataset |
Full resource name of data labeling Dataset. Format: |
dataset_display_name |
The Dataset's display name in datalabeling.googleapis.com. |
data_labeling_annotated_datasets[] |
The migratable AnnotatedDataset in datalabeling.googleapis.com belongs to the data labeling Dataset. |
DataLabelingAnnotatedDataset
Represents one AnnotatedDataset in datalabeling.googleapis.com.
| Fields | |
|---|---|
annotated_dataset |
Full resource name of data labeling AnnotatedDataset. Format: |
annotated_dataset_display_name |
The AnnotatedDataset's display name in datalabeling.googleapis.com. |
MlEngineModelVersion
Represents one model Version in ml.googleapis.com.
| Fields | |
|---|---|
endpoint |
The ml.googleapis.com endpoint that this model Version currently lives in. Example values:
|
version |
Full resource name of ml engine model Version. Format: |
MigrateResourceRequest
Config of migrating one resource from automl.googleapis.com, datalabeling.googleapis.com and ml.googleapis.com to Vertex AI.
| Fields | |
|---|---|
Union field
|
|
migrate_ml_engine_model_version_config |
Config for migrating Version in ml.googleapis.com to Vertex AI's Model. |
migrate_automl_model_config |
Config for migrating Model in automl.googleapis.com to Vertex AI's Model. |
migrate_automl_dataset_config |
Config for migrating Dataset in automl.googleapis.com to Vertex AI's Dataset. |
migrate_data_labeling_dataset_config |
Config for migrating Dataset in datalabeling.googleapis.com to Vertex AI's Dataset. |
MigrateAutomlDatasetConfig
Config for migrating Dataset in automl.googleapis.com to Vertex AI's Dataset.
| Fields | |
|---|---|
dataset |
Required. Full resource name of automl Dataset. Format: |
dataset_display_name |
Required. Display name of the Dataset in Vertex AI. System will pick a display name if unspecified. |
MigrateAutomlModelConfig
Config for migrating Model in automl.googleapis.com to Vertex AI's Model.
| Fields | |
|---|---|
model |
Required. Full resource name of automl Model. Format: |
model_display_name |
Optional. Display name of the model in Vertex AI. System will pick a display name if unspecified. |
MigrateDataLabelingDatasetConfig
Config for migrating Dataset in datalabeling.googleapis.com to Vertex AI's Dataset.
| Fields | |
|---|---|
dataset |
Required. Full resource name of data labeling Dataset. Format: |
dataset_display_name |
Optional. Display name of the Dataset in Vertex AI. System will pick a display name if unspecified. |
migrate_data_labeling_annotated_dataset_configs[] |
Optional. Configs for migrating AnnotatedDataset in datalabeling.googleapis.com to Vertex AI's SavedQuery. The specified AnnotatedDatasets have to belong to the datalabeling Dataset. |
MigrateDataLabelingAnnotatedDatasetConfig
Config for migrating AnnotatedDataset in datalabeling.googleapis.com to Vertex AI's SavedQuery.
| Fields | |
|---|---|
annotated_dataset |
Required. Full resource name of data labeling AnnotatedDataset. Format: |
MigrateMlEngineModelVersionConfig
Config for migrating version in ml.googleapis.com to Vertex AI's Model.
| Fields | |
|---|---|
endpoint |
Required. The ml.googleapis.com endpoint that this model version should be migrated from. Example values:
|
model_version |
Required. Full resource name of ml engine model version. Format: |
model_display_name |
Required. Display name of the model in Vertex AI. System will pick a display name if unspecified. |
MigrateResourceResponse
Describes a successfully migrated resource.
| Fields | |
|---|---|
migratable_resource |
Before migration, the identifier in ml.googleapis.com, automl.googleapis.com or datalabeling.googleapis.com. |
Union field migrated_resource. After migration, the resource name in Vertex AI. migrated_resource can be only one of the following: |
|
dataset |
Migrated Dataset's resource name. |
model |
Migrated Model's resource name. |
Modality
Content Part modality
| Enums | |
|---|---|
MODALITY_UNSPECIFIED |
Unspecified modality. |
TEXT |
Plain text. |
IMAGE |
Image. |
VIDEO |
Video. |
AUDIO |
Audio. |
DOCUMENT |
Document, e.g. PDF. |
ModalityTokenCount
Represents token counting info for a single modality.
| Fields | |
|---|---|
modality |
The modality associated with this token count. |
token_count |
Number of tokens. |
Model
A trained machine learning Model.
| Fields | |
|---|---|
name |
The resource name of the Model. |
version_id |
Output only. Immutable. The version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model id. It is an auto-incrementing decimal number in string representation. |
version_aliases[] |
User provided version aliases so that a model version can be referenced via alias (i.e. |
version_create_time |
Output only. Timestamp when this version was created. |
version_update_time |
Output only. Timestamp when this version was most recently updated. |
display_name |
Required. The display name of the Model. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
description |
The description of the Model. |
version_description |
The description of this version. |
default_checkpoint_id |
The default checkpoint id of a model version. |
predict_schemata |
The schemata that describe formats of the Model's predictions and explanations as given and returned via |
metadata_schema_uri |
Immutable. Points to a YAML file stored on Google Cloud Storage describing additional information about the Model, that is specific to it. Unset if the Model does not have any additional information. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no additional metadata is needed, this field is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access. |
metadata |
Immutable. An additional information about the Model; the schema of the metadata can be found in |
supported_export_formats[] |
Output only. The formats in which this Model may be exported. If empty, this Model is not available for export. |
training_pipeline |
Output only. The resource name of the TrainingPipeline that uploaded this Model, if any. |
container_spec |
Input only. The specification of the container that is to be used when deploying this Model. The specification is ingested upon |
artifact_uri |
Immutable. The path to the directory containing the Model artifact and any of its supporting files. Not required for AutoML Models. |
supported_deployment_resources_types[] |
Output only. When this Model is deployed, its prediction resources are described by the |
supported_input_storage_formats[] |
Output only. The formats this Model supports in The possible formats are:
If this Model doesn't support any of these formats it means it cannot be used with a |
supported_output_storage_formats[] |
Output only. The formats this Model supports in The possible formats are:
If this Model doesn't support any of these formats it means it cannot be used with a |
create_time |
Output only. Timestamp when this Model was uploaded into Vertex AI. |
update_time |
Output only. Timestamp when this Model was most recently updated. |
deployed_models[] |
Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations. |
explanation_spec |
The default explanation specification for this Model. The Model can be used for All fields of the explanation_spec can be overridden by If the default explanation specification is not set for this Model, this Model can still be used for |
etag |
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
The labels with user-defined metadata to organize your Models. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
encryption_spec |
Customer-managed encryption key spec for a Model. If set, this Model and all sub-resources of this Model will be secured by this key. |
model_source_info |
Output only. Source of a model. It can either be automl training pipeline, custom training pipeline, BigQuery ML, or saved and tuned from Genie or Model Garden. |
original_model_info |
Output only. If this Model is a copy of another Model, this contains info about the original. |
metadata_artifact |
Output only. The resource name of the Artifact that was created in MetadataStore when creating the Model. The Artifact resource name pattern is |
base_model_source |
Optional. User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
BaseModelSource
User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models.
| Fields | |
|---|---|
Union field
|
|
model_garden_source |
Source information of Model Garden models. |
genie_source |
Information about the base model of Genie models. |
DeploymentResourcesType
Identifies a type of Model's prediction resources.
| Enums | |
|---|---|
DEPLOYMENT_RESOURCES_TYPE_UNSPECIFIED |
Should not be used. |
DEDICATED_RESOURCES |
Resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. |
AUTOMATIC_RESOURCES |
Resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. |
SHARED_RESOURCES |
Resources that can be shared by multiple DeployedModels. A pre-configured DeploymentResourcePool is required. |
ExportFormat
Represents export format supported by the Model. All formats export to Google Cloud Storage.
| Fields | |
|---|---|
id |
Output only. The ID of the export format. The possible format IDs are:
|
exportable_contents[] |
Output only. The content of this Model that may be exported. |
ExportableContent
The Model content that can be exported.
| Enums | |
|---|---|
EXPORTABLE_CONTENT_UNSPECIFIED |
Should not be used. |
ARTIFACT |
Model artifact and any of its supported files. Will be exported to the location specified by the artifactDestination field of the ExportModelRequest.output_config object. |
IMAGE |
The container image that is to be used when deploying this Model. Will be exported to the location specified by the imageDestination field of the ExportModelRequest.output_config object. |
OriginalModelInfo
Contains information about the original Model if this Model is a copy.
| Fields | |
|---|---|
model |
Output only. The resource name of the Model this Model is a copy of, including the revision. Format: |
ModelContainerSpec
Specification of a container for serving predictions. Some fields in this message correspond to fields in the Kubernetes Container v1 core specification.
| Fields | |
|---|---|
image_uri |
Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field. |
command[] |
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker If you do not specify this field, then the container's If you specify this field, then you can also specify the In this field, you can reference environment variables set by Vertex AI and environment variables set in the
Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with
This field corresponds to the |
args[] |
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's If you don't specify this field but do specify the If you don't specify this field and don't specify the In this field, you can reference environment variables set by Vertex AI and environment variables set in the
Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with
This field corresponds to the |
env[] |
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the |
ports[] |
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: Vertex AI does not use ports other than the first one listed. This field corresponds to the |
predict_route |
Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using For example, if you set this field to If you don't specify this field, it defaults to the following value when you
The placeholders in this value are replaced as follows:
|
health_route |
Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to If you don't specify this field, it defaults to the following value when you
The placeholders in this value are replaced as follows:
|
grpc_ports[] |
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, gRPC requests to the container will be disabled. Vertex AI does not use ports other than the first one listed. This field corresponds to the |
deployment_timeout |
Immutable. Deployment timeout. Limit for deployment timeout is 2 hours. |
shared_memory_size_mb |
Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. |
startup_probe |
Immutable. Specification for Kubernetes startup probe. |
health_probe |
Immutable. Specification for Kubernetes readiness probe. |
liveness_probe |
Immutable. Specification for Kubernetes liveness probe. |
ModelDeploymentMonitoringBigQueryTable
ModelDeploymentMonitoringBigQueryTable specifies the BigQuery table name as well as some information of the logs stored in this table.
| Fields | |
|---|---|
log_source |
The source of log. |
log_type |
The type of log. |
bigquery_table_path |
The created BigQuery table to store logs. Customer could do their own query & analysis. Format: |
request_response_logging_schema_version |
Output only. The schema version of the request/response logging BigQuery table. Default to v1 if unset. |
LogSource
Indicates where does the log come from.
| Enums | |
|---|---|
LOG_SOURCE_UNSPECIFIED |
Unspecified source. |
TRAINING |
Logs coming from Training dataset. |
SERVING |
Logs coming from Serving traffic. |
LogType
Indicates what type of traffic does the log belong to.
| Enums | |
|---|---|
LOG_TYPE_UNSPECIFIED |
Unspecified type. |
PREDICT |
Predict logs. |
EXPLAIN |
Explain logs. |
ModelDeploymentMonitoringJob
Represents a job that runs periodically to monitor the deployed models in an endpoint. It will analyze the logged training & prediction data to detect any abnormal behaviors.
| Fields | |
|---|---|
name |
Output only. Resource name of a ModelDeploymentMonitoringJob. |
display_name |
Required. The user-defined name of the ModelDeploymentMonitoringJob. The name can be up to 128 characters long and can consist of any UTF-8 characters. Display name of a ModelDeploymentMonitoringJob. |
endpoint |
Required. Endpoint resource name. Format: |
state |
Output only. The detailed state of the monitoring job. When the job is still creating, the state will be 'PENDING'. Once the job is successfully created, the state will be 'RUNNING'. Pause the job, the state will be 'PAUSED'. Resume the job, the state will return to 'RUNNING'. |
schedule_state |
Output only. Schedule state when the monitoring job is in Running state. |
latest_monitoring_pipeline_metadata |
Output only. Latest triggered monitoring pipeline metadata. |
model_deployment_monitoring_objective_configs[] |
Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately. |
model_deployment_monitoring_schedule_config |
Required. Schedule config for running the monitoring job. |
logging_sampling_strategy |
Required. Sample Strategy for logging. |
model_monitoring_alert_config |
Alert config for model monitoring. |
predict_instance_schema_uri |
YAML schema file uri describing the format of a single instance, which are given to format this Endpoint's prediction (and explanation). If not set, we will generate predict schema from collected predict requests. |
sample_predict_instance |
Sample Predict instance, same format as |
analysis_instance_schema_uri |
YAML schema file uri describing the format of a single instance that you want Tensorflow Data Validation (TFDV) to analyze. If this field is empty, all the feature data types are inferred from |
bigquery_tables[] |
Output only. The created bigquery tables for the job under customer project. Customer could do their own query & analysis. There could be 4 log tables in maximum: 1. Training data logging predict request/response 2. Serving data logging predict request/response |
log_ttl |
The TTL of BigQuery tables in user projects which stores logs. A day is the basic unit of the TTL and we take the ceil of TTL/86400(a day). e.g. { second: 3600} indicates ttl = 1 day. |
labels |
The labels with user-defined metadata to organize your ModelDeploymentMonitoringJob. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
create_time |
Output only. Timestamp when this ModelDeploymentMonitoringJob was created. |
update_time |
Output only. Timestamp when this ModelDeploymentMonitoringJob was updated most recently. |
next_schedule_time |
Output only. Timestamp when this monitoring pipeline will be scheduled to run for the next round. |
stats_anomalies_base_directory |
Stats anomalies base folder path. |
encryption_spec |
Customer-managed encryption key spec for a ModelDeploymentMonitoringJob. If set, this ModelDeploymentMonitoringJob and all sub-resources of this ModelDeploymentMonitoringJob will be secured by this key. |
enable_monitoring_pipeline_logs |
If true, the scheduled monitoring pipeline logs are sent to Google Cloud Logging, including pipeline status and anomalies detected. Please note the logs incur cost, which are subject to Cloud Logging pricing. |
error |
Output only. Only populated when the job's state is |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
LatestMonitoringPipelineMetadata
All metadata of most recent monitoring pipelines.
| Fields | |
|---|---|
run_time |
The time that most recent monitoring pipelines that is related to this run. |
status |
The status of the most recent monitoring pipeline. |
MonitoringScheduleState
The state to Specify the monitoring pipeline.
| Enums | |
|---|---|
MONITORING_SCHEDULE_STATE_UNSPECIFIED |
Unspecified state. |
PENDING |
The pipeline is picked up and wait to run. |
OFFLINE |
The pipeline is offline and will be scheduled for next run. |
RUNNING |
The pipeline is running. |
ModelDeploymentMonitoringObjectiveConfig
ModelDeploymentMonitoringObjectiveConfig contains the pair of deployed_model_id to ModelMonitoringObjectiveConfig.
| Fields | |
|---|---|
deployed_model_id |
The DeployedModel ID of the objective config. |
objective_config |
The objective config of for the modelmonitoring job of this deployed model. |
ModelDeploymentMonitoringObjectiveType
The Model Monitoring Objective types.
| Enums | |
|---|---|
MODEL_DEPLOYMENT_MONITORING_OBJECTIVE_TYPE_UNSPECIFIED |
Default value, should not be set. |
RAW_FEATURE_SKEW |
Raw feature values' stats to detect skew between Training-Prediction datasets. |
RAW_FEATURE_DRIFT |
Raw feature values' stats to detect drift between Serving-Prediction datasets. |
FEATURE_ATTRIBUTION_SKEW |
Feature attribution scores to detect skew between Training-Prediction datasets. |
FEATURE_ATTRIBUTION_DRIFT |
Feature attribution scores to detect skew between Prediction datasets collected within different time windows. |
ModelDeploymentMonitoringScheduleConfig
The config for scheduling monitoring job.
| Fields | |
|---|---|
monitor_interval |
Required. The model monitoring job scheduling interval. It will be rounded up to next full hour. This defines how often the monitoring jobs are triggered. |
monitor_window |
The time window of the prediction data being included in each prediction dataset. This window specifies how long the data should be collected from historical model results for each run. If not set, |
ModelEvaluation
A collection of metrics calculated by comparing Model's predictions on all of the test data against annotations from the test data.
| Fields | |
|---|---|
name |
Output only. The resource name of the ModelEvaluation. |
display_name |
The display name of the ModelEvaluation. |
metrics_schema_uri |
Points to a YAML file stored on Google Cloud Storage describing the |
metrics |
Evaluation metrics of the Model. The schema of the metrics is stored in |
create_time |
Output only. Timestamp when this ModelEvaluation was created. |
slice_dimensions[] |
All possible |
model_explanation |
Aggregated explanation metrics for the Model's prediction output over the data this ModelEvaluation uses. This field is populated only if the Model is evaluated with explanations, and only for AutoML tabular Models. |
explanation_specs[] |
Describes the values of |
metadata |
The metadata of the ModelEvaluation. For the ModelEvaluation uploaded from Managed Pipeline, metadata contains a structured value with keys of "pipeline_job_id", "evaluation_dataset_type", "evaluation_dataset_path", "row_based_metrics_path". |
bias_configs |
Specify the configuration for bias detection. |
BiasConfig
Configuration for bias detection.
| Fields | |
|---|---|
bias_slices |
Specification for how the data should be sliced for bias. It contains a list of slices, with limitation of two slices. The first slice of data will be the slice_a. The second slice in the list (slice_b) will be compared against the first slice. If only a single slice is provided, then slice_a will be compared against "not slice_a". Below are examples with feature "education" with value "low", "medium", "high" in the dataset: Example 1: A single slice provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'medium' or 'high'. Example 2: Two slices provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'high'. |
labels[] |
Positive labels selection on the target field. |
ModelEvaluationExplanationSpec
| Fields | |
|---|---|
explanation_type |
Explanation type. For AutoML Image Classification models, possible values are:
|
explanation_spec |
Explanation spec details. |
ModelEvaluationSlice
A collection of metrics calculated by comparing Model's predictions on a slice of the test data against ground truth annotations.
| Fields | |
|---|---|
name |
Output only. The resource name of the ModelEvaluationSlice. |
slice |
Output only. The slice of the test data that is used to evaluate the Model. |
metrics_schema_uri |
Output only. Points to a YAML file stored on Google Cloud Storage describing the |
metrics |
Output only. Sliced evaluation metrics of the Model. The schema of the metrics is stored in |
create_time |
Output only. Timestamp when this ModelEvaluationSlice was created. |
model_explanation |
Output only. Aggregated explanation metrics for the Model's prediction output over the data this ModelEvaluation uses. This field is populated only if the Model is evaluated with explanations, and only for tabular Models. |
Slice
Definition of a slice.
| Fields | |
|---|---|
dimension |
Output only. The dimension of the slice. Well-known dimensions are: * |
value |
Output only. The value of the dimension in this slice. |
slice_spec |
Output only. Specification for how the data was sliced. |
SliceSpec
Specification for how the data should be sliced.
| Fields | |
|---|---|
configs |
Mapping configuration for this SliceSpec. The key is the name of the feature. By default, the key will be prefixed by "instance" as a dictionary prefix for Vertex Batch Predictions output format. |
Range
A range of values for slice(s). low is inclusive, high is exclusive.
| Fields | |
|---|---|
low |
Inclusive low value for the range. |
high |
Exclusive high value for the range. |
SliceConfig
Specification message containing the config for this SliceSpec. When kind is selected as value and/or range, only a single slice will be computed. When all_values is present, a separate slice will be computed for each possible label/value for the corresponding key in config. Examples, with feature zip_code with values 12345, 23334, 88888 and feature country with values "US", "Canada", "Mexico" in the dataset:
Example 1:
{
"zip_code": { "value": { "float_value": 12345.0 } }
}
A single slice for any data with zip_code 12345 in the dataset.
Example 2:
{
"zip_code": { "range": { "low": 12345, "high": 20000 } }
}
A single slice containing data where the zip_codes between 12345 and 20000 For this example, data with the zip_code of 12345 will be in this slice.
Example 3:
{
"zip_code": { "range": { "low": 10000, "high": 20000 } },
"country": { "value": { "string_value": "US" } }
}
A single slice containing data where the zip_codes between 10000 and 20000 has the country "US". For this example, data with the zip_code of 12345 and country "US" will be in this slice.
Example 4:
{ "country": {"all_values": { "value": true } } }
Three slices are computed, one for each unique country in the dataset.
Example 5:
{
"country": { "all_values": { "value": true } },
"zip_code": { "value": { "float_value": 12345.0 } }
}
Three slices are computed, one for each unique country in the dataset where the zip_code is also 12345. For this example, data with zip_code 12345 and country "US" will be in one slice, zip_code 12345 and country "Canada" in another slice, and zip_code 12345 and country "Mexico" in another slice, totaling 3 slices.
| Fields | |
|---|---|
Union field
|
|
value |
A unique specific value for a given feature. Example: |
range |
A range of values for a numerical feature. Example: |
all_values |
If all_values is set to true, then all possible labels of the keyed feature will have another slice computed. Example: |
Value
Single value that supports strings and floats.
| Fields | |
|---|---|
Union field
|
|
string_value |
String type. |
float_value |
Float type. |
ModelExplanation
Aggregated explanation metrics for a Model over a set of instances.
| Fields | |
|---|---|
mean_attributions[] |
Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs. For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. The NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. |
ModelGardenSource
Contains information about the source of the models generated from Model Garden.
| Fields | |
|---|---|
public_model_name |
Required. The model garden source model resource name. |
ModelMonitor
Vertex AI Model Monitoring Service serves as a central hub for the analysis and visualization of data quality and performance related to models. ModelMonitor stands as a top level resource for overseeing your model monitoring tasks.
| Fields | |
|---|---|
name |
Immutable. Resource name of the ModelMonitor. Format: |
display_name |
The display name of the ModelMonitor. The name can be up to 128 characters long and can consist of any UTF-8. |
model_monitoring_target |
The entity that is subject to analysis. Currently only models in Vertex AI Model Registry are supported. If you want to analyze the model which is outside the Vertex AI, you could register a model in Vertex AI Model Registry using just a display name. |
training_dataset |
Optional training dataset used to train the model. It can serve as a reference dataset to identify changes in production. |
notification_spec |
Optional default notification spec, it can be overridden in the ModelMonitoringJob notification spec. |
output_spec |
Optional default monitoring metrics/logs export spec, it can be overridden in the ModelMonitoringJob output spec. If not specified, a default Google Cloud Storage bucket will be created under your project. |
explanation_spec |
Optional model explanation spec. It is used for feature attribution monitoring. |
model_monitoring_schema |
Monitoring Schema is to specify the model's features, prediction outputs and ground truth properties. It is used to extract pertinent data from the dataset and to process features based on their properties. Make sure that the schema aligns with your dataset, if it does not, we will be unable to extract data from the dataset. It is required for most models, but optional for Vertex AI AutoML Tables unless the schem information is not available. |
create_time |
Output only. Timestamp when this ModelMonitor was created. |
update_time |
Output only. Timestamp when this ModelMonitor was updated most recently. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
Union field default_objective. Optional default monitoring objective, it can be overridden in the ModelMonitoringJob objective spec. default_objective can be only one of the following: |
|
tabular_objective |
Optional default tabular model monitoring objective. |
ModelMonitoringTarget
The monitoring target refers to the entity that is subject to analysis. e.g. Vertex AI Model version.
| Fields | |
|---|---|
Union field
|
|
vertex_model |
Model in Vertex AI Model Registry. |
VertexModelSource
Model in Vertex AI Model Registry.
| Fields | |
|---|---|
model |
Model resource name. Format: projects/{project}/locations/{location}/models/{model}. |
model_version_id |
Model version id. |
ModelMonitoringAlert
Represents a single monitoring alert. This is currently used in the SearchModelMonitoringAlerts api, thus the alert wrapped in this message belongs to the resource asked in the request.
| Fields | |
|---|---|
stats_name |
The stats name. |
objective_type |
One of the supported monitoring objectives: |
alert_time |
Alert creation time. |
anomaly |
Anomaly details. |
ModelMonitoringAlertCondition
Monitoring alert triggered condition.
| Fields | |
|---|---|
Union field condition. Alert triggered condition. condition can be only one of the following: |
|
threshold |
A condition that compares a stats value against a threshold. Alert will be triggered if value above the threshold. |
ModelMonitoringAlertConfig
The alert config for model monitoring.
| Fields | |
|---|---|
enable_logging |
Dump the anomalies to Cloud Logging. The anomalies will be put to json payload encoded from proto |
notification_channels[] |
Resource names of the NotificationChannels to send alert. Must be of the format |
Union field
|
|
email_alert_config |
Email alert config. |
EmailAlertConfig
The config for email alert.
| Fields | |
|---|---|
user_emails[] |
The email addresses to send the alert. |
ModelMonitoringAnomaly
Represents a single model monitoring anomaly.
| Fields | |
|---|---|
model_monitoring_job |
Model monitoring job resource name. |
algorithm |
Algorithm used to calculated the metrics, eg: jensen_shannon_divergence, l_infinity. |
Union field
|
|
tabular_anomaly |
Tabular anomaly. |
TabularAnomaly
Tabular anomaly details.
| Fields | |
|---|---|
anomaly_uri |
Additional anomaly information. e.g. Google Cloud Storage uri. |
summary |
Overview of this anomaly. |
anomaly |
Anomaly body. |
trigger_time |
The time the anomaly was triggered. |
condition |
The alert condition associated with this anomaly. |
ModelMonitoringConfig
The model monitoring configuration used for Batch Prediction Job.
| Fields | |
|---|---|
objective_configs[] |
Model monitoring objective config. |
alert_config |
Model monitoring alert config. |
analysis_instance_schema_uri |
YAML schema file uri in Cloud Storage describing the format of a single instance that you want Tensorflow Data Validation (TFDV) to analyze. If there are any data type differences between predict instance and TFDV instance, this field can be used to override the schema. For models trained with Vertex AI, this field must be set as all the fields in predict instance formatted as string. |
stats_anomalies_base_directory |
A Google Cloud Storage location for batch prediction model monitoring to dump statistics and anomalies. If not provided, a folder will be created in customer project to hold statistics and anomalies. |
ModelMonitoringInput
Model monitoring data input spec.
| Fields | |
|---|---|
Union field dataset. Dataset source. dataset can be only one of the following: |
|
columnized_dataset |
Columnized dataset. |
batch_prediction_output |
Vertex AI Batch prediction Job. |
vertex_endpoint_logs |
Vertex AI Endpoint request & response logging. |
Union field time_spec. Time specification for the dataset. time_spec can be only one of the following: |
|
time_interval |
The time interval (pair of start_time and end_time) for which results should be returned. |
time_offset |
The time offset setting for which results should be returned. |
BatchPredictionOutput
Data from Vertex AI Batch prediction job output.
| Fields | |
|---|---|
batch_prediction_job |
Vertex AI Batch prediction job resource name. The job must match the model version specified in [ModelMonitor].[model_monitoring_target]. |
ModelMonitoringDataset
Input dataset spec.
| Fields | |
|---|---|
timestamp_field |
The timestamp field. Usually for serving data. |
Union field data_location. Choose one of supported data location for columnized dataset. data_location can be only one of the following: |
|
vertex_dataset |
Resource name of the Vertex AI managed dataset. |
gcs_source |
Google Cloud Storage data source. |
bigquery_source |
BigQuery data source. |
ModelMonitoringBigQuerySource
Dataset spec for data sotred in BigQuery.
| Fields | |
|---|---|
Union field
|
|
table_uri |
BigQuery URI to a table, up to 2000 characters long. All the columns in the table will be selected. Accepted forms:
|
query |
Standard SQL to be used instead of the |
ModelMonitoringGcsSource
Dataset spec for data stored in Google Cloud Storage.
| Fields | |
|---|---|
gcs_uri |
Google Cloud Storage URI to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames. |
format |
Data format of the dataset. |
DataFormat
Supported data format.
| Enums | |
|---|---|
DATA_FORMAT_UNSPECIFIED |
Data format unspecified, used when this field is unset. |
CSV |
CSV files. |
TF_RECORD |
TfRecord files |
JSONL |
JsonL files. |
TimeOffset
Time offset setting.
| Fields | |
|---|---|
offset |
[offset] is the time difference from the cut-off time. For scheduled jobs, the cut-off time is the scheduled time. For non-scheduled jobs, it's the time when the job was created. Currently we support the following format: 'w|W': Week, 'd|D': Day, 'h|H': Hour E.g. '1h' stands for 1 hour, '2d' stands for 2 days. |
window |
[window] refers to the scope of data selected for analysis. It allows you to specify the quantity of data you wish to examine. Currently we support the following format: 'w|W': Week, 'd|D': Day, 'h|H': Hour E.g. '1h' stands for 1 hour, '2d' stands for 2 days. |
VertexEndpointLogs
Data from Vertex AI Endpoint request response logging.
| Fields | |
|---|---|
endpoints[] |
List of endpoint resource names. The endpoints must enable the logging with the [Endpoint].[request_response_logging_config], and must contain the deployed model corresponding to the model version specified in [ModelMonitor].[model_monitoring_target]. |
ModelMonitoringJob
Represents a model monitoring job that analyze dataset using different monitoring algorithm.
| Fields | |
|---|---|
name |
Output only. Resource name of a ModelMonitoringJob. Format: |
display_name |
The display name of the ModelMonitoringJob. The name can be up to 128 characters long and can consist of any UTF-8. |
model_monitoring_spec |
Monitoring monitoring job spec. It outlines the specifications for monitoring objectives, notifications, and result exports. If left blank, the default monitoring specifications from the top-level resource 'ModelMonitor' will be applied. If provided, we will use the specification defined here rather than the default one. |
create_time |
Output only. Timestamp when this ModelMonitoringJob was created. |
update_time |
Output only. Timestamp when this ModelMonitoringJob was updated most recently. |
state |
Output only. The state of the monitoring job. * When the job is still creating, the state will be 'JOB_STATE_PENDING'. * Once the job is successfully created, the state will be 'JOB_STATE_RUNNING'. * Once the job is finished, the state will be one of 'JOB_STATE_FAILED', 'JOB_STATE_SUCCEEDED', 'JOB_STATE_PARTIALLY_SUCCEEDED'. |
schedule |
Output only. Schedule resource name. It will only appear when this job is triggered by a schedule. |
job_execution_detail |
Output only. Execution results for all the monitoring objectives. |
schedule_time |
Output only. Timestamp when this ModelMonitoringJob was scheduled. It will only appear when this job is triggered by a schedule. |
ModelMonitoringJobExecutionDetail
Represent the execution details of the job.
| Fields | |
|---|---|
baseline_datasets[] |
Processed baseline datasets. |
target_datasets[] |
Processed target datasets. |
objective_status |
Status of data processing for each monitoring objective. Key is the objective. |
error |
Additional job error status. |
ProcessedDataset
Processed dataset information.
| Fields | |
|---|---|
location |
Actual data location of the processed dataset. |
time_range |
Dataset time range information if any. |
ModelMonitoringNotificationSpec
Notification spec(email, notification channel) for model monitoring statistics/alerts.
| Fields | |
|---|---|
email_config |
Email alert config. |
enable_cloud_logging |
Dump the anomalies to Cloud Logging. The anomalies will be put to json payload encoded from proto [google.cloud.aiplatform.logging.ModelMonitoringAnomaliesLogEntry][]. This can be further sinked to Pub/Sub or any other services supported by Cloud Logging. |
notification_channel_configs[] |
Notification channel config. |
EmailConfig
The config for email alerts.
| Fields | |
|---|---|
user_emails[] |
The email addresses to send the alerts. |
NotificationChannelConfig
Google Cloud Notification Channel config.
| Fields | |
|---|---|
notification_channel |
Resource names of the NotificationChannels. Must be of the format |
ModelMonitoringObjectiveConfig
The objective configuration for model monitoring, including the information needed to detect anomalies for one particular model.
| Fields | |
|---|---|
training_dataset |
Training dataset for models. This field has to be set only if TrainingPredictionSkewDetectionConfig is specified. |
training_prediction_skew_detection_config |
The config for skew between training data and prediction data. |
prediction_drift_detection_config |
The config for drift of prediction data. |
explanation_config |
The config for integrating with Vertex Explainable AI. |
ExplanationConfig
The config for integrating with Vertex Explainable AI. Only applicable if the Model has explanation_spec populated.
| Fields | |
|---|---|
enable_feature_attributes |
If want to analyze the Vertex Explainable AI feature attribute scores or not. If set to true, Vertex AI will log the feature attributions from explain response and do the skew/drift detection for them. |
explanation_baseline |
Predictions generated by the BatchPredictionJob using baseline dataset. |
ExplanationBaseline
Output from BatchPredictionJob for Model Monitoring baseline dataset, which can be used to generate baseline attribution scores.
| Fields | |
|---|---|
prediction_format |
The storage format of the predictions generated BatchPrediction job. |
Union field destination. The configuration specifying of BatchExplain job output. This can be used to generate the baseline of feature attribution scores. destination can be only one of the following: |
|
gcs |
Cloud Storage location for BatchExplain output. |
bigquery |
BigQuery location for BatchExplain output. |
PredictionFormat
The storage format of the predictions generated BatchPrediction job.
| Enums | |
|---|---|
PREDICTION_FORMAT_UNSPECIFIED |
Should not be set. |
JSONL |
Predictions are in JSONL files. |
BIGQUERY |
Predictions are in BigQuery. |
PredictionDriftDetectionConfig
The config for Prediction data drift detection.
| Fields | |
|---|---|
drift_thresholds |
Key is the feature name and value is the threshold. If a feature needs to be monitored for drift, a value threshold must be configured for that feature. The threshold here is against feature distribution distance between different time windws. |
attribution_score_drift_thresholds |
Key is the feature name and value is the threshold. The threshold here is against attribution score distance between different time windows. |
default_drift_threshold |
Drift anomaly detection threshold used by all features. When the per-feature thresholds are not set, this field can be used to specify a threshold for all features. |
TrainingDataset
Training Dataset information.
| Fields | |
|---|---|
data_format |
Data format of the dataset, only applicable if the input is from Google Cloud Storage. The possible formats are: "tf-record" The source file is a TFRecord file. "csv" The source file is a CSV file. "jsonl" The source file is a JSONL file. |
target_field |
The target field name the model is to predict. This field will be excluded when doing Predict and (or) Explain for the training data. |
logging_sampling_strategy |
Strategy to sample data from Training Dataset. If not set, we process the whole dataset. |
Union field
|
|
dataset |
The resource name of the Dataset used to train this Model. |
gcs_source |
The Google Cloud Storage uri of the unmanaged Dataset used to train this Model. |
bigquery_source |
The BigQuery table of the unmanaged Dataset used to train this Model. |
TrainingPredictionSkewDetectionConfig
The config for Training & Prediction data skew detection. It specifies the training dataset sources and the skew detection parameters.
| Fields | |
|---|---|
skew_thresholds |
Key is the feature name and value is the threshold. If a feature needs to be monitored for skew, a value threshold must be configured for that feature. The threshold here is against feature distribution distance between the training and prediction feature. |
attribution_score_skew_thresholds |
Key is the feature name and value is the threshold. The threshold here is against attribution score distance between the training and prediction feature. |
default_skew_threshold |
Skew anomaly detection threshold used by all features. When the per-feature thresholds are not set, this field can be used to specify a threshold for all features. |
ModelMonitoringObjectiveSpec
Monitoring objectives spec.
| Fields | |
|---|---|
explanation_spec |
The explanation spec. This spec is required when the objectives spec includes feature attribution objectives. |
baseline_dataset |
Baseline dataset. It could be the training dataset or production serving dataset from a previous period. |
target_dataset |
Target dataset. |
Union field objective. The monitoring objective. objective can be only one of the following: |
|
tabular_objective |
Tabular monitoring objective. |
DataDriftSpec
Data drift monitoring spec. Data drift measures the distribution distance between the current dataset and a baseline dataset. A typical use case is to detect data drift between the recent production serving dataset and the training dataset, or to compare the recent production dataset with a dataset from a previous period.
| Fields | |
|---|---|
features[] |
Feature names / Prediction output names interested in monitoring. These should be a subset of the input feature names or prediction output names specified in the monitoring schema. If the field is not specified all features / prediction outputs outlied in the monitoring schema will be used. |
categorical_metric_type |
Supported metrics type: * l_infinity * jensen_shannon_divergence |
numeric_metric_type |
Supported metrics type: * jensen_shannon_divergence |
default_categorical_alert_condition |
Default alert condition for all the categorical features. |
default_numeric_alert_condition |
Default alert condition for all the numeric features. |
feature_alert_conditions |
Per feature alert condition will override default alert condition. |
FeatureAttributionSpec
Feature attribution monitoring spec.
| Fields | |
|---|---|
features[] |
Feature names interested in monitoring. These should be a subset of the input feature names specified in the monitoring schema. If the field is not specified all features outlied in the monitoring schema will be used. |
default_alert_condition |
Default alert condition for all the features. |
feature_alert_conditions |
Per feature alert condition will override default alert condition. |
batch_explanation_dedicated_resources |
The config of resources used by the Model Monitoring during the batch explanation for non-AutoML models. If not set, |
TabularObjective
Tabular monitoring objective.
| Fields | |
|---|---|
feature_drift_spec |
Input feature distribution drift monitoring spec. |
prediction_output_drift_spec |
Prediction output distribution drift monitoring spec. |
feature_attribution_spec |
Feature attribution monitoring spec. |
ModelMonitoringOutputSpec
Specification for the export destination of monitoring results, including metrics, logs, etc.
| Fields | |
|---|---|
gcs_base_directory |
Google Cloud Storage base folder path for metrics, error logs, etc. |
ModelMonitoringSchema
The Model Monitoring Schema definition.
| Fields | |
|---|---|
feature_fields[] |
Feature names of the model. Vertex AI will try to match the features from your dataset as follows: * For 'csv' files, the header names are required, and we will extract the corresponding feature values when the header names align with the feature names. * For 'jsonl' files, we will extract the corresponding feature values if the key names match the feature names. Note: Nested features are not supported, so please ensure your features are flattened. Ensure the feature values are scalar or an array of scalars. * For 'bigquery' dataset, we will extract the corresponding feature values if the column names match the feature names. Note: The column type can be a scalar or an array of scalars. STRUCT or JSON types are not supported. You may use SQL queries to select or aggregate the relevant features from your original table. However, ensure that the 'schema' of the query results meets our requirements. * For the Vertex AI Endpoint Request Response Logging table or Vertex AI Batch Prediction Job results. If the |
prediction_fields[] |
Prediction output names of the model. The requirements are the same as the |
ground_truth_fields[] |
Target /ground truth names of the model. |
FieldSchema
Schema field definition.
| Fields | |
|---|---|
name |
Field name. |
data_type |
Supported data types are: |
repeated |
Describes if the schema field is an array of given data type. |
ModelMonitoringSpec
Monitoring monitoring job spec. It outlines the specifications for monitoring objectives, notifications, and result exports.
| Fields | |
|---|---|
objective_spec |
The monitoring objective spec. |
notification_spec |
The model monitoring notification spec. |
output_spec |
The Output destination spec for metrics, error logs, etc. |
ModelMonitoringStats
Represents the collection of statistics for a metric.
| Fields | |
|---|---|
Union field
|
|
tabular_stats |
Generated tabular statistics. |
ModelMonitoringStatsAnomalies
Statistics and anomalies generated by Model Monitoring.
| Fields | |
|---|---|
objective |
Model Monitoring Objective those stats and anomalies belonging to. |
deployed_model_id |
Deployed Model ID. |
anomaly_count |
Number of anomalies within all stats. |
feature_stats[] |
A list of historical Stats and Anomalies generated for all Features. |
FeatureHistoricStatsAnomalies
Historical Stats (and Anomalies) for a specific Feature.
| Fields | |
|---|---|
feature_display_name |
Display Name of the Feature. |
threshold |
Threshold for anomaly detection. |
training_stats |
Stats calculated for the Training Dataset. |
prediction_stats[] |
A list of historical stats generated by different time window's Prediction Dataset. |
ModelMonitoringStatsDataPoint
Represents a single statistics data point.
| Fields | |
|---|---|
current_stats |
Statistics from current dataset. |
baseline_stats |
Statistics from baseline dataset. |
threshold_value |
Threshold value. |
has_anomaly |
Indicate if the statistics has anomaly. |
model_monitoring_job |
Model monitoring job resource name. |
schedule |
Schedule resource name. |
create_time |
Statistics create time. |
algorithm |
Algorithm used to calculated the metrics, eg: jensen_shannon_divergence, l_infinity. |
TypedValue
Typed value of the statistics.
| Fields | |
|---|---|
Union field value. The typed value. value can be only one of the following: |
|
double_value |
Double. |
distribution_value |
Distribution. |
DistributionDataValue
Summary statistics for a population of values.
| Fields | |
|---|---|
distribution |
Predictive monitoring drift distribution in |
distribution_deviation |
Distribution distance deviation from the current dataset's statistics to baseline dataset's statistics. * For categorical feature, the distribution distance is calculated by L-inifinity norm or Jensen–Shannon divergence. * For numerical feature, the distribution distance is calculated by Jensen–Shannon divergence. |
ModelMonitoringTabularStats
A collection of data points that describes the time-varying values of a tabular metric.
| Fields | |
|---|---|
stats_name |
The stats name. |
objective_type |
One of the supported monitoring objectives: |
data_points[] |
The data points of this time series. When listing time series, points are returned in reverse time order. |
ModelSourceInfo
Detail description of the source information of the model.
| Fields | |
|---|---|
source_type |
Type of the model source. |
copy |
If this Model is copy of another Model. If true then |
ModelSourceType
Source of the model. Different from objective field, this ModelSourceType enum indicates the source from which the model was accessed or obtained, whereas the objective indicates the overall aim or function of this model.
| Enums | |
|---|---|
MODEL_SOURCE_TYPE_UNSPECIFIED |
Should not be used. |
AUTOML |
The Model is uploaded by automl training pipeline. |
CUSTOM |
The Model is uploaded by user or custom training pipeline. |
BQML |
The Model is registered and sync'ed from BigQuery ML. |
MODEL_GARDEN |
The Model is saved or tuned from Model Garden. |
GENIE |
The Model is saved or tuned from Genie. |
CUSTOM_TEXT_EMBEDDING |
The Model is uploaded by text embedding finetuning pipeline. |
MARKETPLACE |
The Model is saved or tuned from Marketplace. |
ModelVersionCheckpoint
Describes the machine learning model version checkpoint.
| Fields | |
|---|---|
name |
Identifier. The resource name of the ModelVersionCheckpoint. Format: |
checkpoint_id |
The ID of the checkpoint. |
epoch |
The epoch of the checkpoint. |
step |
The step of the checkpoint. |
MutateDeployedIndexOperationMetadata
Runtime operation information for IndexEndpointService.MutateDeployedIndex.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
deployed_index_id |
The unique index id specified by user |
MutateDeployedIndexRequest
Request message for IndexEndpointService.MutateDeployedIndex.
| Fields | |
|---|---|
index_endpoint |
Required. The name of the IndexEndpoint resource into which to deploy an Index. Format: |
deployed_index |
Required. The DeployedIndex to be updated within the IndexEndpoint. Currently, the updatable fields are |
MutateDeployedIndexResponse
Response message for IndexEndpointService.MutateDeployedIndex.
| Fields | |
|---|---|
deployed_index |
The DeployedIndex that had been updated in the IndexEndpoint. |
MutateDeployedModelOperationMetadata
Runtime operation information for EndpointService.MutateDeployedModel.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
MutateDeployedModelRequest
Request message for EndpointService.MutateDeployedModel.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint resource into which to mutate a DeployedModel. Format: |
deployed_model |
Required. The DeployedModel to be mutated within the Endpoint. Only the following fields can be mutated:
|
update_mask |
Required. The update mask applies to the resource. See |
MutateDeployedModelResponse
Response message for EndpointService.MutateDeployedModel.
| Fields | |
|---|---|
deployed_model |
The DeployedModel that's being mutated. |
NearestNeighborQuery
A query to find a number of similar entities.
| Fields | |
|---|---|
neighbor_count |
Optional. The number of similar entities to be retrieved from feature view for each query. |
string_filters[] |
Optional. The list of string filters. |
numeric_filters[] |
Optional. The list of numeric filters. |
per_crowding_attribute_neighbor_count |
Optional. Crowding is a constraint on a neighbor list produced by nearest neighbor search requiring that no more than sper_crowding_attribute_neighbor_count of the k neighbors returned have the same value of crowding_attribute. It's used for improving result diversity. |
parameters |
Optional. Parameters that can be set to tune query on the fly. |
Union field
|
|
entity_id |
Optional. The entity id whose similar entities should be searched for. If embedding is set, search will use embedding instead of entity_id. |
embedding |
Optional. The embedding vector that be used for similar search. |
Embedding
The embedding vector.
| Fields | |
|---|---|
value[] |
Optional. Individual value in the embedding. |
NumericFilter
Numeric filter is used to search a subset of the entities by using boolean rules on numeric columns. For example: Database Point 0: {name: "a" value_int: 42} {name: "b" value_float: 1.0} Database Point 1: {name: "a" value_int: 10} {name: "b" value_float: 2.0} Database Point 2: {name: "a" value_int: -1} {name: "b" value_float: 3.0} Query: {name: "a" value_int: 12 operator: LESS} // Matches Point 1, 2 {name: "b" value_float: 2.0 operator: EQUAL} // Matches Point 1
| Fields | |
|---|---|
name |
Required. Column name in BigQuery that used as filters. |
Union field Value. The type of Value must be consistent for all datapoints with a given name. This is verified at runtime. Value can be only one of the following: |
|
value_int |
int value type. |
value_float |
float value type. |
value_double |
double value type. |
op |
Optional. This MUST be specified for queries and must NOT be specified for database points. |
Operator
Datapoints for which Operator is true relative to the query's Value field will be allowlisted.
| Enums | |
|---|---|
OPERATOR_UNSPECIFIED |
Unspecified operator. |
LESS |
Entities are eligible if their value is < the query's. |
LESS_EQUAL |
Entities are eligible if their value is <= the query's. |
EQUAL |
Entities are eligible if their value is == the query's. |
GREATER_EQUAL |
Entities are eligible if their value is >= the query's. |
GREATER |
Entities are eligible if their value is > the query's. |
NOT_EQUAL |
Entities are eligible if their value is != the query's. |
Parameters
Parameters that can be overrided in each query to tune query latency and recall.
| Fields | |
|---|---|
approximate_neighbor_candidates |
Optional. The number of neighbors to find via approximate search before exact reordering is performed; if set, this value must be > neighbor_count. |
leaf_nodes_search_fraction |
Optional. The fraction of the number of leaves to search, set at query time allows user to tune search performance. This value increase result in both search accuracy and latency increase. The value should be between 0.0 and 1.0. |
StringFilter
String filter is used to search a subset of the entities by using boolean rules on string columns. For example: if a query specifies string filter with 'name = color, allow_tokens = {red, blue}, deny_tokens = {purple}',' then that query will match entities that are red or blue, but if those points are also purple, then they will be excluded even if they are red/blue. Only string filter is supported for now, numeric filter will be supported in the near future.
| Fields | |
|---|---|
name |
Required. Column names in BigQuery that used as filters. |
allow_tokens[] |
Optional. The allowed tokens. |
deny_tokens[] |
Optional. The denied tokens. |
NearestNeighborSearchOperationMetadata
Runtime operation metadata with regard to Matching Engine Index.
| Fields | |
|---|---|
content_validation_stats[] |
The validation stats of the content (per file) to be inserted or updated on the Matching Engine Index resource. Populated if contentsDeltaUri is provided as part of |
data_bytes_count |
The ingested data size in bytes. |
ContentValidationStats
| Fields | |
|---|---|
source_gcs_uri |
Cloud Storage URI pointing to the original file in user's bucket. |
valid_record_count |
Number of records in this file that were successfully processed. |
invalid_record_count |
Number of records in this file we skipped due to validate errors. |
partial_errors[] |
The detail information of the partial failures encountered for those invalid records that couldn't be parsed. Up to 50 partial errors will be reported. |
valid_sparse_record_count |
Number of sparse records in this file that were successfully processed. |
invalid_sparse_record_count |
Number of sparse records in this file we skipped due to validate errors. |
RecordError
| Fields | |
|---|---|
error_type |
The error type of this record. |
error_message |
A human-readable message that is shown to the user to help them fix the error. Note that this message may change from time to time, your code should check against error_type as the source of truth. |
source_gcs_uri |
Cloud Storage URI pointing to the original file in user's bucket. |
embedding_id |
Empty if the embedding id is failed to parse. |
raw_record |
The original content of this record. |
RecordErrorType
| Enums | |
|---|---|
ERROR_TYPE_UNSPECIFIED |
Default, shall not be used. |
EMPTY_LINE |
The record is empty. |
INVALID_JSON_SYNTAX |
Invalid json format. |
INVALID_CSV_SYNTAX |
Invalid csv format. |
INVALID_AVRO_SYNTAX |
Invalid avro format. |
INVALID_EMBEDDING_ID |
The embedding id is not valid. |
EMBEDDING_SIZE_MISMATCH |
The size of the dense embedding vectors does not match with the specified dimension. |
NAMESPACE_MISSING |
The namespace field is missing. |
PARSING_ERROR |
Generic catch-all error. Only used for validation failure where the root cause cannot be easily retrieved programmatically. |
DUPLICATE_NAMESPACE |
There are multiple restricts with the same namespace value. |
OP_IN_DATAPOINT |
Numeric restrict has operator specified in datapoint. |
MULTIPLE_VALUES |
Numeric restrict has multiple values specified. |
INVALID_NUMERIC_VALUE |
Numeric restrict has invalid numeric value specified. |
INVALID_ENCODING |
File is not in UTF_8 format. |
INVALID_SPARSE_DIMENSIONS |
Error parsing sparse dimensions field. |
INVALID_TOKEN_VALUE |
Token restrict value is invalid. |
INVALID_SPARSE_EMBEDDING |
Invalid sparse embedding. |
INVALID_EMBEDDING |
Invalid dense embedding. |
NearestNeighbors
Nearest neighbors for one query.
| Fields | |
|---|---|
neighbors[] |
All its neighbors. |
Neighbor
A neighbor of the query vector.
| Fields | |
|---|---|
entity_id |
The id of the similar entity. |
distance |
The distance between the neighbor and the query vector. |
entity_key_values |
The attributes of the neighbor, e.g. filters, crowding and metadata Note that full entities are returned only when "return_full_entity" is set to true. Otherwise, only the "entity_id" and "distance" fields are populated. |
Neighbor
Neighbors for example-based explanations.
| Fields | |
|---|---|
neighbor_id |
Output only. The neighbor id. |
neighbor_distance |
Output only. The neighbor distance. |
NetworkSpec
Network spec.
| Fields | |
|---|---|
enable_internet_access |
Whether to enable public internet access. Default false. |
network |
The full name of the Google Compute Engine network |
subnetwork |
The name of the subnet that this instance is in. Format: |
NfsMount
Represents a mount configuration for Network File System (NFS) to mount.
| Fields | |
|---|---|
server |
Required. IP address of the NFS server. |
path |
Required. Source path exported from NFS server. Has to start with '/', and combined with the ip address, it indicates the source mount path in the form of |
mount_point |
Required. Destination mount path. The NFS will be mounted for the user under /mnt/nfs/ |
NotebookEucConfig
The euc configuration of NotebookRuntimeTemplate.
| Fields | |
|---|---|
euc_disabled |
Input only. Whether EUC is disabled in this NotebookRuntimeTemplate. In proto3, the default value of a boolean is false. In this way, by default EUC will be enabled for NotebookRuntimeTemplate. |
bypass_actas_check |
Output only. Whether ActAs check is bypassed for service account attached to the VM. If false, we need ActAs check for the default Compute Engine Service account. When a Runtime is created, a VM is allocated using Default Compute Engine Service Account. Any user requesting to use this Runtime requires Service Account User (ActAs) permission over this SA. If true, Runtime owner is using EUC and does not require the above permission as VM no longer use default Compute Engine SA, but a P4SA. |
NotebookExecutionJob
NotebookExecutionJob represents an instance of a notebook execution.
| Fields | |
|---|---|
name |
Output only. The resource name of this NotebookExecutionJob. Format: |
display_name |
The display name of the NotebookExecutionJob. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
execution_timeout |
Max running time of the execution job in seconds (default 86400s / 24 hrs). |
schedule_resource_name |
The Schedule resource name if this job is triggered by one. Format: |
job_state |
Output only. The state of the NotebookExecutionJob. |
status |
Output only. Populated when the NotebookExecutionJob is completed. When there is an error during notebook execution, the error details are populated. |
create_time |
Output only. Timestamp when this NotebookExecutionJob was created. |
update_time |
Output only. Timestamp when this NotebookExecutionJob was most recently updated. |
labels |
The labels with user-defined metadata to organize NotebookExecutionJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
kernel_name |
The name of the kernel to use during notebook execution. If unset, the default kernel is used. |
encryption_spec |
Customer-managed encryption key spec for the notebook execution job. This field is auto-populated if the |
Union field notebook_source. The input notebook. notebook_source can be only one of the following: |
|
dataform_repository_source |
The Dataform Repository pointing to a single file notebook repository. |
gcs_notebook_source |
The Cloud Storage url pointing to the ipynb file. Format: |
direct_notebook_source |
The contents of an input notebook file. |
Union field environment_spec. The compute config to use for an execution job. environment_spec can be only one of the following: |
|
notebook_runtime_template_resource_name |
The NotebookRuntimeTemplate to source compute configuration from. |
custom_environment_spec |
The custom compute configuration for an execution job. |
Union field execution_sink. The location to store the notebook execution result. execution_sink can be only one of the following: |
|
gcs_output_uri |
The Cloud Storage location to upload the result to. Format: |
Union field execution_identity. The identity to run the execution as. execution_identity can be only one of the following: |
|
execution_user |
The user email to run the execution as. Only supported by Colab runtimes. |
service_account |
The service account to run the execution as. |
Union field runtime_environment. Runtime environment for the notebook execution job. If unspecified, the default runtime of Colab is used. runtime_environment can be only one of the following: |
|
workbench_runtime |
The Workbench runtime configuration to use for the notebook execution. |
CustomEnvironmentSpec
Compute configuration to use for an execution job.
| Fields | |
|---|---|
machine_spec |
The specification of a single machine for the execution job. |
persistent_disk_spec |
The specification of a persistent disk to attach for the execution job. |
network_spec |
The network configuration to use for the execution job. |
DataformRepositorySource
The Dataform Repository containing the input notebook.
| Fields | |
|---|---|
dataform_repository_resource_name |
The resource name of the Dataform Repository. Format: |
commit_sha |
The commit SHA to read repository with. If unset, the file will be read at HEAD. |
DirectNotebookSource
The content of the input notebook in ipynb format.
| Fields | |
|---|---|
content |
The base64-encoded contents of the input notebook file. |
GcsNotebookSource
The Cloud Storage uri for the input notebook.
| Fields | |
|---|---|
uri |
The Cloud Storage uri pointing to the ipynb file. Format: |
generation |
The version of the Cloud Storage object to read. If unset, the current version of the object is read. See https://cloud.google.com/storage/docs/metadata#generation-number. |
WorkbenchRuntime
This type has no fields.
Configuration for a Workbench Instances-based environment.
NotebookExecutionJobView
Views for Get/List NotebookExecutionJob
| Enums | |
|---|---|
NOTEBOOK_EXECUTION_JOB_VIEW_UNSPECIFIED |
When unspecified, the API defaults to the BASIC view. |
NOTEBOOK_EXECUTION_JOB_VIEW_BASIC |
Includes all fields except for direct notebook inputs. |
NOTEBOOK_EXECUTION_JOB_VIEW_FULL |
Includes all fields. |
NotebookIdleShutdownConfig
The idle shutdown configuration of NotebookRuntimeTemplate, which contains the idle_timeout as required field.
| Fields | |
|---|---|
idle_timeout |
Required. Duration is accurate to the second. In Notebook, Idle Timeout is accurate to minute so the range of idle_timeout (second) is: 10 * 60 ~ 1440 * 60. |
idle_shutdown_disabled |
Whether Idle Shutdown is disabled in this NotebookRuntimeTemplate. |
NotebookRuntime
A runtime is a virtual machine allocated to a particular user for a particular Notebook file on temporary basis with lifetime limited to 24 hours.
| Fields | |
|---|---|
name |
Output only. The resource name of the NotebookRuntime. |
runtime_user |
Required. The user email of the NotebookRuntime. |
notebook_runtime_template_ref |
Output only. The pointer to NotebookRuntimeTemplate this NotebookRuntime is created from. |
proxy_uri |
Output only. The proxy endpoint used to access the NotebookRuntime. |
create_time |
Output only. Timestamp when this NotebookRuntime was created. |
update_time |
Output only. Timestamp when this NotebookRuntime was most recently updated. |
health_state |
Output only. The health state of the NotebookRuntime. |
display_name |
Required. The display name of the NotebookRuntime. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
description |
The description of the NotebookRuntime. |
service_account |
Output only. Deprecated: This field is no longer used and the "Vertex AI Notebook Service Account" (service-PROJECT_NUMBER@gcp-sa-aiplatform-vm.iam.gserviceaccount.com) is used for the runtime workload identity. See https://cloud.google.com/iam/docs/service-agents#vertex-ai-notebook-service-account for more details. The service account that the NotebookRuntime workload runs as. |
runtime_state |
Output only. The runtime (instance) state of the NotebookRuntime. |
is_upgradable |
Output only. Whether NotebookRuntime is upgradable. |
labels |
The labels with user-defined metadata to organize your NotebookRuntime. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one NotebookRuntime (System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. Following system labels exist for NotebookRuntime:
|
expiration_time |
Output only. Timestamp when this NotebookRuntime will be expired: 1. System Predefined NotebookRuntime: 24 hours after creation. After expiration, system predifined runtime will be deleted. 2. User created NotebookRuntime: 6 months after last upgrade. After expiration, user created runtime will be stopped and allowed for upgrade. |
version |
Output only. The VM os image version of NotebookRuntime. |
notebook_runtime_type |
Output only. The type of the notebook runtime. |
machine_spec |
Output only. The specification of a single machine used by the notebook runtime. |
data_persistent_disk_spec |
Output only. The specification of [persistent disk][https://cloud.google.com/compute/docs/disks/persistent-disks] attached to the notebook runtime as data disk storage. |
network_spec |
Output only. Network spec of the notebook runtime. |
idle_shutdown_config |
Output only. The idle shutdown configuration of the notebook runtime. |
euc_config |
Output only. EUC configuration of the notebook runtime. |
shielded_vm_config |
Output only. Runtime Shielded VM spec. |
network_tags[] |
Optional. The Compute Engine tags to add to runtime (see Tagging instances). |
software_config |
Output only. Software config of the notebook runtime. |
encryption_spec |
Output only. Customer-managed encryption key spec for the notebook runtime. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
HealthState
The substate of the NotebookRuntime to display health information.
| Enums | |
|---|---|
HEALTH_STATE_UNSPECIFIED |
Unspecified health state. |
HEALTHY |
NotebookRuntime is in healthy state. Applies to ACTIVE state. |
UNHEALTHY |
NotebookRuntime is in unhealthy state. Applies to ACTIVE state. |
RuntimeState
The substate of the NotebookRuntime to display state of runtime. The resource of NotebookRuntime is in ACTIVE state for these sub state.
| Enums | |
|---|---|
RUNTIME_STATE_UNSPECIFIED |
Unspecified runtime state. |
RUNNING |
NotebookRuntime is in running state. |
BEING_STARTED |
NotebookRuntime is in starting state. |
BEING_STOPPED |
NotebookRuntime is in stopping state. |
STOPPED |
NotebookRuntime is in stopped state. |
BEING_UPGRADED |
NotebookRuntime is in upgrading state. It is in the middle of upgrading process. |
ERROR |
NotebookRuntime was unable to start/stop properly. |
INVALID |
NotebookRuntime is in invalid state. Cannot be recovered. |
NotebookRuntimeTemplate
A template that specifies runtime configurations such as machine type, runtime version, network configurations, etc. Multiple runtimes can be created from a runtime template.
| Fields | |
|---|---|
name |
The resource name of the NotebookRuntimeTemplate. |
display_name |
Required. The display name of the NotebookRuntimeTemplate. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
description |
The description of the NotebookRuntimeTemplate. |
is_default |
Output only. Deprecated: This field has no behavior. Use notebook_runtime_type = 'ONE_CLICK' instead. The default template to use if not specified. |
machine_spec |
Optional. Immutable. The specification of a single machine for the template. |
data_persistent_disk_spec |
Optional. The specification of [persistent disk][https://cloud.google.com/compute/docs/disks/persistent-disks] attached to the runtime as data disk storage. |
network_spec |
Optional. Network spec. |
service_account |
Deprecated: This field is ignored and the "Vertex AI Notebook Service Account" (service-PROJECT_NUMBER@gcp-sa-aiplatform-vm.iam.gserviceaccount.com) is used for the runtime workload identity. See https://cloud.google.com/iam/docs/service-agents#vertex-ai-notebook-service-account for more details. For NotebookExecutionJob, use NotebookExecutionJob.service_account instead. The service account that the runtime workload runs as. You can use any service account within the same project, but you must have the service account user permission to use the instance. If not specified, the Compute Engine default service account is used. |
etag |
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
labels |
The labels with user-defined metadata to organize the NotebookRuntimeTemplates. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
idle_shutdown_config |
The idle shutdown configuration of NotebookRuntimeTemplate. This config will only be set when idle shutdown is enabled. |
euc_config |
EUC configuration of the NotebookRuntimeTemplate. |
create_time |
Output only. Timestamp when this NotebookRuntimeTemplate was created. |
update_time |
Output only. Timestamp when this NotebookRuntimeTemplate was most recently updated. |
notebook_runtime_type |
Optional. Immutable. The type of the notebook runtime template. |
shielded_vm_config |
Optional. Immutable. Runtime Shielded VM spec. |
network_tags[] |
Optional. The Compute Engine tags to add to runtime (see Tagging instances). |
encryption_spec |
Customer-managed encryption key spec for the notebook runtime. |
software_config |
Optional. The notebook software configuration of the notebook runtime. |
NotebookRuntimeTemplateRef
Points to a NotebookRuntimeTemplateRef.
| Fields | |
|---|---|
notebook_runtime_template |
Immutable. A resource name of the NotebookRuntimeTemplate. |
NotebookRuntimeType
Represents a notebook runtime type.
| Enums | |
|---|---|
NOTEBOOK_RUNTIME_TYPE_UNSPECIFIED |
Unspecified notebook runtime type, NotebookRuntimeType will default to USER_DEFINED. |
USER_DEFINED |
runtime or template with coustomized configurations from user. |
ONE_CLICK |
runtime or template with system defined configurations. |
NotebookSoftwareConfig
Notebook Software Config.
| Fields | |
|---|---|
env[] |
Optional. Environment variables to be passed to the container. Maximum limit is 100. |
post_startup_script_config |
Optional. Post startup script config. |
OutputConfig
Config for evaluation output.
| Fields | |
|---|---|
Union field destination. The destination for evaluation output. destination can be only one of the following: |
|
gcs_destination |
Cloud storage destination for evaluation output. |
OutputInfo
Describes the info for output of EvaluationService.EvaluateDataset.
| Fields | |
|---|---|
Union field output_location. The output location into which evaluation output is written. output_location can be only one of the following: |
|
gcs_output_directory |
Output only. The full path of the Cloud Storage directory created, into which the evaluation results and aggregation results are written. |
PSCAutomationConfig
PSC config that is used to automatically create forwarding rule via ServiceConnectionMap.
| Fields | |
|---|---|
project_id |
Required. Project id used to create forwarding rule. |
network |
Required. The full name of the Google Compute Engine network. Format: |
PairwiseChoice
Pairwise prediction autorater preference.
| Enums | |
|---|---|
PAIRWISE_CHOICE_UNSPECIFIED |
Unspecified prediction choice. |
BASELINE |
Baseline prediction wins |
CANDIDATE |
Candidate prediction wins |
TIE |
Winner cannot be determined |
PairwiseMetricInput
Input for pairwise metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for pairwise metric. |
instance |
Required. Pairwise metric instance. |
PairwiseMetricInstance
Pairwise metric instance. Usually one instance corresponds to one row in an evaluation dataset.
| Fields | |
|---|---|
Union field instance. Instance for pairwise metric. instance can be only one of the following: |
|
json_instance |
Instance specified as a json string. String key-value pairs are expected in the json_instance to render PairwiseMetricSpec.instance_prompt_template. |
PairwiseMetricResult
Spec for pairwise metric result.
| Fields | |
|---|---|
pairwise_choice |
Output only. Pairwise metric choice. |
explanation |
Output only. Explanation for pairwise metric score. |
PairwiseMetricSpec
Spec for pairwise metric.
| Fields | |
|---|---|
candidate_response_field_name |
Optional. The field name of the candidate response. |
baseline_response_field_name |
Optional. The field name of the baseline response. |
metric_prompt_template |
Required. Metric prompt template for pairwise metric. |
system_instruction |
Optional. System instructions for pairwise metric. |
PairwiseQuestionAnsweringQualityInput
Input for pairwise question answering quality metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for pairwise question answering quality score metric. |
instance |
Required. Pairwise question answering quality instance. |
PairwiseQuestionAnsweringQualityInstance
Spec for pairwise question answering quality instance.
| Fields | |
|---|---|
prediction |
Required. Output of the candidate model. |
baseline_prediction |
Required. Output of the baseline model. |
reference |
Optional. Ground truth used to compare against the prediction. |
context |
Required. Text to answer the question. |
instruction |
Required. Question Answering prompt for LLM. |
PairwiseQuestionAnsweringQualityResult
Spec for pairwise question answering quality result.
| Fields | |
|---|---|
pairwise_choice |
Output only. Pairwise question answering prediction choice. |
explanation |
Output only. Explanation for question answering quality score. |
confidence |
Output only. Confidence for question answering quality score. |
PairwiseQuestionAnsweringQualitySpec
Spec for pairwise question answering quality score metric.
| Fields | |
|---|---|
use_reference |
Optional. Whether to use instance.reference to compute question answering quality. |
version |
Optional. Which version to use for evaluation. |
PairwiseSummarizationQualityInput
Input for pairwise summarization quality metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for pairwise summarization quality score metric. |
instance |
Required. Pairwise summarization quality instance. |
PairwiseSummarizationQualityInstance
Spec for pairwise summarization quality instance.
| Fields | |
|---|---|
prediction |
Required. Output of the candidate model. |
baseline_prediction |
Required. Output of the baseline model. |
reference |
Optional. Ground truth used to compare against the prediction. |
context |
Required. Text to be summarized. |
instruction |
Required. Summarization prompt for LLM. |
PairwiseSummarizationQualityResult
Spec for pairwise summarization quality result.
| Fields | |
|---|---|
pairwise_choice |
Output only. Pairwise summarization prediction choice. |
explanation |
Output only. Explanation for summarization quality score. |
confidence |
Output only. Confidence for summarization quality score. |
PairwiseSummarizationQualitySpec
Spec for pairwise summarization quality score metric.
| Fields | |
|---|---|
use_reference |
Optional. Whether to use instance.reference to compute pairwise summarization quality. |
version |
Optional. Which version to use for evaluation. |
Part
A datatype containing media that is part of a multi-part Content message.
A Part consists of data which has an associated datatype. A Part can only contain one of the accepted types in Part.data.
A Part must have a fixed IANA MIME type identifying the type and subtype of the media if inline_data or file_data field is filled with raw bytes.
| Fields | |
|---|---|
thought |
Output only. Indicates if the part is thought from the model. |
Union field
|
|
text |
Optional. Text part (can be code). |
inline_data |
Optional. Inlined bytes data. |
file_data |
Optional. URI based data. |
function_call |
Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values. |
function_response |
Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model. |
executable_code |
Optional. Code generated by the model that is meant to be executed. |
code_execution_result |
Optional. Result of executing the [ExecutableCode]. |
Union field
|
|
video_metadata |
Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data. |
PartnerModelTuningSpec
Tuning spec for Partner models.
| Fields | |
|---|---|
training_dataset_uri |
Required. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file. |
validation_dataset_uri |
Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file. |
hyper_parameters |
Hyperparameters for tuning. The accepted hyper_parameters and their valid range of values will differ depending on the base model. |
PauseModelDeploymentMonitoringJobRequest
Request message for JobService.PauseModelDeploymentMonitoringJob.
| Fields | |
|---|---|
name |
Required. The resource name of the ModelDeploymentMonitoringJob to pause. Format: |
PauseScheduleRequest
Request message for ScheduleService.PauseSchedule.
| Fields | |
|---|---|
name |
Required. The name of the Schedule resource to be paused. Format: |
PersistentDiskSpec
Represents the spec of [persistent disk][https://cloud.google.com/compute/docs/disks/persistent-disks] options.
| Fields | |
|---|---|
disk_type |
Type of the disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) "pd-standard" (Persistent Disk Hard Disk Drive) "pd-balanced" (Balanced Persistent Disk) "pd-extreme" (Extreme Persistent Disk) |
disk_size_gb |
Size in GB of the disk (default is 100GB). |
PersistentResource
Represents long-lasting resources that are dedicated to users to runs custom workloads. A PersistentResource can have multiple node pools and each node pool can have its own machine spec.
| Fields | |
|---|---|
name |
Immutable. Resource name of a PersistentResource. |
display_name |
Optional. The display name of the PersistentResource. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
resource_pools[] |
Required. The spec of the pools of different resources. |
state |
Output only. The detailed state of a Study. |
error |
Output only. Only populated when persistent resource's state is |
create_time |
Output only. Time when the PersistentResource was created. |
start_time |
Output only. Time when the PersistentResource for the first time entered the |
update_time |
Output only. Time when the PersistentResource was most recently updated. |
labels |
Optional. The labels with user-defined metadata to organize PersistentResource. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
network |
Optional. The full name of the Compute Engine network to peered with Vertex AI to host the persistent resources. For example, To specify this field, you must have already configured VPC Network Peering for Vertex AI. If this field is left unspecified, the resources aren't peered with any network. |
psc_interface_config |
Optional. Configuration for PSC-I for PersistentResource. |
encryption_spec |
Optional. Customer-managed encryption key spec for a PersistentResource. If set, this PersistentResource and all sub-resources of this PersistentResource will be secured by this key. |
resource_runtime_spec |
Optional. Persistent Resource runtime spec. For example, used for Ray cluster configuration. |
resource_runtime |
Output only. Runtime information of the Persistent Resource. |
reserved_ip_ranges[] |
Optional. A list of names for the reserved IP ranges under the VPC network that can be used for this persistent resource. If set, we will deploy the persistent resource within the provided IP ranges. Otherwise, the persistent resource is deployed to any IP ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
State
Describes the PersistentResource state.
| Enums | |
|---|---|
STATE_UNSPECIFIED |
Not set. |
PROVISIONING |
The PROVISIONING state indicates the persistent resources is being created. |
RUNNING |
The RUNNING state indicates the persistent resource is healthy and fully usable. |
STOPPING |
The STOPPING state indicates the persistent resource is being deleted. |
ERROR |
The ERROR state indicates the persistent resource may be unusable. Details can be found in the error field. |
REBOOTING |
The REBOOTING state indicates the persistent resource is being rebooted (PR is not available right now but is expected to be ready again later). |
UPDATING |
The UPDATING state indicates the persistent resource is being updated. |
PipelineFailurePolicy
Represents the failure policy of a pipeline. Currently, the default of a pipeline is that the pipeline will continue to run until no more tasks can be executed, also known as PIPELINE_FAILURE_POLICY_FAIL_SLOW. However, if a pipeline is set to PIPELINE_FAILURE_POLICY_FAIL_FAST, it will stop scheduling any new tasks when a task has failed. Any scheduled tasks will continue to completion.
| Enums | |
|---|---|
PIPELINE_FAILURE_POLICY_UNSPECIFIED |
Default value, and follows fail slow behavior. |
PIPELINE_FAILURE_POLICY_FAIL_SLOW |
Indicates that the pipeline should continue to run until all possible tasks have been scheduled and completed. |
PIPELINE_FAILURE_POLICY_FAIL_FAST |
Indicates that the pipeline should stop scheduling new tasks after a task has failed. |
PipelineJob
An instance of a machine learning PipelineJob.
| Fields | |
|---|---|
name |
Output only. The resource name of the PipelineJob. |
display_name |
The display name of the Pipeline. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
create_time |
Output only. Pipeline creation time. |
start_time |
Output only. Pipeline start time. |
end_time |
Output only. Pipeline end time. |
update_time |
Output only. Timestamp when this PipelineJob was most recently updated. |
pipeline_spec |
The spec of the pipeline. |
state |
Output only. The detailed state of the job. |
job_detail |
Output only. The details of pipeline run. Not available in the list view. |
error |
Output only. The error that occurred during pipeline execution. Only populated when the pipeline's state is FAILED or CANCELLED. |
labels |
The labels with user-defined metadata to organize PipelineJob. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. Note there is some reserved label key for Vertex AI Pipelines. - |
runtime_config |
Runtime config of the pipeline. |
encryption_spec |
Customer-managed encryption key spec for a pipelineJob. If set, this PipelineJob and all of its sub-resources will be secured by this key. |
service_account |
The service account that the pipeline workload runs as. If not specified, the Compute Engine default service account in the project will be used. See https://cloud.google.com/compute/docs/access/service-accounts#default_service_account Users starting the pipeline must have the |
network |
The full name of the Compute Engine network to which the Pipeline Job's workload should be peered. For example, Private services access must already be configured for the network. Pipeline job will apply the network configuration to the Google Cloud resources being launched, if applied, such as Vertex AI Training or Dataflow job. If left unspecified, the workload is not peered with any network. |
reserved_ip_ranges[] |
A list of names for the reserved ip ranges under the VPC network that can be used for this Pipeline Job's workload. If set, we will deploy the Pipeline Job's workload within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. |
psc_interface_config |
Optional. Configuration for PSC-I for PipelineJob. |
template_uri |
A template uri from where the |
template_metadata |
Output only. Pipeline template metadata. Will fill up fields if |
schedule_name |
Output only. The schedule resource name. Only returned if the Pipeline is created by Schedule API. |
preflight_validations |
Optional. Whether to do component level validations before job creation. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
original_pipeline_job_id |
Optional. The original pipeline job id if this pipeline job is a rerun of a previous pipeline job. |
pipeline_task_rerun_configs[] |
Optional. The rerun configs for each task in the pipeline job. By default, the rerun will: 1. Use the same input artifacts as the original run. 2. Use the same input parameters as the original run. 3. Skip all the tasks that are already succeeded in the original run. 4. Rerun all the tasks that are not succeeded in the original run. By providing this field, users can override the default behavior and specify the rerun config for each task. |
RuntimeConfig
The runtime config of a PipelineJob.
| Fields | |
|---|---|
parameters |
Deprecated. Use |
gcs_output_directory |
Required. A path in a Cloud Storage bucket, which will be treated as the root output directory of the pipeline. It is used by the system to generate the paths of output artifacts. The artifact paths are generated with a sub-path pattern |
parameter_values |
The runtime parameters of the PipelineJob. The parameters will be passed into |
failure_policy |
Represents the failure policy of a pipeline. Currently, the default of a pipeline is that the pipeline will continue to run until no more tasks can be executed, also known as PIPELINE_FAILURE_POLICY_FAIL_SLOW. However, if a pipeline is set to PIPELINE_FAILURE_POLICY_FAIL_FAST, it will stop scheduling any new tasks when a task has failed. Any scheduled tasks will continue to completion. |
input_artifacts |
The runtime artifacts of the PipelineJob. The key will be the input artifact name and the value would be one of the InputArtifact. |
default_runtime |
Optional. The default runtime for the PipelineJob. If not set, Standard Vertex Custom Job(https://cloud.google.com/vertex-ai/docs/training/overview) is used as the runtime. If set, all pipeline tasks will run on the default runtime unless a task is a GCPC custom job component (https://cloud.google.com/vertex-ai/docs/pipelines/customjob-component) based task. If the task is based on a GCPC custom job component, it runs solely according to the component's configuration. |
DefaultRuntime
The default runtime for the PipelineJob.
| Fields | |
|---|---|
Union field
|
|
persistent_resource_runtime_detail |
Persistent resource based runtime detail. |
InputArtifact
The type of an input artifact.
| Fields | |
|---|---|
Union field
|
|
artifact_id |
Artifact resource id from MLMD. Which is the last portion of an artifact resource name: |
PersistentResourceRuntimeDetail
Persistent resource based runtime detail. For more information about persistent resource, refer to https://cloud.google.com/vertex-ai/docs/training/persistent-resource-overview
| Fields | |
|---|---|
persistent_resource_name |
Persistent resource name. Format: |
task_resource_unavailable_wait_time_ms |
The max time a pipeline task waits for the required CPU, memory, or accelerator resource to become available from the specified persistent resource. Default wait time is 0. |
task_resource_unavailable_timeout_behavior |
Specifies the behavior to take if the timeout is reached. |
PipelineJobDetail
The runtime detail of PipelineJob.
| Fields | |
|---|---|
pipeline_context |
Output only. The context of the pipeline. |
pipeline_run_context |
Output only. The context of the current pipeline run. |
task_details[] |
Output only. The runtime details of the tasks under the pipeline. |
PipelineState
Describes the state of a pipeline.
| Enums | |
|---|---|
PIPELINE_STATE_UNSPECIFIED |
The pipeline state is unspecified. |
PIPELINE_STATE_QUEUED |
The pipeline has been created or resumed, and processing has not yet begun. |
PIPELINE_STATE_PENDING |
The service is preparing to run the pipeline. |
PIPELINE_STATE_RUNNING |
The pipeline is in progress. |
PIPELINE_STATE_SUCCEEDED |
The pipeline completed successfully. |
PIPELINE_STATE_FAILED |
The pipeline failed. |
PIPELINE_STATE_CANCELLING |
The pipeline is being cancelled. From this state, the pipeline may only go to either PIPELINE_STATE_SUCCEEDED, PIPELINE_STATE_FAILED or PIPELINE_STATE_CANCELLED. |
PIPELINE_STATE_CANCELLED |
The pipeline has been cancelled. |
PIPELINE_STATE_PAUSED |
The pipeline has been stopped, and can be resumed. |
PipelineTaskDetail
The runtime detail of a task execution.
| Fields | |
|---|---|
task_id |
Output only. The system generated ID of the task. |
parent_task_id |
Output only. The id of the parent task if the task is within a component scope. Empty if the task is at the root level. |
task_name |
Output only. The user specified name of the task that is defined in |
create_time |
Output only. Task create time. |
start_time |
Output only. Task start time. |
end_time |
Output only. Task end time. |
executor_detail |
Output only. The detailed execution info. |
state |
Output only. State of the task. |
execution |
Output only. The execution metadata of the task. |
error |
Output only. The error that occurred during task execution. Only populated when the task's state is FAILED or CANCELLED. |
pipeline_task_status[] |
Output only. A list of task status. This field keeps a record of task status evolving over time. |
inputs |
Output only. The runtime input artifacts of the task. |
outputs |
Output only. The runtime output artifacts of the task. |
ArtifactList
A list of artifact metadata.
| Fields | |
|---|---|
artifacts[] |
Output only. A list of artifact metadata. |
PipelineTaskStatus
A single record of the task status.
| Fields | |
|---|---|
update_time |
Output only. Update time of this status. |
state |
Output only. The state of the task. |
error |
Output only. The error that occurred during the state. May be set when the state is any of the non-final state (PENDING/RUNNING/CANCELLING) or FAILED state. If the state is FAILED, the error here is final and not going to be retried. If the state is a non-final state, the error indicates a system-error being retried. |
State
Specifies state of TaskExecution
| Enums | |
|---|---|
STATE_UNSPECIFIED |
Unspecified. |
PENDING |
Specifies pending state for the task. |
RUNNING |
Specifies task is being executed. |
SUCCEEDED |
Specifies task completed successfully. |
CANCEL_PENDING |
Specifies Task cancel is in pending state. |
CANCELLING |
Specifies task is being cancelled. |
CANCELLED |
Specifies task was cancelled. |
FAILED |
Specifies task failed. |
SKIPPED |
Specifies task was skipped due to cache hit. |
NOT_TRIGGERED |
Specifies that the task was not triggered because the task's trigger policy is not satisfied. The trigger policy is specified in the condition field of PipelineJob.pipeline_spec. |
PipelineTaskExecutorDetail
The runtime detail of a pipeline executor.
| Fields | |
|---|---|
Union field
|
|
container_detail |
Output only. The detailed info for a container executor. |
custom_job_detail |
Output only. The detailed info for a custom job executor. |
ContainerDetail
The detail of a container execution. It contains the job names of the lifecycle of a container execution.
| Fields | |
|---|---|
main_job |
Output only. The name of the |
pre_caching_check_job |
Output only. The name of the |
failed_main_jobs[] |
Output only. The names of the previously failed |
failed_pre_caching_check_jobs[] |
Output only. The names of the previously failed |
CustomJobDetail
The detailed info for a custom job executor.
| Fields | |
|---|---|
job |
Output only. The name of the |
failed_jobs[] |
Output only. The names of the previously failed |
PipelineTaskRerunConfig
User provided rerun config to submit a rerun pipelinejob. This includes 1. Which task to rerun 2. User override input parameters and artifacts.
| Fields | |
|---|---|
task_id |
Optional. The system generated ID of the task. Retrieved from original run. |
task_name |
Optional. The name of the task. |
inputs |
Optional. The runtime input of the task overridden by the user. |
skip_task |
Optional. Whether to skip this task. Default value is False. |
skip_downstream_tasks |
Optional. Whether to skip downstream tasks. Default value is False. |
ArtifactList
A list of artifact metadata.
| Fields | |
|---|---|
artifacts[] |
Optional. A list of artifact metadata. |
Inputs
Runtime inputs data of the task.
| Fields | |
|---|---|
artifacts |
Optional. Input artifacts. |
parameter_values |
Optional. Input parameters. |
PipelineTemplateMetadata
Pipeline template metadata if PipelineJob.template_uri is from supported template registry. Currently, the only supported registry is Artifact Registry.
| Fields | |
|---|---|
version |
The version_name in artifact registry. Will always be presented in output if the Format is "sha256:abcdef123456...". |
PointwiseMetricInput
Input for pointwise metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for pointwise metric. |
instance |
Required. Pointwise metric instance. |
PointwiseMetricInstance
Pointwise metric instance. Usually one instance corresponds to one row in an evaluation dataset.
| Fields | |
|---|---|
Union field instance. Instance for pointwise metric. instance can be only one of the following: |
|
json_instance |
Instance specified as a json string. String key-value pairs are expected in the json_instance to render PointwiseMetricSpec.instance_prompt_template. |
PointwiseMetricResult
Spec for pointwise metric result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for pointwise metric score. |
score |
Output only. Pointwise metric score. |
PointwiseMetricSpec
Spec for pointwise metric.
| Fields | |
|---|---|
metric_prompt_template |
Required. Metric prompt template for pointwise metric. |
system_instruction |
Optional. System instructions for pointwise metric. |
Port
Represents a network port in a container.
| Fields | |
|---|---|
container_port |
The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive. |
PostStartupScriptConfig
Post startup script config.
| Fields | |
|---|---|
post_startup_script |
Optional. Post startup script to run after runtime is started. |
post_startup_script_url |
Optional. Post startup script url to download. Example: |
post_startup_script_behavior |
Optional. Post startup script behavior that defines download and execution behavior. |
PostStartupScriptBehavior
Represents a notebook runtime post startup script behavior.
| Enums | |
|---|---|
POST_STARTUP_SCRIPT_BEHAVIOR_UNSPECIFIED |
Unspecified post startup script behavior. |
RUN_ONCE |
Run post startup script after runtime is started. |
RUN_EVERY_START |
Run post startup script after runtime is stopped. |
DOWNLOAD_AND_RUN_EVERY_START |
Download and run post startup script every time runtime is started. |
PrebuiltVoiceConfig
The configuration for the prebuilt speaker to use.
| Fields | |
|---|---|
voice_name |
The name of the preset voice to use. |
PredefinedSplit
Assigns input data to training, validation, and test sets based on the value of a provided key.
Supported only for tabular Datasets.
| Fields | |
|---|---|
key |
Required. The key is a name of one of the Dataset's data columns. The value of the key (either the label's value or value in the column) must be one of { |
PredictLongRunningMetadata
This type has no fields.
Metadata for PredictLongRunning long running operations.
PredictLongRunningResponse
Response message for [PredictionService.PredictLongRunning]
| Fields | |
|---|---|
Union field response. The response of the long running operation. response can be only one of the following: |
|
generate_video_response |
The response of the video generation prediction. |
PredictRequest
Request message for PredictionService.Predict.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to serve the prediction. Format: |
instances[] |
Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' |
parameters |
The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' |
PredictRequestResponseLoggingConfig
Configuration for logging request-response to a BigQuery table.
| Fields | |
|---|---|
enabled |
If logging is enabled or not. |
sampling_rate |
Percentage of requests to be logged, expressed as a fraction in range(0,1]. |
bigquery_destination |
BigQuery table for logging. If only given a project, a new dataset will be created with name |
PredictResponse
Response message for PredictionService.Predict.
| Fields | |
|---|---|
predictions[] |
The predictions that are the output of the predictions call. The schema of any single prediction may be specified via Endpoint's DeployedModels' |
deployed_model_id |
ID of the Endpoint's DeployedModel that served this prediction. |
model |
Output only. The resource name of the Model which is deployed as the DeployedModel that this prediction hits. |
model_version_id |
Output only. The version ID of the Model which is deployed as the DeployedModel that this prediction hits. |
model_display_name |
Output only. The |
metadata |
Output only. Request-level metadata returned by the model. The metadata type will be dependent upon the model implementation. |
PredictSchemata
Contains the schemata used in Model's predictions and explanations via PredictionService.Predict, PredictionService.Explain and BatchPredictionJob.
| Fields | |
|---|---|
instance_schema_uri |
Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in |
parameters_schema_uri |
Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via |
prediction_schema_uri |
Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via |
Presets
Preset configuration for example-based explanations
| Fields | |
|---|---|
modality |
The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type. |
query |
Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to |
Modality
Preset option controlling parameters for different modalities
| Enums | |
|---|---|
MODALITY_UNSPECIFIED |
Should not be set. Added as a recommended best practice for enums |
IMAGE |
IMAGE modality |
TEXT |
TEXT modality |
TABULAR |
TABULAR modality |
Query
Preset option controlling parameters for query speed-precision trade-off
| Enums | |
|---|---|
PRECISE |
More precise neighbors as a trade-off against slower response. |
FAST |
Faster response as a trade-off against less precise neighbors. |
PrivateEndpoints
PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predict_http_uri, explain_http_uri or health_http_uri. To send request via private service connect, use service_attachment.
| Fields | |
|---|---|
predict_http_uri |
Output only. Http(s) path to send prediction requests. |
explain_http_uri |
Output only. Http(s) path to send explain requests. |
health_http_uri |
Output only. Http(s) path to send health check requests. |
service_attachment |
Output only. The name of the service attachment resource. Populated if private service connect is enabled. |
PrivateServiceConnectConfig
Represents configuration for private service connect.
| Fields | |
|---|---|
enable_private_service_connect |
Required. If true, expose the IndexEndpoint via private service connect. |
project_allowlist[] |
A list of Projects from which the forwarding rule will target the service attachment. |
enable_secure_private_service_connect |
Optional. If set to true, enable secure private service connect with IAM authorization. Otherwise, private service connect will be done without authorization. Note latency will be slightly increased if authorization is enabled. |
service_attachment |
Output only. The name of the generated service attachment resource. This is only populated if the endpoint is deployed with PrivateServiceConnect. |
Probe
Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic.
| Fields | |
|---|---|
period_seconds |
How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'. |
timeout_seconds |
Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'. |
failure_threshold |
Number of consecutive failures before the probe is considered failed. Defaults to 3. Minimum value is 1. Maps to Kubernetes probe argument 'failureThreshold'. |
success_threshold |
Number of consecutive successes before the probe is considered successful. Defaults to 1. Minimum value is 1. Maps to Kubernetes probe argument 'successThreshold'. |
initial_delay_seconds |
Number of seconds to wait before starting the probe. Defaults to 0. Minimum value is 0. Maps to Kubernetes probe argument 'initialDelaySeconds'. |
Union field
|
|
exec |
ExecAction probes the health of a container by executing a command. |
http_get |
HttpGetAction probes the health of a container by sending an HTTP GET request. |
grpc |
GrpcAction probes the health of a container by sending a gRPC request. |
tcp_socket |
TcpSocketAction probes the health of a container by opening a TCP socket connection. |
ExecAction
ExecAction specifies a command to execute.
| Fields | |
|---|---|
command[] |
Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. |
GrpcAction
GrpcAction checks the health of a container using a gRPC service.
| Fields | |
|---|---|
port |
Port number of the gRPC service. Number must be in the range 1 to 65535. |
service |
Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. |
HttpGetAction
HttpGetAction describes an action based on HTTP Get requests.
| Fields | |
|---|---|
path |
Path to access on the HTTP server. |
port |
Number of the port to access on the container. Number must be in the range 1 to 65535. |
host |
Host name to connect to, defaults to the model serving container's IP. You probably want to set "Host" in httpHeaders instead. |
scheme |
Scheme to use for connecting to the host. Defaults to HTTP. Acceptable values are "HTTP" or "HTTPS". |
http_headers[] |
Custom headers to set in the request. HTTP allows repeated headers. |
HttpHeader
HttpHeader describes a custom header to be used in HTTP probes
| Fields | |
|---|---|
name |
The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. |
value |
The header field value |
TcpSocketAction
TcpSocketAction probes the health of a container by opening a TCP socket connection.
| Fields | |
|---|---|
port |
Number of the port to access on the container. Number must be in the range 1 to 65535. |
host |
Optional: Host name to connect to, defaults to the model serving container's IP. |
PscAutomatedEndpoints
PscAutomatedEndpoints defines the output of the forwarding rule automatically created by each PscAutomationConfig.
| Fields | |
|---|---|
project_id |
Corresponding project_id in pscAutomationConfigs |
network |
Corresponding network in pscAutomationConfigs. |
match_address |
Ip Address created by the automated forwarding rule. |
PscInterfaceConfig
Configuration for PSC-I.
| Fields | |
|---|---|
network_attachment |
Optional. The name of the Compute Engine network attachment to attach to the resource within the region and user project. To specify this field, you must have already created a network attachment. This field is only used for resources using PSC-I. |
PublisherModel
A Model Garden Publisher Model.
| Fields | |
|---|---|
name |
Output only. The resource name of the PublisherModel. |
version_id |
Output only. Immutable. The version ID of the PublisherModel. A new version is committed when a new model version is uploaded under an existing model id. It is an auto-incrementing decimal number in string representation. |
open_source_category |
Required. Indicates the open source category of the publisher model. |
parent |
Optional. The parent that this model was customized from. E.g., Vision API, Natural Language API, LaMDA, T5, etc. Foundation models don't have parents. |
supported_actions |
Optional. Supported call-to-action options. |
frameworks[] |
Optional. Additional information about the model's Frameworks. |
launch_stage |
Optional. Indicates the launch stage of the model. |
version_state |
Optional. Indicates the state of the model version. |
publisher_model_template |
Optional. Output only. Immutable. Used to indicate this model has a publisher model and provide the template of the publisher model resource name. |
predict_schemata |
Optional. The schemata that describes formats of the PublisherModel's predictions and explanations as given and returned via |
CallToAction
Actions could take on this Publisher Model.
| Fields | |
|---|---|
view_rest_api |
Optional. To view Rest API docs. |
open_notebook |
Optional. Open notebook of the PublisherModel. |
create_application |
Optional. Create application using the PublisherModel. |
open_fine_tuning_pipeline |
Optional. Open fine-tuning pipeline of the PublisherModel. |
open_prompt_tuning_pipeline |
Optional. Open prompt-tuning pipeline of the PublisherModel. |
open_genie |
Optional. Open Genie / Playground. |
deploy |
Optional. Deploy the PublisherModel to Vertex Endpoint. |
multi_deploy_vertex |
Optional. Multiple setups to deploy the PublisherModel to Vertex Endpoint. |
deploy_gke |
Optional. Deploy PublisherModel to Google Kubernetes Engine. |
open_generation_ai_studio |
Optional. Open in Generation AI Studio. |
request_access |
Optional. Request for access. |
open_evaluation_pipeline |
Optional. Open evaluation pipeline of the PublisherModel. |
open_notebooks |
Optional. Open notebooks of the PublisherModel. |
open_fine_tuning_pipelines |
Optional. Open fine-tuning pipelines of the PublisherModel. |
Deploy
Model metadata that is needed for UploadModel or DeployModel/CreateEndpoint requests.
| Fields | |
|---|---|
model_display_name |
Optional. Default model display name. |
large_model_reference |
Optional. Large model reference. When this is set, model_artifact_spec is not needed. |
container_spec |
Optional. The specification of the container that is to be used when deploying this Model in Vertex AI. Not present for Large Models. |
artifact_uri |
Optional. The path to the directory containing the Model artifact and any of its supporting files. |
title |
Required. The title of the regional resource reference. |
public_artifact_uri |
Optional. The signed URI for ephemeral Cloud Storage access to model artifact. |
Union field prediction_resources. The prediction (for example, the machine) resources that the DeployedModel uses. prediction_resources can be only one of the following: |
|
dedicated_resources |
A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. |
automatic_resources |
A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. |
shared_resources |
The resource name of the shared DeploymentResourcePool to deploy on. Format: |
deploy_task_name |
Optional. The name of the deploy task (e.g., "text to image generation"). |
deploy_metadata |
Optional. Metadata information about this deployment config. |
DeployMetadata
Metadata information about the deployment for managing deployment config.
| Fields | |
|---|---|
labels |
Optional. Labels for the deployment config. For managing deployment config like verifying, source of deployment config, etc. |
sample_request |
Optional. Sample request for deployed endpoint. |
DeployGke
Configurations for PublisherModel GKE deployment
| Fields | |
|---|---|
gke_yaml_configs[] |
Optional. GKE deployment configuration in yaml format. |
DeployVertex
Multiple setups to deploy the PublisherModel.
| Fields | |
|---|---|
multi_deploy_vertex[] |
Optional. One click deployment configurations. |
OpenFineTuningPipelines
Open fine tuning pipelines.
| Fields | |
|---|---|
fine_tuning_pipelines[] |
Required. Regional resource references to fine tuning pipelines. |
OpenNotebooks
Open notebooks.
| Fields | |
|---|---|
notebooks[] |
Required. Regional resource references to notebooks. |
RegionalResourceReferences
The regional resource name or the URI. Key is region, e.g., us-central1, europe-west2, global, etc..
| Fields | |
|---|---|
references |
Required. |
title |
Required. |
resource_title |
Optional. Title of the resource. |
resource_use_case |
Optional. Use case (CUJ) of the resource. |
resource_description |
Optional. Description of the resource. |
ViewRestApi
Rest API docs.
| Fields | |
|---|---|
documentations[] |
Required. |
title |
Required. The title of the view rest API. |
Documentation
A named piece of documentation.
| Fields | |
|---|---|
title |
Required. E.g., OVERVIEW, USE CASES, DOCUMENTATION, SDK & SAMPLES, JAVA, NODE.JS, etc.. |
content |
Required. Content of this piece of document (in Markdown format). |
LaunchStage
An enum representing the launch stage of a PublisherModel.
| Enums | |
|---|---|
LAUNCH_STAGE_UNSPECIFIED |
The model launch stage is unspecified. |
EXPERIMENTAL |
Used to indicate the PublisherModel is at Experimental launch stage, available to a small set of customers. |
PRIVATE_PREVIEW |
Used to indicate the PublisherModel is at Private Preview launch stage, only available to a small set of customers, although a larger set of customers than an Experimental launch. Previews are the first launch stage used to get feedback from customers. |
PUBLIC_PREVIEW |
Used to indicate the PublisherModel is at Public Preview launch stage, available to all customers, although not supported for production workloads. |
GA |
Used to indicate the PublisherModel is at GA launch stage, available to all customers and ready for production workload. |
OpenSourceCategory
An enum representing the open source category of a PublisherModel.
| Enums | |
|---|---|
OPEN_SOURCE_CATEGORY_UNSPECIFIED |
The open source category is unspecified, which should not be used. |
PROPRIETARY |
Used to indicate the PublisherModel is not open sourced. |
GOOGLE_OWNED_OSS_WITH_GOOGLE_CHECKPOINT |
Used to indicate the PublisherModel is a Google-owned open source model w/ Google checkpoint. |
THIRD_PARTY_OWNED_OSS_WITH_GOOGLE_CHECKPOINT |
Used to indicate the PublisherModel is a 3p-owned open source model w/ Google checkpoint. |
GOOGLE_OWNED_OSS |
Used to indicate the PublisherModel is a Google-owned pure open source model. |
THIRD_PARTY_OWNED_OSS |
Used to indicate the PublisherModel is a 3p-owned pure open source model. |
Parent
The information about the parent of a model.
| Fields | |
|---|---|
display_name |
Required. The display name of the parent. E.g., LaMDA, T5, Vision API, Natural Language API. |
reference |
Optional. The Google Cloud resource name or the URI reference. |
ResourceReference
Reference to a resource.
| Fields | |
|---|---|
Union field
|
|
uri |
The URI of the resource. |
resource_name |
The resource name of the Google Cloud resource. |
use_case |
Use case (CUJ) of the resource. |
description |
Description of the resource. |
VersionState
An enum representing the state of the PublicModelVersion.
| Enums | |
|---|---|
VERSION_STATE_UNSPECIFIED |
The version state is unspecified. |
VERSION_STATE_STABLE |
Used to indicate the version is stable. |
VERSION_STATE_UNSTABLE |
Used to indicate the version is unstable. |
PublisherModelView
View enumeration of PublisherModel.
| Enums | |
|---|---|
PUBLISHER_MODEL_VIEW_UNSPECIFIED |
The default / unset value. The API will default to the BASIC view. |
PUBLISHER_MODEL_VIEW_BASIC |
Include basic metadata about the publisher model, but not the full contents. |
PUBLISHER_MODEL_VIEW_FULL |
Include everything. |
PUBLISHER_MODEL_VERSION_VIEW_BASIC |
Include: VersionId, ModelVersionExternalName, and SupportedActions. |
PurgeArtifactsMetadata
Details of operations that perform MetadataService.PurgeArtifacts.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for purging Artifacts. |
PurgeArtifactsRequest
Request message for MetadataService.PurgeArtifacts.
| Fields | |
|---|---|
parent |
Required. The metadata store to purge Artifacts from. Format: |
filter |
Required. A required filter matching the Artifacts to be purged. E.g., |
force |
Optional. Flag to indicate to actually perform the purge. If |
PurgeArtifactsResponse
Response message for MetadataService.PurgeArtifacts.
| Fields | |
|---|---|
purge_count |
The number of Artifacts that this request deleted (or, if |
purge_sample[] |
A sample of the Artifact names that will be deleted. Only populated if |
PurgeContextsMetadata
Details of operations that perform MetadataService.PurgeContexts.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for purging Contexts. |
PurgeContextsRequest
Request message for MetadataService.PurgeContexts.
| Fields | |
|---|---|
parent |
Required. The metadata store to purge Contexts from. Format: |
filter |
Required. A required filter matching the Contexts to be purged. E.g., |
force |
Optional. Flag to indicate to actually perform the purge. If |
PurgeContextsResponse
Response message for MetadataService.PurgeContexts.
| Fields | |
|---|---|
purge_count |
The number of Contexts that this request deleted (or, if |
purge_sample[] |
A sample of the Context names that will be deleted. Only populated if |
PurgeExecutionsMetadata
Details of operations that perform MetadataService.PurgeExecutions.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for purging Executions. |
PurgeExecutionsRequest
Request message for MetadataService.PurgeExecutions.
| Fields | |
|---|---|
parent |
Required. The metadata store to purge Executions from. Format: |
filter |
Required. A required filter matching the Executions to be purged. E.g., |
force |
Optional. Flag to indicate to actually perform the purge. If |
PurgeExecutionsResponse
Response message for MetadataService.PurgeExecutions.
| Fields | |
|---|---|
purge_count |
The number of Executions that this request deleted (or, if |
purge_sample[] |
A sample of the Execution names that will be deleted. Only populated if |
PythonPackageSpec
The spec of a Python packaged code.
| Fields | |
|---|---|
executor_image_uri |
Required. The URI of a container image in Artifact Registry that will run the provided Python package. Vertex AI provides a wide range of executor images with pre-installed packages to meet users' various use cases. See the list of pre-built containers for training. You must use an image from this list. |
package_uris[] |
Required. The Google Cloud Storage location of the Python package files which are the training program and its dependent packages. The maximum number of package URIs is 100. Authorization requires the following IAM permission on the specified resource
|
python_module |
Required. The Python module name to run after installing the packages. |
args[] |
Command line arguments to be passed to the Python task. |
env[] |
Environment variables to be passed to the python module. Maximum limit is 100. |
QueryArtifactLineageSubgraphRequest
Request message for MetadataService.QueryArtifactLineageSubgraph.
| Fields | |
|---|---|
artifact |
Required. The resource name of the Artifact whose Lineage needs to be retrieved as a LineageSubgraph. Format: The request may error with FAILED_PRECONDITION if the number of Artifacts, the number of Executions, or the number of Events that would be returned for the Context exceeds 1000. |
max_hops |
Specifies the size of the lineage graph in terms of number of hops from the specified artifact. Negative Value: INVALID_ARGUMENT error is returned 0: Only input artifact is returned. No value: Transitive closure is performed to return the complete graph. |
filter |
Filter specifying the boolean condition for the Artifacts to satisfy in order to be part of the Lineage Subgraph. The syntax to define filter query is based on https://google.aip.dev/160. The supported set of filters include the following:
Each of the above supported filter types can be combined together using logical operators ( For example: |
QueryContextLineageSubgraphRequest
Request message for MetadataService.QueryContextLineageSubgraph.
| Fields | |
|---|---|
context |
Required. The resource name of the Context whose Artifacts and Executions should be retrieved as a LineageSubgraph. Format: The request may error with FAILED_PRECONDITION if the number of Artifacts, the number of Executions, or the number of Events that would be returned for the Context exceeds 1000. |
QueryDeployedModelsRequest
Request message for QueryDeployedModels method.
| Fields | |
|---|---|
deployment_resource_pool |
Required. The name of the target DeploymentResourcePool to query. Format: |
page_size |
The maximum number of DeployedModels to return. The service may return fewer than this value. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
QueryDeployedModelsResponse
Response message for QueryDeployedModels method.
| Fields | |
|---|---|
deployed_models[] |
DEPRECATED Use deployed_model_refs instead. |
next_page_token |
A token, which can be sent as |
deployed_model_refs[] |
References to the DeployedModels that share the specified deploymentResourcePool. |
total_deployed_model_count |
The total number of DeployedModels on this DeploymentResourcePool. |
total_endpoint_count |
The total number of Endpoints that have DeployedModels on this DeploymentResourcePool. |
QueryExecutionInputsAndOutputsRequest
Request message for MetadataService.QueryExecutionInputsAndOutputs.
| Fields | |
|---|---|
execution |
Required. The resource name of the Execution whose input and output Artifacts should be retrieved as a LineageSubgraph. Format: |
QueryExtensionRequest
Request message for ExtensionExecutionService.QueryExtension.
| Fields | |
|---|---|
name |
Required. Name (identifier) of the extension; Format: |
contents[] |
Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request. |
QueryExtensionResponse
Response message for ExtensionExecutionService.QueryExtension.
| Fields | |
|---|---|
steps[] |
Steps of extension or LLM interaction, can contain function call, function response, or text response. The last step contains the final response to the query. |
failure_message |
Failure message if any. |
QueryReasoningEngineRequest
Request message for [ReasoningEngineExecutionService.Query][].
| Fields | |
|---|---|
name |
Required. The name of the ReasoningEngine resource to use. Format: |
input |
Optional. Input content provided by users in JSON object format. Examples include text query, function calling parameters, media bytes, etc. |
class_method |
Optional. Class method to be used for the query. It is optional and defaults to "query" if unspecified. |
QueryReasoningEngineResponse
Response message for [ReasoningEngineExecutionService.Query][]
| Fields | |
|---|---|
output |
Response provided by users in JSON object format. |
QuestionAnsweringCorrectnessInput
Input for question answering correctness metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for question answering correctness score metric. |
instance |
Required. Question answering correctness instance. |
QuestionAnsweringCorrectnessInstance
Spec for question answering correctness instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Optional. Ground truth used to compare against the prediction. |
context |
Optional. Text provided as context to answer the question. |
instruction |
Required. The question asked and other instruction in the inference prompt. |
QuestionAnsweringCorrectnessResult
Spec for question answering correctness result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for question answering correctness score. |
score |
Output only. Question Answering Correctness score. |
confidence |
Output only. Confidence for question answering correctness score. |
QuestionAnsweringCorrectnessSpec
Spec for question answering correctness metric.
| Fields | |
|---|---|
use_reference |
Optional. Whether to use instance.reference to compute question answering correctness. |
version |
Optional. Which version to use for evaluation. |
QuestionAnsweringHelpfulnessInput
Input for question answering helpfulness metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for question answering helpfulness score metric. |
instance |
Required. Question answering helpfulness instance. |
QuestionAnsweringHelpfulnessInstance
Spec for question answering helpfulness instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Optional. Ground truth used to compare against the prediction. |
context |
Optional. Text provided as context to answer the question. |
instruction |
Required. The question asked and other instruction in the inference prompt. |
QuestionAnsweringHelpfulnessResult
Spec for question answering helpfulness result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for question answering helpfulness score. |
score |
Output only. Question Answering Helpfulness score. |
confidence |
Output only. Confidence for question answering helpfulness score. |
QuestionAnsweringHelpfulnessSpec
Spec for question answering helpfulness metric.
| Fields | |
|---|---|
use_reference |
Optional. Whether to use instance.reference to compute question answering helpfulness. |
version |
Optional. Which version to use for evaluation. |
QuestionAnsweringQualityInput
Input for question answering quality metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for question answering quality score metric. |
instance |
Required. Question answering quality instance. |
QuestionAnsweringQualityInstance
Spec for question answering quality instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Optional. Ground truth used to compare against the prediction. |
context |
Required. Text to answer the question. |
instruction |
Required. Question Answering prompt for LLM. |
QuestionAnsweringQualityResult
Spec for question answering quality result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for question answering quality score. |
score |
Output only. Question Answering Quality score. |
confidence |
Output only. Confidence for question answering quality score. |
QuestionAnsweringQualitySpec
Spec for question answering quality score metric.
| Fields | |
|---|---|
use_reference |
Optional. Whether to use instance.reference to compute question answering quality. |
version |
Optional. Which version to use for evaluation. |
QuestionAnsweringRelevanceInput
Input for question answering relevance metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for question answering relevance score metric. |
instance |
Required. Question answering relevance instance. |
QuestionAnsweringRelevanceInstance
Spec for question answering relevance instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Optional. Ground truth used to compare against the prediction. |
context |
Optional. Text provided as context to answer the question. |
instruction |
Required. The question asked and other instruction in the inference prompt. |
QuestionAnsweringRelevanceResult
Spec for question answering relevance result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for question answering relevance score. |
score |
Output only. Question Answering Relevance score. |
confidence |
Output only. Confidence for question answering relevance score. |
QuestionAnsweringRelevanceSpec
Spec for question answering relevance metric.
| Fields | |
|---|---|
use_reference |
Optional. Whether to use instance.reference to compute question answering relevance. |
version |
Optional. Which version to use for evaluation. |
RagContexts
Relevant contexts for one query.
| Fields | |
|---|---|
contexts[] |
All its contexts. |
Context
A context of the query.
| Fields | |
|---|---|
source_uri |
If the file is imported from Cloud Storage or Google Drive, source_uri will be original file URI in Cloud Storage or Google Drive; if file is uploaded, source_uri will be file display name. |
source_display_name |
The file display name. |
text |
The text chunk. |
distance |
The distance between the query dense embedding vector and the context text vector. |
sparse_distance |
The distance between the query sparse embedding vector and the context text vector. |
score |
According to the underlying Vector DB and the selected metric type, the score can be either the distance or the similarity between the query and the context and its range depends on the metric type. For example, if the metric type is COSINE_DISTANCE, it represents the distance between the query and the context. The larger the distance, the less relevant the context is to the query. The range is [0, 2], while 0 means the most relevant and 2 means the least relevant. |
RagCorpus
A RagCorpus is a RagFile container and a project can have multiple RagCorpora.
| Fields | |
|---|---|
name |
Output only. The resource name of the RagCorpus. |
display_name |
Required. The display name of the RagCorpus. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
description |
Optional. The description of the RagCorpus. |
rag_embedding_model_config |
Optional. Immutable. The embedding model config of the RagCorpus. |
rag_vector_db_config |
Optional. Immutable. The Vector DB config of the RagCorpus. |
create_time |
Output only. Timestamp when this RagCorpus was created. |
update_time |
Output only. Timestamp when this RagCorpus was last updated. |
corpus_status |
Output only. RagCorpus state. |
rag_files_count |
Output only. Number of RagFiles in the RagCorpus. |
Union field backend_config. The backend config of the RagCorpus. It can be data store and/or retrieval engine. backend_config can be only one of the following: |
|
vector_db_config |
Optional. Immutable. The config for the Vector DBs. |
vertex_ai_search_config |
Optional. Immutable. The config for the Vertex AI Search. |
RagEmbeddingModelConfig
Config for the embedding model to use for RAG.
| Fields | |
|---|---|
Union field model_config. The model config to use. model_config can be only one of the following: |
|
vertex_prediction_endpoint |
The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search. |
hybrid_search_config |
Configuration for hybrid search. |
HybridSearchConfig
Config for hybrid search.
| Fields | |
|---|---|
sparse_embedding_config |
Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus. |
dense_embedding_model_prediction_endpoint |
Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations. |
SparseEmbeddingConfig
Configuration for sparse emebdding generation.
| Fields | |
|---|---|
Union field model. The model to use for sparse embedding generation. model can be only one of the following: |
|
bm25 |
Use BM25 scoring algorithm. |
Bm25
Message for BM25 parameters.
| Fields | |
|---|---|
multilingual |
Optional. Use multilingual tokenizer if set to true. |
k1 |
Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2. |
b |
Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75. |
VertexPredictionEndpoint
Config representing a model hosted on Vertex Prediction Endpoint.
| Fields | |
|---|---|
endpoint |
Required. The endpoint resource name. Format: |
model |
Output only. The resource name of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. Pattern: |
model_version_id |
Output only. Version ID of the model that is deployed on the endpoint. Present only when the endpoint is not a publisher model. |
RagFile
A RagFile contains user data for chunking, embedding and indexing.
| Fields | |
|---|---|
name |
Output only. The resource name of the RagFile. |
display_name |
Required. The display name of the RagFile. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
description |
Optional. The description of the RagFile. |
size_bytes |
Output only. The size of the RagFile in bytes. |
rag_file_type |
Output only. The type of the RagFile. |
create_time |
Output only. Timestamp when this RagFile was created. |
update_time |
Output only. Timestamp when this RagFile was last updated. |
file_status |
Output only. State of the RagFile. |
Union field rag_file_source. The origin location of the RagFile if it is imported from Google Cloud Storage or Google Drive. rag_file_source can be only one of the following: |
|
gcs_source |
Output only. Google Cloud Storage location of the RagFile. It does not support wildcards in the Cloud Storage uri for now. |
google_drive_source |
Output only. Google Drive location. Supports importing individual files as well as Google Drive folders. |
direct_upload_source |
Output only. The RagFile is encapsulated and uploaded in the UploadRagFile request. |
slack_source |
The RagFile is imported from a Slack channel. |
jira_source |
The RagFile is imported from a Jira query. |
share_point_sources |
The RagFile is imported from a SharePoint source. |
RagFileType
The type of the RagFile.
| Enums | |
|---|---|
RAG_FILE_TYPE_UNSPECIFIED |
RagFile type is unspecified. |
RAG_FILE_TYPE_TXT |
RagFile type is TXT. |
RAG_FILE_TYPE_PDF |
RagFile type is PDF. |
RagFileChunkingConfig
Specifies the size and overlap of chunks for RagFiles.
| Fields | |
|---|---|
chunk_size |
The size of the chunks. |
chunk_overlap |
The overlap between chunks. |
Union field chunking_config. Specifies the chunking config for RagFiles. chunking_config can be only one of the following: |
|
fixed_length_chunking |
Specifies the fixed length chunking config. |
FixedLengthChunking
Specifies the fixed length chunking config.
| Fields | |
|---|---|
chunk_size |
The size of the chunks. |
chunk_overlap |
The overlap between chunks. |
RagFileParsingConfig
Specifies the parsing config for RagFiles.
| Fields | |
|---|---|
use_advanced_pdf_parsing |
Whether to use advanced PDF parsing. |
Union field parser. The parser to use for RagFiles. parser can be only one of the following: |
|
advanced_parser |
The Advanced Parser to use for RagFiles. |
layout_parser |
The Layout Parser to use for RagFiles. |
llm_parser |
The LLM Parser to use for RagFiles. |
AdvancedParser
Specifies the advanced parsing for RagFiles.
| Fields | |
|---|---|
use_advanced_pdf_parsing |
Whether to use advanced PDF parsing. |
LayoutParser
Document AI Layout Parser config.
| Fields | |
|---|---|
processor_name |
The full resource name of a Document AI processor or processor version. The processor must have type |
max_parsing_requests_per_min |
The maximum number of requests the job is allowed to make to the Document AI processor per minute. Consult https://cloud.google.com/document-ai/quotas and the Quota page for your project to set an appropriate value here. If unspecified, a default value of 120 QPM would be used. |
LlmParser
Specifies the advanced parsing for RagFiles.
| Fields | |
|---|---|
model_name |
The name of a LLM model used for parsing. Format: * |
max_parsing_requests_per_min |
The maximum number of requests the job is allowed to make to the LLM model per minute. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If unspecified, a default value of 5000 QPM would be used. |
custom_parsing_prompt |
The prompt to use for parsing. If not specified, a default prompt will be used. |
RagFileTransformationConfig
Specifies the transformation config for RagFiles.
| Fields | |
|---|---|
rag_file_chunking_config |
Specifies the chunking config for RagFiles. |
RagQuery
A query to retrieve relevant contexts.
| Fields | |
|---|---|
similarity_top_k |
Optional. The number of contexts to retrieve. |
ranking |
Optional. Configurations for hybrid search results ranking. |
rag_retrieval_config |
Optional. The retrieval config for the query. |
Union field query. The query to retrieve contexts. Currently only text query is supported. query can be only one of the following: |
|
text |
Optional. The query in text format to get relevant contexts. |
Ranking
Configurations for hybrid search results ranking.
| Fields | |
|---|---|
alpha |
Optional. Alpha value controls the weight between dense and sparse vector search results. The range is [0, 1], while 0 means sparse vector search only and 1 means dense vector search only. The default value is 0.5 which balances sparse and dense vector search equally. |
RagRetrievalConfig
Specifies the context retrieval config.
| Fields | |
|---|---|
top_k |
Optional. The number of contexts to retrieve. |
hybrid_search |
Optional. Config for Hybrid Search. |
filter |
Optional. Config for filters. |
ranking |
Optional. Config for ranking and reranking. |
Filter
Config for filters.
| Fields | |
|---|---|
metadata_filter |
Optional. String for metadata filtering. |
Union field vector_db_threshold. Filter contexts retrieved from the vector DB based on either vector distance or vector similarity. vector_db_threshold can be only one of the following: |
|
vector_distance_threshold |
Optional. Only returns contexts with vector distance smaller than the threshold. |
vector_similarity_threshold |
Optional. Only returns contexts with vector similarity larger than the threshold. |
HybridSearch
Config for Hybrid Search.
| Fields | |
|---|---|
alpha |
Optional. Alpha value controls the weight between dense and sparse vector search results. The range is [0, 1], while 0 means sparse vector search only and 1 means dense vector search only. The default value is 0.5 which balances sparse and dense vector search equally. |
Ranking
Config for ranking and reranking.
| Fields | |
|---|---|
Union field ranking_config. Config options for ranking. Currently only Rank Service is supported. ranking_config can be only one of the following: |
|
rank_service |
Optional. Config for Rank Service. |
llm_ranker |
Optional. Config for LlmRanker. |
LlmRanker
Config for LlmRanker.
| Fields | |
|---|---|
model_name |
Optional. The model name used for ranking. Format: |
RankService
Config for Rank Service.
| Fields | |
|---|---|
model_name |
Optional. The model name of the rank service. Format: |
RagVectorDbConfig
Config for the Vector DB to use for RAG.
| Fields | |
|---|---|
api_auth |
Authentication config for the chosen Vector DB. |
rag_embedding_model_config |
Optional. Immutable. The embedding model config of the Vector DB. |
Union field vector_db. The config for the Vector DB. vector_db can be only one of the following: |
|
rag_managed_db |
The config for the RAG-managed Vector DB. |
weaviate |
The config for the Weaviate. |
pinecone |
The config for the Pinecone. |
vertex_feature_store |
The config for the Vertex Feature Store. |
vertex_vector_search |
The config for the Vertex Vector Search. |
Pinecone
The config for the Pinecone.
| Fields | |
|---|---|
index_name |
Pinecone index name. This value cannot be changed after it's set. |
RagManagedDb
This type has no fields.
The config for the default RAG-managed Vector DB.
VertexFeatureStore
The config for the Vertex Feature Store.
| Fields | |
|---|---|
feature_view_resource_name |
The resource name of the FeatureView. Format: |
VertexVectorSearch
The config for the Vertex Vector Search.
| Fields | |
|---|---|
index_endpoint |
The resource name of the Index Endpoint. Format: |
index |
The resource name of the Index. Format: |
Weaviate
The config for the Weaviate.
| Fields | |
|---|---|
http_endpoint |
Weaviate DB instance HTTP endpoint. e.g. 34.56.78.90:8080 Vertex RAG only supports HTTP connection to Weaviate. This value cannot be changed after it's set. |
collection_name |
The corresponding collection this corpus maps to. This value cannot be changed after it's set. |
RawPredictRequest
Request message for PredictionService.RawPredict.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to serve the prediction. Format: |
http_body |
The prediction input. Supports HTTP headers and arbitrary data payload. A You can specify the schema for each instance in the |
RayLogsSpec
Configuration for the Ray OSS Logs.
| Fields | |
|---|---|
disabled |
Optional. Flag to disable the export of Ray OSS logs to Cloud Logging. |
RayMetricSpec
Configuration for the Ray metrics.
| Fields | |
|---|---|
disabled |
Optional. Flag to disable the Ray metrics collection. |
RaySpec
Configuration information for the Ray cluster. For experimental launch, Ray cluster creation and Persistent cluster creation are 1:1 mapping: We will provision all the nodes within the Persistent cluster as Ray nodes.
| Fields | |
|---|---|
image_uri |
Optional. Default image for user to choose a preferred ML framework (for example, TensorFlow or Pytorch) by choosing from Vertex prebuilt images. Either this or the resource_pool_images is required. Use this field if you need all the resource pools to have the same Ray image. Otherwise, use the {@code resource_pool_images} field. |
nfs_mounts[] |
Optional. Use if you want to mount to any NFS storages. |
resource_pool_images |
Optional. Required if image_uri isn't set. A map of resource_pool_id to prebuild Ray image if user need to use different images for different head/worker pools. This map needs to cover all the resource pool ids. Example: { "ray_head_node_pool": "head image" "ray_worker_node_pool1": "worker image" "ray_worker_node_pool2": "another worker image" } |
head_node_resource_pool_id |
Optional. This will be used to indicate which resource pool will serve as the Ray head node(the first node within that pool). Will use the machine from the first workerpool as the head node by default if this field isn't set. |
ray_metric_spec |
Optional. Ray metrics configurations. |
ray_logs_spec |
Optional. OSS Ray logging configurations. |
ReadFeatureValuesRequest
Request message for FeaturestoreOnlineServingService.ReadFeatureValues.
| Fields | |
|---|---|
entity_type |
Required. The resource name of the EntityType for the entity being read. Value format: |
entity_id |
Required. ID for a specific entity. For example, for a machine learning model predicting user clicks on a website, an entity ID could be |
feature_selector |
Required. Selector choosing Features of the target EntityType. |
ReadFeatureValuesResponse
Response message for FeaturestoreOnlineServingService.ReadFeatureValues.
| Fields | |
|---|---|
header |
Response header. |
entity_view |
Entity view with Feature values. This may be the entity in the Featurestore if values for all Features were requested, or a projection of the entity in the Featurestore if values for only some Features were requested. |
EntityView
Entity view with Feature values.
| Fields | |
|---|---|
entity_id |
ID of the requested entity. |
data[] |
Each piece of data holds the k requested values for one requested Feature. If no values for the requested Feature exist, the corresponding cell will be empty. This has the same size and is in the same order as the features from the header |
Data
Container to hold value(s), successive in time, for one Feature from the request.
| Fields | |
|---|---|
Union field
|
|
value |
Feature value if a single value is requested. |
values |
Feature values list if values, successive in time, are requested. If the requested number of values is greater than the number of existing Feature values, nonexistent values are omitted instead of being returned as empty. |
FeatureDescriptor
Metadata for requested Features.
| Fields | |
|---|---|
id |
Feature ID. |
Header
Response header with metadata for the requested ReadFeatureValuesRequest.entity_type and Features.
| Fields | |
|---|---|
entity_type |
The resource name of the EntityType from the |
feature_descriptors[] |
List of Feature metadata corresponding to each piece of |
ReadTensorboardBlobDataRequest
Request message for TensorboardService.ReadTensorboardBlobData.
| Fields | |
|---|---|
time_series |
Required. The resource name of the TensorboardTimeSeries to list Blobs. Format: |
blob_ids[] |
IDs of the blobs to read. |
ReadTensorboardBlobDataResponse
Response message for TensorboardService.ReadTensorboardBlobData.
| Fields | |
|---|---|
blobs[] |
Blob messages containing blob bytes. |
ReadTensorboardSizeRequest
Request message for TensorboardService.ReadTensorboardSize.
| Fields | |
|---|---|
tensorboard |
Required. The name of the Tensorboard resource. Format: |
ReadTensorboardSizeResponse
Response message for TensorboardService.ReadTensorboardSize.
| Fields | |
|---|---|
storage_size_byte |
Payload storage size for the TensorBoard |
ReadTensorboardTimeSeriesDataRequest
Request message for TensorboardService.ReadTensorboardTimeSeriesData.
| Fields | |
|---|---|
tensorboard_time_series |
Required. The resource name of the TensorboardTimeSeries to read data from. Format: |
max_data_points |
The maximum number of TensorboardTimeSeries' data to return. This value should be a positive integer. This value can be set to -1 to return all data. |
filter |
Reads the TensorboardTimeSeries' data that match the filter expression. |
ReadTensorboardTimeSeriesDataResponse
Response message for TensorboardService.ReadTensorboardTimeSeriesData.
| Fields | |
|---|---|
time_series_data |
The returned time series data. |
ReadTensorboardUsageRequest
Request message for TensorboardService.ReadTensorboardUsage.
| Fields | |
|---|---|
tensorboard |
Required. The name of the Tensorboard resource. Format: |
ReadTensorboardUsageResponse
Response message for TensorboardService.ReadTensorboardUsage.
| Fields | |
|---|---|
monthly_usage_data |
Maps year-month (YYYYMM) string to per month usage data. |
PerMonthUsageData
Per month usage data
| Fields | |
|---|---|
user_usage_data[] |
Usage data for each user in the given month. |
PerUserUsageData
Per user usage data.
| Fields | |
|---|---|
username |
User's username |
view_count |
Number of times the user has read data within the Tensorboard. |
ReasoningEngine
ReasoningEngine provides a customizable runtime for models to determine which actions to take and in which order.
| Fields | |
|---|---|
name |
Identifier. The resource name of the ReasoningEngine. |
display_name |
Required. The display name of the ReasoningEngine. |
description |
Optional. The description of the ReasoningEngine. |
spec |
Required. Configurations of the ReasoningEngine |
create_time |
Output only. Timestamp when this ReasoningEngine was created. |
update_time |
Output only. Timestamp when this ReasoningEngine was most recently updated. |
etag |
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
ReasoningEngineSpec
ReasoningEngine configurations
| Fields | |
|---|---|
package_spec |
Required. User provided package spec of the ReasoningEngine. |
class_methods[] |
Optional. Declarations for object class methods in OpenAPI specification format. |
PackageSpec
User provided package spec like pickled object and package requirements.
| Fields | |
|---|---|
pickle_object_gcs_uri |
Optional. The Cloud Storage URI of the pickled python object. |
dependency_files_gcs_uri |
Optional. The Cloud Storage URI of the dependency files in tar.gz format. |
requirements_gcs_uri |
Optional. The Cloud Storage URI of the |
python_version |
Optional. The Python version. Currently support 3.8, 3.9, 3.10, 3.11. If not specified, default value is 3.10. |
RebaseTunedModelOperationMetadata
Runtime operation information for GenAiTuningService.RebaseTunedModel.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation generic information. |
RebaseTunedModelRequest
Request message for GenAiTuningService.RebaseTunedModel.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location into which to rebase the Model. Format: |
tuned_model_ref |
Required. TunedModel reference to retrieve the legacy model information. |
tuning_job |
Optional. The TuningJob to be updated. Users can use this TuningJob field to overwrite tuning configs. |
artifact_destination |
Optional. The Google Cloud Storage location to write the artifacts. |
deploy_to_same_endpoint |
Optional. By default, bison to gemini migration will always create new model/endpoint, but for gemini-1.0 to gemini-1.5 migration, we default deploy to the same endpoint. See details in this Section. |
RebootPersistentResourceOperationMetadata
Details of operations that perform reboot PersistentResource.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for PersistentResource. |
progress_message |
Progress Message for Reboot LRO |
RebootPersistentResourceRequest
Request message for PersistentResourceService.RebootPersistentResource.
| Fields | |
|---|---|
name |
Required. The name of the PersistentResource resource. Format: |
RemoveContextChildrenRequest
Request message for [MetadataService.DeleteContextChildrenRequest][].
| Fields | |
|---|---|
context |
Required. The resource name of the parent Context. Format: |
child_contexts[] |
The resource names of the child Contexts. |
RemoveContextChildrenResponse
This type has no fields.
Response message for MetadataService.RemoveContextChildren.
RemoveDatapointsRequest
Request message for IndexService.RemoveDatapoints
| Fields | |
|---|---|
index |
Required. The name of the Index resource to be updated. Format: |
datapoint_ids[] |
A list of datapoint ids to be deleted. |
RemoveDatapointsResponse
This type has no fields.
Response message for IndexService.RemoveDatapoints
ReservationAffinity
A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity.
| Fields | |
|---|---|
reservation_affinity_type |
Required. Specifies the reservation affinity type. |
key |
Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use |
values[] |
Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation or reservation block. |
Type
Identifies a type of reservation affinity.
| Enums | |
|---|---|
TYPE_UNSPECIFIED |
Default value. This should not be used. |
NO_RESERVATION |
Do not consume from any reserved capacity, only use on-demand. |
ANY_RESERVATION |
Consume any reservation available, falling back to on-demand. |
SPECIFIC_RESERVATION |
Consume from a specific reservation. When chosen, the reservation must be identified via the key and values fields. |
ResourcePool
Represents the spec of a group of resources of the same type, for example machine type, disk, and accelerators, in a PersistentResource.
| Fields | |
|---|---|
id |
Immutable. The unique ID in a PersistentResource for referring to this resource pool. User can specify it if necessary. Otherwise, it's generated automatically. |
machine_spec |
Required. Immutable. The specification of a single machine. |
disk_spec |
Optional. Disk spec for the machine in this node pool. |
used_replica_count |
Output only. The number of machines currently in use by training jobs for this resource pool. Will replace idle_replica_count. |
autoscaling_spec |
Optional. Optional spec to configure GKE or Ray-on-Vertex autoscaling |
replica_count |
Optional. The total number of machines to use for this resource pool. |
AutoscalingSpec
The min/max number of replicas allowed if enabling autoscaling
| Fields | |
|---|---|
min_replica_count |
Optional. min replicas in the node pool, must be ≤ replica_count and < max_replica_count or will throw error. For autoscaling enabled Ray-on-Vertex, we allow min_replica_count of a resource_pool to be 0 to match the OSS Ray behavior(https://docs.ray.io/en/latest/cluster/vms/user-guides/configuring-autoscaling.html#cluster-config-parameters). As for Persistent Resource, the min_replica_count must be > 0, we added a corresponding validation inside CreatePersistentResourceRequestValidator.java. |
max_replica_count |
Optional. max replicas in the node pool, must be ≥ replica_count and > min_replica_count or will throw error |
ResourceRuntime
Persistent Cluster runtime information as output
| Fields | |
|---|---|
access_uris |
Output only. URIs for user to connect to the Cluster. Example: { "RAY_HEAD_NODE_INTERNAL_IP": "head-node-IP:10001" "RAY_DASHBOARD_URI": "ray-dashboard-address:8888" } |
notebook_runtime_template |
Output only. The resource name of NotebookRuntimeTemplate for the RoV Persistent Cluster The NotebokRuntimeTemplate is created in the same VPC (if set), and with the same Ray and Python version as the Persistent Cluster. Example: "projects/1000/locations/us-central1/notebookRuntimeTemplates/abc123" |
ResourceRuntimeSpec
Configuration for the runtime on a PersistentResource instance, including but not limited to:
- Service accounts used to run the workloads.
- Whether to make it a dedicated Ray Cluster.
| Fields | |
|---|---|
service_account_spec |
Optional. Configure the use of workload identity on the PersistentResource |
ray_spec |
Optional. Ray cluster configuration. Required when creating a dedicated RayCluster on the PersistentResource. |
ResourcesConsumed
Statistics information about resource consumption.
| Fields | |
|---|---|
replica_hours |
Output only. The number of replica hours used. Note that many replicas may run in parallel, and additionally any given work may be queued for some time. Therefore this value is not strictly related to wall time. |
RestoreDatasetVersionOperationMetadata
Runtime operation information for DatasetService.RestoreDatasetVersion.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
RestoreDatasetVersionRequest
Request message for DatasetService.RestoreDatasetVersion.
| Fields | |
|---|---|
name |
Required. The name of the DatasetVersion resource. Format: |
ResumeModelDeploymentMonitoringJobRequest
Request message for JobService.ResumeModelDeploymentMonitoringJob.
| Fields | |
|---|---|
name |
Required. The resource name of the ModelDeploymentMonitoringJob to resume. Format: |
ResumeScheduleRequest
Request message for ScheduleService.ResumeSchedule.
| Fields | |
|---|---|
name |
Required. The name of the Schedule resource to be resumed. Format: |
catch_up |
Optional. Whether to backfill missed runs when the schedule is resumed from PAUSED state. If set to true, all missed runs will be scheduled. New runs will be scheduled after the backfill is complete. This will also update |
Retrieval
Defines a retrieval tool that model can call to access external knowledge.
| Fields | |
|---|---|
disable_attribution |
Optional. Deprecated. This option is no longer supported. |
Union field source. The source of the retrieval. source can be only one of the following: |
|
vertex_ai_search |
Set to use data source powered by Vertex AI Search. |
vertex_rag_store |
Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService. |
RetrievalConfig
Retrieval config.
| Fields | |
|---|---|
lat_lng |
The location of the user. |
language_code |
The language code of the user. |
RetrievalMetadata
Metadata related to retrieval in the grounding flow.
| Fields | |
|---|---|
google_search_dynamic_retrieval_score |
Optional. Score indicating how likely information from Google Search could help answer the prompt. The score is in the range |
RetrieveContextsRequest
Request message for VertexRagService.RetrieveContexts.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location from which to retrieve RagContexts. The users must have permission to make a call in the project. Format: |
query |
Required. Single RAG retrieve query. |
Union field data_source. Data Source to retrieve contexts. data_source can be only one of the following: |
|
vertex_rag_store |
The data source for Vertex RagStore. |
VertexRagStore
The data source for Vertex RagStore.
| Fields | |
|---|---|
rag_corpora[] |
Optional. Deprecated. Please use rag_resources to specify the data source. |
rag_resources[] |
Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support. |
vector_distance_threshold |
Optional. Only return contexts with vector distance smaller than the threshold. |
RagResource
The definition of the Rag resource.
| Fields | |
|---|---|
rag_corpus |
Optional. RagCorpora resource name. Format: |
rag_file_ids[] |
Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field. |
RetrieveContextsResponse
Response message for VertexRagService.RetrieveContexts.
| Fields | |
|---|---|
contexts |
The contexts of the query. |
RolloutOptions
Configuration for rolling deployments.
| Fields | |
|---|---|
previous_deployed_model |
ID of the DeployedModel that this deployment should replace. |
revision_number |
Output only. Read-only. Revision number determines the relative priority of DeployedModels in the same rollout. The DeployedModel with the largest revision number specifies the intended state of the deployment. |
Union field max_unavailable. Configures how many replicas are allowed to be unavailable during a rolling deployment. max_unavailable can be only one of the following: |
|
max_unavailable_replicas |
Absolute count of replicas allowed to be unavailable. |
max_unavailable_percentage |
Percentage of replicas allowed to be unavailable. For autoscaling deployments, this refers to the target replica count. |
Union field max_surge. Configures how many additional replicas can be provisioned during a rolling deployment. max_surge can be only one of the following: |
|
max_surge_replicas |
Absolute count of allowed additional replicas. |
max_surge_percentage |
Percentage of allowed additional replicas. For autoscaling deployments, this refers to the target replica count. |
RougeInput
Input for rouge metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for rouge score metric. |
instances[] |
Required. Repeated rouge instances. |
RougeInstance
Spec for rouge instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Required. Ground truth used to compare against the prediction. |
RougeMetricValue
Rouge metric value for an instance.
| Fields | |
|---|---|
score |
Output only. Rouge score. |
RougeResults
Results for rouge metric.
| Fields | |
|---|---|
rouge_metric_values[] |
Output only. Rouge metric values. |
RougeSpec
Spec for rouge score metric - calculates the recall of n-grams in prediction as compared to reference - returns a score ranging between 0 and 1.
| Fields | |
|---|---|
rouge_type |
Optional. Supported rouge types are rougen[1-9], rougeL, and rougeLsum. |
use_stemmer |
Optional. Whether to use stemmer to compute rouge score. |
split_summaries |
Optional. Whether to split summaries while using rougeLsum. |
RuntimeArtifact
The definition of a runtime artifact.
| Fields | |
|---|---|
name |
The name of an artifact. |
type |
The type of the artifact. |
uri |
The URI of the artifact. |
properties |
The properties of the artifact. Deprecated. Use |
custom_properties |
The custom properties of the artifact. Deprecated. Use |
metadata |
Properties of the Artifact. |
RuntimeConfig
Runtime configuration to run the extension.
| Fields | |
|---|---|
default_params |
Optional. Default parameters that will be set for all the execution of this extension. If specified, the parameter values can be overridden by values in [[ExecuteExtensionRequest.operation_params]] at request time. The struct should be in a form of map with param name as the key and actual param value as the value. E.g. If this operation requires a param "name" to be set to "abc". you can set this to something like {"name": "abc"}. |
Union field GoogleFirstPartyExtensionConfig. Runtime configurations for Google first party extensions. GoogleFirstPartyExtensionConfig can be only one of the following: |
|
code_interpreter_runtime_config |
Code execution runtime configurations for code interpreter extension. |
vertex_ai_search_runtime_config |
Runtime configuration for Vertex AI Search extension. |
CodeInterpreterRuntimeConfig
| Fields | |
|---|---|
file_input_gcs_bucket |
Optional. The Cloud Storage bucket for file input of this Extension. If specified, support input from the Cloud Storage bucket. Vertex Extension Custom Code Service Agent should be granted file reader to this bucket. If not specified, the extension will only accept file contents from request body and reject Cloud Storage file inputs. |
file_output_gcs_bucket |
Optional. The Cloud Storage bucket for file output of this Extension. If specified, write all output files to the Cloud Storage bucket. Vertex Extension Custom Code Service Agent should be granted file writer to this bucket. If not specified, the file content will be output in response body. |
VertexAISearchRuntimeConfig
| Fields | |
|---|---|
serving_config_name |
Optional. Vertex AI Search serving config name. Format: |
engine_id |
Optional. Vertex AI Search engine ID. This is used to construct the search request. By setting this engine_id, API will construct the serving config using the default value to call search API for the user. The engine_id and serving_config_name cannot both be empty at the same time. |
SafetyInput
Input for safety metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for safety metric. |
instance |
Required. Safety instance. |
SafetyInstance
Spec for safety instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
SafetyRating
Safety rating corresponding to the generated content.
| Fields | |
|---|---|
category |
Output only. Harm category. |
probability |
Output only. Harm probability levels in the content. |
probability_score |
Output only. Harm probability score. |
severity |
Output only. Harm severity levels in the content. |
severity_score |
Output only. Harm severity score. |
blocked |
Output only. Indicates whether the content was filtered out because of this rating. |
HarmProbability
Harm probability levels in the content.
| Enums | |
|---|---|
HARM_PROBABILITY_UNSPECIFIED |
Harm probability unspecified. |
NEGLIGIBLE |
Negligible level of harm. |
LOW |
Low level of harm. |
MEDIUM |
Medium level of harm. |
HIGH |
High level of harm. |
HarmSeverity
Harm severity levels.
| Enums | |
|---|---|
HARM_SEVERITY_UNSPECIFIED |
Harm severity unspecified. |
HARM_SEVERITY_NEGLIGIBLE |
Negligible level of harm severity. |
HARM_SEVERITY_LOW |
Low level of harm severity. |
HARM_SEVERITY_MEDIUM |
Medium level of harm severity. |
HARM_SEVERITY_HIGH |
High level of harm severity. |
SafetyResult
Spec for safety result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for safety score. |
score |
Output only. Safety score. |
confidence |
Output only. Confidence for safety score. |
SafetySetting
Safety settings.
| Fields | |
|---|---|
category |
Required. Harm category. |
threshold |
Required. The harm block threshold. |
method |
Optional. Specify if the threshold is used for probability or severity score. If not specified, the threshold is used for probability score. |
HarmBlockMethod
Probability vs severity.
| Enums | |
|---|---|
HARM_BLOCK_METHOD_UNSPECIFIED |
The harm block method is unspecified. |
SEVERITY |
The harm block method uses both probability and severity scores. |
PROBABILITY |
The harm block method uses the probability score. |
HarmBlockThreshold
Probability based thresholds levels for blocking.
| Enums | |
|---|---|
HARM_BLOCK_THRESHOLD_UNSPECIFIED |
Unspecified harm block threshold. |
BLOCK_LOW_AND_ABOVE |
Block low threshold and above (i.e. block more). |
BLOCK_MEDIUM_AND_ABOVE |
Block medium threshold and above. |
BLOCK_ONLY_HIGH |
Block only high threshold (i.e. block less). |
BLOCK_NONE |
Block none. |
OFF |
Turn off the safety filter. |
SafetySpec
Spec for safety metric.
| Fields | |
|---|---|
version |
Optional. Which version to use for evaluation. |
SampledShapleyAttribution
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
| Fields | |
|---|---|
path_count |
Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively. |
SamplingStrategy
Sampling Strategy for logging, can be for both training and prediction dataset.
| Fields | |
|---|---|
random_sample_config |
Random sample config. Will support more sampling strategies later. |
RandomSampleConfig
Requests are randomly selected.
| Fields | |
|---|---|
sample_rate |
Sample rate (0, 1] |
SavedQuery
A SavedQuery is a view of the dataset. It references a subset of annotations by problem type and filters.
| Fields | |
|---|---|
name |
Output only. Resource name of the SavedQuery. |
display_name |
Required. The user-defined name of the SavedQuery. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
metadata |
Some additional information about the SavedQuery. |
create_time |
Output only. Timestamp when this SavedQuery was created. |
update_time |
Output only. Timestamp when SavedQuery was last updated. |
annotation_filter |
Output only. Filters on the Annotations in the dataset. |
problem_type |
Required. Problem type of the SavedQuery. Allowed values:
|
annotation_spec_count |
Output only. Number of AnnotationSpecs in the context of the SavedQuery. |
etag |
Used to perform a consistent read-modify-write update. If not set, a blind "overwrite" update happens. |
support_automl_training |
Output only. If the Annotations belonging to the SavedQuery can be used for AutoML training. |
Scalar
One point viewable on a scalar metric plot.
| Fields | |
|---|---|
value |
Value of the point at this step / timestamp. |
Schedule
An instance of a Schedule periodically schedules runs to make API calls based on user specified time specification and API request type.
| Fields | |
|---|---|
name |
Immutable. The resource name of the Schedule. |
display_name |
Required. User provided name of the Schedule. The name can be up to 128 characters long and can consist of any UTF-8 characters. |
start_time |
Optional. Timestamp after which the first run can be scheduled. Default to Schedule create time if not specified. |
end_time |
Optional. Timestamp after which no new runs can be scheduled. If specified, The schedule will be completed when either end_time is reached or when scheduled_run_count >= max_run_count. If not specified, new runs will keep getting scheduled until this Schedule is paused or deleted. Already scheduled runs will be allowed to complete. Unset if not specified. |
max_run_count |
Optional. Maximum run count of the schedule. If specified, The schedule will be completed when either started_run_count >= max_run_count or when end_time is reached. If not specified, new runs will keep getting scheduled until this Schedule is paused or deleted. Already scheduled runs will be allowed to complete. Unset if not specified. |
started_run_count |
Output only. The number of runs started by this schedule. |
state |
Output only. The state of this Schedule. |
create_time |
Output only. Timestamp when this Schedule was created. |
update_time |
Output only. Timestamp when this Schedule was updated. |
next_run_time |
Output only. Timestamp when this Schedule should schedule the next run. Having a next_run_time in the past means the runs are being started behind schedule. |
last_pause_time |
Output only. Timestamp when this Schedule was last paused. Unset if never paused. |
last_resume_time |
Output only. Timestamp when this Schedule was last resumed. Unset if never resumed from pause. |
max_concurrent_run_count |
Required. Maximum number of runs that can be started concurrently for this Schedule. This is the limit for starting the scheduled requests and not the execution of the operations/jobs created by the requests (if applicable). |
allow_queueing |
Optional. Whether new scheduled runs can be queued when max_concurrent_runs limit is reached. If set to true, new runs will be queued instead of skipped. Default to false. |
catch_up |
Output only. Whether to backfill missed runs when the schedule is resumed from PAUSED state. If set to true, all missed runs will be scheduled. New runs will be scheduled after the backfill is complete. Default to false. |
last_scheduled_run_response |
Output only. Response of the last scheduled run. This is the response for starting the scheduled requests and not the execution of the operations/jobs created by the requests (if applicable). Unset if no run has been scheduled yet. |
Union field time_specification. Required. The time specification to launch scheduled runs. time_specification can be only one of the following: |
|
cron |
Cron schedule (https://en.wikipedia.org/wiki/Cron) to launch scheduled runs. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: "CRON_TZ=${IANA_TIME_ZONE}" or "TZ=${IANA_TIME_ZONE}". The ${IANA_TIME_ZONE} may only be a valid string from IANA time zone database. For example, "CRON_TZ=America/New_York 1 * * * *", or "TZ=America/New_York 1 * * * *". |
Union field request. Required. The API request template to launch the scheduled runs. User-specified ID is not supported in the request template. request can be only one of the following: |
|
create_pipeline_job_request |
Request for |
create_model_monitoring_job_request |
Request for |
create_notebook_execution_job_request |
Request for |
RunResponse
Status of a scheduled run.
| Fields | |
|---|---|
scheduled_run_time |
The scheduled run time based on the user-specified schedule. |
run_response |
The response of the scheduled run. |
State
Possible state of the schedule.
| Enums | |
|---|---|
STATE_UNSPECIFIED |
Unspecified. |
ACTIVE |
The Schedule is active. Runs are being scheduled on the user-specified timespec. |
PAUSED |
The schedule is paused. No new runs will be created until the schedule is resumed. Already started runs will be allowed to complete. |
COMPLETED |
The Schedule is completed. No new runs will be scheduled. Already started runs will be allowed to complete. Schedules in completed state cannot be paused or resumed. |
ScheduleConfig
Schedule configuration for the FeatureMonitor.
| Fields | |
|---|---|
cron |
Cron schedule (https://en.wikipedia.org/wiki/Cron) to launch scheduled runs. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: "CRON_TZ=${IANA_TIME_ZONE}" or "TZ=${IANA_TIME_ZONE}". The ${IANA_TIME_ZONE} may only be a valid string from IANA time zone database. For example, "CRON_TZ=America/New_York 1 * * * *", or "TZ=America/New_York 1 * * * *". |
Scheduling
All parameters related to queuing and scheduling of custom jobs.
| Fields | |
|---|---|
timeout |
Optional. The maximum job running time. The default is 7 days. |
restart_job_on_worker_restart |
Optional. Restarts the entire CustomJob if a worker gets restarted. This feature can be used by distributed training jobs that are not resilient to workers leaving and joining a job. |
strategy |
Optional. This determines which type of scheduling strategy to use. |
disable_retries |
Optional. Indicates if the job should retry for internal errors after the job starts running. If true, overrides |
max_wait_duration |
Optional. This is the maximum duration that a job will wait for the requested resources to be provisioned if the scheduling strategy is set to [Strategy.DWS_FLEX_START]. If set to 0, the job will wait indefinitely. The default is 24 hours. |
Strategy
Optional. This determines which type of scheduling strategy to use. Right now users have two options such as STANDARD which will use regular on demand resources to schedule the job, the other is SPOT which would leverage spot resources alongwith regular resources to schedule the job.
| Enums | |
|---|---|
STRATEGY_UNSPECIFIED |
Strategy will default to STANDARD. |
ON_DEMAND |
Deprecated. Regular on-demand provisioning strategy. |
LOW_COST |
Deprecated. Low cost by making potential use of spot resources. |
STANDARD |
Standard provisioning strategy uses regular on-demand resources. |
SPOT |
Spot provisioning strategy uses spot resources. |
FLEX_START |
Flex Start strategy uses DWS to queue for resources. |
Schema
Schema is used to define the format of input/output data. Represents a select subset of an OpenAPI 3.0 schema object. More fields may be added in the future as needed.
| Fields | |
|---|---|
type |
Optional. The type of the data. |
format |
Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc |
title |
Optional. The title of the Schema. |
description |
Optional. The description of the data. |
nullable |
Optional. Indicates if the value may be null. |
default |
Optional. Default value of the data. |
items |
Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. |
min_items |
Optional. Minimum number of the elements for Type.ARRAY. |
max_items |
Optional. Maximum number of the elements for Type.ARRAY. |
enum[] |
Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]} |
properties |
Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. |
property_ordering[] |
Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties. |
required[] |
Optional. Required properties of Type.OBJECT. |
min_properties |
Optional. Minimum number of the properties for Type.OBJECT. |
max_properties |
Optional. Maximum number of the properties for Type.OBJECT. |
minimum |
Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER |
maximum |
Optional. Maximum value of the Type.INTEGER and Type.NUMBER |
min_length |
Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING |
max_length |
Optional. Maximum length of the Type.STRING |
pattern |
Optional. Pattern of the Type.STRING to restrict a string to a regular expression. |
example |
Optional. Example of the object. Will only populated when the object is the root. |
any_of[] |
Optional. The value should be validated against any (one or more) of the subschemas in the list. |
SearchDataItemsRequest
Request message for DatasetService.SearchDataItems.
| Fields | |
|---|---|
dataset |
Required. The resource name of the Dataset from which to search DataItems. Format: |
saved_query |
The resource name of a SavedQuery(annotation set in UI). Format: |
data_labeling_job |
The resource name of a DataLabelingJob. Format: |
data_item_filter |
An expression for filtering the DataItem that will be returned.
For example:
|
annotations_filter |
An expression for filtering the Annotations that will be returned per DataItem. * |
annotation_filters[] |
An expression that specifies what Annotations will be returned per DataItem. Annotations satisfied either of the conditions will be returned. * |
field_mask |
Mask specifying which fields of |
annotations_limit |
If set, only up to this many of Annotations will be returned per DataItemView. The maximum value is 1000. If not set, the maximum value will be used. |
page_size |
Requested page size. Server may return fewer results than requested. Default and maximum page size is 100. |
order_by |
A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. |
page_token |
A token identifying a page of results for the server to return Typically obtained via |
Union field
|
|
order_by_data_item |
A comma-separated list of data item fields to order by, sorted in ascending order. Use "desc" after a field name for descending. |
order_by_annotation |
Expression that allows ranking results based on annotation's property. |
OrderByAnnotation
Expression that allows ranking results based on annotation's property.
| Fields | |
|---|---|
saved_query |
Required. Saved query of the Annotation. Only Annotations belong to this saved query will be considered for ordering. |
order_by |
A comma-separated list of annotation fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Must also specify saved_query. |
SearchDataItemsResponse
Response message for DatasetService.SearchDataItems.
| Fields | |
|---|---|
data_item_views[] |
The DataItemViews read. |
next_page_token |
A token to retrieve next page of results. Pass to |
SearchEntryPoint
Google search entry point.
| Fields | |
|---|---|
rendered_content |
Optional. Web content snippet that can be embedded in a web page or an app webview. |
sdk_blob |
Optional. Base64 encoded JSON representing array of <search term, search url> tuple. |
SearchFeaturesRequest
Request message for FeaturestoreService.SearchFeatures.
| Fields | |
|---|---|
location |
Required. The resource name of the Location to search Features. Format: |
query |
Query string that is a conjunction of field-restricted queries and/or field-restricted filters. Field-restricted queries and filters can be combined using A field query is in the form FIELD:QUERY. This implicitly checks if QUERY exists as a substring within Feature's FIELD. The QUERY and the FIELD are converted to a sequence of words (i.e. tokens) for comparison. This is done by:
A QUERY must be either a singular token or a phrase. A phrase is one or multiple words enclosed in double quotation marks ("). With phrases, the order of the words is important. Words in the phrase must be matching in order and consecutively. Supported FIELDs for field-restricted queries:
Examples:
Besides field queries, the following exact-match filters are supported. The exact-match filters do not support wildcards. Unlike field-restricted queries, exact-match filters are case-sensitive.
Examples:
|
page_size |
The maximum number of Features to return. The service may return fewer than this value. If unspecified, at most 100 Features will be returned. The maximum value is 100; any value greater than 100 will be coerced to 100. |
page_token |
A page token, received from a previous When paginating, all other parameters provided to |
SearchFeaturesResponse
Response message for FeaturestoreService.SearchFeatures.
| Fields | |
|---|---|
features[] |
The Features matching the request. Fields returned:
|
next_page_token |
A token, which can be sent as |
SearchMigratableResourcesRequest
Request message for MigrationService.SearchMigratableResources.
| Fields | |
|---|---|
parent |
Required. The location that the migratable resources should be searched from. It's the Vertex AI location that the resources can be migrated to, not the resources' original location. Format: |
page_size |
The standard page size. The default and maximum value is 100. |
page_token |
The standard page token. |
filter |
A filter for your search. You can use the following types of filters:
|
SearchMigratableResourcesResponse
Response message for MigrationService.SearchMigratableResources.
| Fields | |
|---|---|
migratable_resources[] |
All migratable resources that can be migrated to the location specified in the request. |
next_page_token |
The standard next-page token. The migratable_resources may not fill page_size in SearchMigratableResourcesRequest even when there are subsequent pages. |
SearchModelDeploymentMonitoringStatsAnomaliesRequest
Request message for JobService.SearchModelDeploymentMonitoringStatsAnomalies.
| Fields | |
|---|---|
model_deployment_monitoring_job |
Required. ModelDeploymentMonitoring Job resource name. Format: |
deployed_model_id |
Required. The DeployedModel ID of the [ModelDeploymentMonitoringObjectiveConfig.deployed_model_id]. |
feature_display_name |
The feature display name. If specified, only return the stats belonging to this feature. Format: |
objectives[] |
Required. Objectives of the stats to retrieve. |
page_size |
The standard list page size. |
page_token |
A page token received from a previous |
start_time |
The earliest timestamp of stats being generated. If not set, indicates fetching stats till the earliest possible one. |
end_time |
The latest timestamp of stats being generated. If not set, indicates feching stats till the latest possible one. |
StatsAnomaliesObjective
Stats requested for specific objective.
| Fields | |
|---|---|
type |
|
top_feature_count |
If set, all attribution scores between |
SearchModelDeploymentMonitoringStatsAnomaliesResponse
Response message for JobService.SearchModelDeploymentMonitoringStatsAnomalies.
| Fields | |
|---|---|
monitoring_stats[] |
Stats retrieved for requested objectives. There are at most 1000 |
next_page_token |
The page token that can be used by the next |
SearchModelMonitoringAlertsRequest
Request message for ModelMonitoringService.SearchModelMonitoringAlerts.
| Fields | |
|---|---|
model_monitor |
Required. ModelMonitor resource name. Format: |
model_monitoring_job |
If non-empty, returns the alerts of this model monitoring job. |
alert_time_interval |
If non-empty, returns the alerts in this time interval. |
stats_name |
If non-empty, returns the alerts of this stats_name. |
objective_type |
If non-empty, returns the alerts of this objective type. Supported monitoring objectives: |
page_size |
The standard list page size. |
page_token |
A page token received from a previous |
SearchModelMonitoringAlertsResponse
Response message for ModelMonitoringService.SearchModelMonitoringAlerts.
| Fields | |
|---|---|
model_monitoring_alerts[] |
Alerts retrieved for the requested objectives. Sorted by alert time descendingly. |
total_number_alerts |
The total number of alerts retrieved by the requested objectives. |
next_page_token |
The page token that can be used by the next |
SearchModelMonitoringStatsFilter
Filter for searching ModelMonitoringStats.
| Fields | |
|---|---|
Union field
|
|
tabular_stats_filter |
Tabular statistics filter. |
TabularStatsFilter
Tabular statistics filter.
| Fields | |
|---|---|
stats_name |
If not specified, will return all the stats_names. |
objective_type |
One of the supported monitoring objectives: |
model_monitoring_job |
From a particular monitoring job. |
model_monitoring_schedule |
From a particular monitoring schedule. |
algorithm |
Specify the algorithm type used for distance calculation, eg: jensen_shannon_divergence, l_infinity. |
SearchModelMonitoringStatsRequest
Request message for ModelMonitoringService.SearchModelMonitoringStats.
| Fields | |
|---|---|
model_monitor |
Required. ModelMonitor resource name. Format: |
stats_filter |
Filter for search different stats. |
time_interval |
The time interval for which results should be returned. |
page_size |
The standard list page size. |
page_token |
A page token received from a previous |
SearchModelMonitoringStatsResponse
Response message for ModelMonitoringService.SearchModelMonitoringStats.
| Fields | |
|---|---|
monitoring_stats[] |
Stats retrieved for requested objectives. |
next_page_token |
The page token that can be used by the next |
SearchNearestEntitiesRequest
The request message for FeatureOnlineStoreService.SearchNearestEntities.
| Fields | |
|---|---|
feature_view |
Required. FeatureView resource format |
query |
Required. The query. |
return_full_entity |
Optional. If set to true, the full entities (including all vector values and metadata) of the nearest neighbors are returned; otherwise only entity id of the nearest neighbors will be returned. Note that returning full entities will significantly increase the latency and cost of the query. |
SearchNearestEntitiesResponse
Response message for FeatureOnlineStoreService.SearchNearestEntities
| Fields | |
|---|---|
nearest_neighbors |
The nearest neighbors of the query entity. |
Segment
Segment of the content.
| Fields | |
|---|---|
part_index |
Output only. The index of a Part object within its parent Content object. |
start_index |
Output only. Start index in the given Part, measured in bytes. Offset from the start of the Part, inclusive, starting at zero. |
end_index |
Output only. End index in the given Part, measured in bytes. Offset from the start of the Part, exclusive, starting at zero. |
text |
Output only. The text corresponding to the segment from the response. |
ServiceAccountSpec
Configuration for the use of custom service account to run the workloads.
| Fields | |
|---|---|
enable_custom_service_account |
Required. If true, custom user-managed service account is enforced to run any workloads (for example, Vertex Jobs) on the resource. Otherwise, uses the Vertex AI Custom Code Service Agent. |
service_account |
Optional. Required when all below conditions are met * The users must have Do not set this field if you want to submit jobs using custom service account to this PersistentResource after creation, but only specify the |
ShieldedVmConfig
A set of Shielded Instance options. See Images using supported Shielded VM features.
| Fields | |
|---|---|
enable_secure_boot |
Defines whether the instance has Secure Boot enabled. Secure Boot helps ensure that the system only runs authentic software by verifying the digital signature of all boot components, and halting the boot process if signature verification fails. |
SlackSource
The Slack source for the ImportRagFilesRequest.
| Fields | |
|---|---|
channels[] |
Required. The Slack channels. |
SlackChannels
SlackChannels contains the Slack channels and corresponding access token.
| Fields | |
|---|---|
channels[] |
Required. The Slack channel IDs. |
api_key_config |
Required. The SecretManager secret version resource name (e.g. projects/{project}/secrets/{secret}/versions/{version}) storing the Slack channel access token that has access to the slack channel IDs. See: https://api.slack.com/tutorials/tracks/getting-a-token. |
SlackChannel
SlackChannel contains the Slack channel ID and the time range to import.
| Fields | |
|---|---|
channel_id |
Required. The Slack channel ID. |
start_time |
Optional. The starting timestamp for messages to import. |
end_time |
Optional. The ending timestamp for messages to import. |
SmoothGradConfig
Config for SmoothGrad approximation of gradients.
When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
| Fields | |
|---|---|
noisy_sample_count |
The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3. |
Union field GradientNoiseSigma. Represents the standard deviation of the gaussian kernel that will be used to add noise to the interpolated inputs prior to computing gradients. GradientNoiseSigma can be only one of the following: |
|
noise_sigma |
This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about normalization. For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set |
feature_noise_sigma |
This is similar to |
SpecialistPool
SpecialistPool represents customers' own workforce to work on their data labeling jobs. It includes a group of specialist managers and workers. Managers are responsible for managing the workers in this pool as well as customers' data labeling jobs associated with this pool. Customers create specialist pool as well as start data labeling jobs on Cloud, managers and workers handle the jobs using CrowdCompute console.
| Fields | |
|---|---|
name |
Required. The resource name of the SpecialistPool. |
display_name |
Required. The user-defined name of the SpecialistPool. The name can be up to 128 characters long and can consist of any UTF-8 characters. This field should be unique on project-level. |
specialist_managers_count |
Output only. The number of managers in this SpecialistPool. |
specialist_manager_emails[] |
The email addresses of the managers in the SpecialistPool. |
pending_data_labeling_jobs[] |
Output only. The resource name of the pending data labeling jobs. |
specialist_worker_emails[] |
The email addresses of workers in the SpecialistPool. |
SpeechConfig
The speech generation config.
| Fields | |
|---|---|
voice_config |
The configuration for the speaker to use. |
StartNotebookRuntimeOperationMetadata
Metadata information for NotebookService.StartNotebookRuntime.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
progress_message |
A human-readable message that shows the intermediate progress details of NotebookRuntime. |
StartNotebookRuntimeRequest
Request message for NotebookService.StartNotebookRuntime.
| Fields | |
|---|---|
name |
Required. The name of the NotebookRuntime resource to be started. Instead of checking whether the name is in valid NotebookRuntime resource name format, directly throw NotFound exception if there is no such NotebookRuntime in spanner. |
StartNotebookRuntimeResponse
This type has no fields.
Response message for NotebookService.StartNotebookRuntime.
StopNotebookRuntimeOperationMetadata
Metadata information for NotebookService.StopNotebookRuntime.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
StopNotebookRuntimeRequest
Request message for NotebookService.StopNotebookRuntime.
| Fields | |
|---|---|
name |
Required. The name of the NotebookRuntime resource to be stopped. Instead of checking whether the name is in valid NotebookRuntime resource name format, directly throw NotFound exception if there is no such NotebookRuntime in spanner. |
StopNotebookRuntimeResponse
This type has no fields.
Response message for NotebookService.StopNotebookRuntime.
StopTrialRequest
Request message for VizierService.StopTrial.
| Fields | |
|---|---|
name |
Required. The Trial's name. Format: |
StratifiedSplit
Assigns input data to the training, validation, and test sets so that the distribution of values found in the categorical column (as specified by the key field) is mirrored within each split. The fraction values determine the relative sizes of the splits.
For example, if the specified column has three values, with 50% of the rows having value "A", 25% value "B", and 25% value "C", and the split fractions are specified as 80/10/10, then the training set will constitute 80% of the training data, with about 50% of the training set rows having the value "A" for the specified column, about 25% having the value "B", and about 25% having the value "C".
Only the top 500 occurring values are used; any values not in the top 500 values are randomly assigned to a split. If less than three rows contain a specific value, those rows are randomly assigned.
Supported only for tabular Datasets.
| Fields | |
|---|---|
training_fraction |
The fraction of the input data that is to be used to train the Model. |
validation_fraction |
The fraction of the input data that is to be used to validate the Model. |
test_fraction |
The fraction of the input data that is to be used to evaluate the Model. |
key |
Required. The key is a name of one of the Dataset's data columns. The key provided must be for a categorical column. |
StreamDirectPredictRequest
Request message for PredictionService.StreamDirectPredict.
The first message must contain endpoint field and optionally [input][]. The subsequent messages must contain [input][].
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to serve the prediction. Format: |
inputs[] |
Optional. The prediction input. |
parameters |
Optional. The parameters that govern the prediction. |
StreamDirectPredictResponse
Response message for PredictionService.StreamDirectPredict.
| Fields | |
|---|---|
outputs[] |
The prediction output. |
parameters |
The parameters that govern the prediction. |
StreamDirectRawPredictRequest
Request message for PredictionService.StreamDirectRawPredict.
The first message must contain endpoint and method_name fields and optionally input. The subsequent messages must contain input. method_name in the subsequent messages have no effect.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to serve the prediction. Format: |
method_name |
Optional. Fully qualified name of the API method being invoked to perform predictions. Format: |
input |
Optional. The prediction input. |
StreamDirectRawPredictResponse
Response message for PredictionService.StreamDirectRawPredict.
| Fields | |
|---|---|
output |
The prediction output. |
StreamQueryReasoningEngineRequest
Request message for [ReasoningEngineExecutionService.StreamQuery][].
| Fields | |
|---|---|
name |
Required. The name of the ReasoningEngine resource to use. Format: |
input |
Optional. Input content provided by users in JSON object format. Examples include text query, function calling parameters, media bytes, etc. |
class_method |
Optional. Class method to be used for the stream query. It is optional and defaults to "stream_query" if unspecified. |
StreamRawPredictRequest
Request message for PredictionService.StreamRawPredict.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to serve the prediction. Format: |
http_body |
The prediction input. Supports HTTP headers and arbitrary data payload. |
StreamingFetchFeatureValuesRequest
Request message for FeatureOnlineStoreService.StreamingFetchFeatureValues. For the entities requested, all features under the requested feature view will be returned.
| Fields | |
|---|---|
feature_view |
Required. FeatureView resource format |
data_keys[] |
|
data_format |
Specify response data format. If not set, KeyValue format will be used. |
StreamingFetchFeatureValuesResponse
Response message for FeatureOnlineStoreService.StreamingFetchFeatureValues.
| Fields | |
|---|---|
status |
Response status. If OK, then |
data[] |
|
data_keys_with_error[] |
|
StreamingPredictRequest
Request message for PredictionService.StreamingPredict.
The first message must contain endpoint field and optionally [input][]. The subsequent messages must contain [input][].
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to serve the prediction. Format: |
inputs[] |
The prediction input. |
parameters |
The parameters that govern the prediction. |
StreamingPredictResponse
Response message for PredictionService.StreamingPredict.
| Fields | |
|---|---|
outputs[] |
The prediction output. |
parameters |
The parameters that govern the prediction. |
StreamingRawPredictRequest
Request message for PredictionService.StreamingRawPredict.
The first message must contain endpoint and method_name fields and optionally input. The subsequent messages must contain input. method_name in the subsequent messages have no effect.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint requested to serve the prediction. Format: |
method_name |
Fully qualified name of the API method being invoked to perform predictions. Format: |
input |
The prediction input. |
StreamingRawPredictResponse
Response message for PredictionService.StreamingRawPredict.
| Fields | |
|---|---|
output |
The prediction output. |
StreamingReadFeatureValuesRequest
Request message for FeaturestoreOnlineServingService.StreamingReadFeatureValues.
| Fields | |
|---|---|
entity_type |
Required. The resource name of the entities' type. Value format: |
entity_ids[] |
Required. IDs of entities to read Feature values of. The maximum number of IDs is 100. For example, for a machine learning model predicting user clicks on a website, an entity ID could be |
feature_selector |
Required. Selector choosing Features of the target EntityType. Feature IDs will be deduplicated. |
StringArray
A list of string values.
| Fields | |
|---|---|
values[] |
A list of string values. |
StructFieldValue
One field of a Struct (or object) type feature value.
| Fields | |
|---|---|
name |
Name of the field in the struct feature. |
value |
The value for this field. |
StructValue
Struct (or object) type feature value.
| Fields | |
|---|---|
values[] |
A list of field values. |
Study
A message representing a Study.
| Fields | |
|---|---|
name |
Output only. The name of a study. The study's globally unique identifier. Format: |
display_name |
Required. Describes the Study, default value is empty string. |
study_spec |
Required. Configuration of the Study. |
state |
Output only. The detailed state of a Study. |
create_time |
Output only. Time at which the study was created. |
inactive_reason |
Output only. A human readable reason why the Study is inactive. This should be empty if a study is ACTIVE or COMPLETED. |
State
Describes the Study state.
| Enums | |
|---|---|
STATE_UNSPECIFIED |
The study state is unspecified. |
ACTIVE |
The study is active. |
INACTIVE |
The study is stopped due to an internal error. |
COMPLETED |
The study is done when the service exhausts the parameter search space or max_trial_count is reached. |
StudySpec
Represents specification of a Study.
| Fields | |
|---|---|
metrics[] |
Required. Metric specs for the Study. |
parameters[] |
Required. The set of parameters to tune. |
algorithm |
The search algorithm specified for the Study. |
observation_noise |
The observation noise level of the study. Currently only supported by the Vertex AI Vizier service. Not supported by HyperparameterTuningJob or TrainingPipeline. |
measurement_selection_type |
Describe which measurement selection type will be used |
transfer_learning_config |
The configuration info/options for transfer learning. Currently supported for Vertex AI Vizier service, not HyperParameterTuningJob |
Union field
|
|
decay_curve_stopping_spec |
The automated early stopping spec using decay curve rule. |
median_automated_stopping_spec |
The automated early stopping spec using median rule. |
convex_stop_config |
Deprecated. The automated early stopping using convex stopping rule. |
convex_automated_stopping_spec |
The automated early stopping spec using convex stopping rule. |
study_stopping_config |
Conditions for automated stopping of a Study. Enable automated stopping by configuring at least one condition. |
Algorithm
The available search algorithms for the Study.
| Enums | |
|---|---|
ALGORITHM_UNSPECIFIED |
The default algorithm used by Vertex AI for hyperparameter tuning and Vertex AI Vizier. |
GRID_SEARCH |
Simple grid search within the feasible space. To use grid search, all parameters must be INTEGER, CATEGORICAL, or DISCRETE. |
RANDOM_SEARCH |
Simple random search within the feasible space. |
ConvexAutomatedStoppingSpec
Configuration for ConvexAutomatedStoppingSpec. When there are enough completed trials (configured by min_measurement_count), for pending trials with enough measurements and steps, the policy first computes an overestimate of the objective value at max_num_steps according to the slope of the incomplete objective value curve. No prediction can be made if the curve is completely flat. If the overestimation is worse than the best objective value of the completed trials, this pending trial will be early-stopped, but a last measurement will be added to the pending trial with max_num_steps and predicted objective value from the autoregression model.
| Fields | |
|---|---|
max_step_count |
Steps used in predicting the final objective for early stopped trials. In general, it's set to be the same as the defined steps in training / tuning. If not defined, it will learn it from the completed trials. When use_steps is false, this field is set to the maximum elapsed seconds. |
min_step_count |
Minimum number of steps for a trial to complete. Trials which do not have a measurement with step_count > min_step_count won't be considered for early stopping. It's ok to set it to 0, and a trial can be early stopped at any stage. By default, min_step_count is set to be one-tenth of the max_step_count. When use_elapsed_duration is true, this field is set to the minimum elapsed seconds. |
min_measurement_count |
The minimal number of measurements in a Trial. Early-stopping checks will not trigger if less than min_measurement_count+1 completed trials or pending trials with less than min_measurement_count measurements. If not defined, the default value is 5. |
learning_rate_parameter_name |
The hyper-parameter name used in the tuning job that stands for learning rate. Leave it blank if learning rate is not in a parameter in tuning. The learning_rate is used to estimate the objective value of the ongoing trial. |
use_elapsed_duration |
This bool determines whether or not the rule is applied based on elapsed_secs or steps. If use_elapsed_duration==false, the early stopping decision is made according to the predicted objective values according to the target steps. If use_elapsed_duration==true, elapsed_secs is used instead of steps. Also, in this case, the parameters max_num_steps and min_num_steps are overloaded to contain max_elapsed_seconds and min_elapsed_seconds. |
update_all_stopped_trials |
ConvexAutomatedStoppingSpec by default only updates the trials that needs to be early stopped using a newly trained auto-regressive model. When this flag is set to True, all stopped trials from the beginning are potentially updated in terms of their |
ConvexStopConfig
Configuration for ConvexStopPolicy.
| Fields | |
|---|---|
max_num_steps |
Steps used in predicting the final objective for early stopped trials. In general, it's set to be the same as the defined steps in training / tuning. When use_steps is false, this field is set to the maximum elapsed seconds. |
min_num_steps |
Minimum number of steps for a trial to complete. Trials which do not have a measurement with num_steps > min_num_steps won't be considered for early stopping. It's ok to set it to 0, and a trial can be early stopped at any stage. By default, min_num_steps is set to be one-tenth of the max_num_steps. When use_steps is false, this field is set to the minimum elapsed seconds. |
autoregressive_order |
The number of Trial measurements used in autoregressive model for value prediction. A trial won't be considered early stopping if has fewer measurement points. |
learning_rate_parameter_name |
The hyper-parameter name used in the tuning job that stands for learning rate. Leave it blank if learning rate is not in a parameter in tuning. The learning_rate is used to estimate the objective value of the ongoing trial. |
use_seconds |
This bool determines whether or not the rule is applied based on elapsed_secs or steps. If use_seconds==false, the early stopping decision is made according to the predicted objective values according to the target steps. If use_seconds==true, elapsed_secs is used instead of steps. Also, in this case, the parameters max_num_steps and min_num_steps are overloaded to contain max_elapsed_seconds and min_elapsed_seconds. |
DecayCurveAutomatedStoppingSpec
The decay curve automated stopping rule builds a Gaussian Process Regressor to predict the final objective value of a Trial based on the already completed Trials and the intermediate measurements of the current Trial. Early stopping is requested for the current Trial if there is very low probability to exceed the optimal value found so far.
| Fields | |
|---|---|
use_elapsed_duration |
True if |
MeasurementSelectionType
This indicates which measurement to use if/when the service automatically selects the final measurement from previously reported intermediate measurements. Choose this based on two considerations: A) Do you expect your measurements to monotonically improve? If so, choose LAST_MEASUREMENT. On the other hand, if you're in a situation where your system can "over-train" and you expect the performance to get better for a while but then start declining, choose BEST_MEASUREMENT. B) Are your measurements significantly noisy and/or irreproducible? If so, BEST_MEASUREMENT will tend to be over-optimistic, and it may be better to choose LAST_MEASUREMENT. If both or neither of (A) and (B) apply, it doesn't matter which selection type is chosen.
| Enums | |
|---|---|
MEASUREMENT_SELECTION_TYPE_UNSPECIFIED |
Will be treated as LAST_MEASUREMENT. |
LAST_MEASUREMENT |
Use the last measurement reported. |
BEST_MEASUREMENT |
Use the best measurement reported. |
MedianAutomatedStoppingSpec
The median automated stopping rule stops a pending Trial if the Trial's best objective_value is strictly below the median 'performance' of all completed Trials reported up to the Trial's last measurement. Currently, 'performance' refers to the running average of the objective values reported by the Trial in each measurement.
| Fields | |
|---|---|
use_elapsed_duration |
True if median automated stopping rule applies on |
MetricSpec
Represents a metric to optimize.
| Fields | |
|---|---|
metric_id |
Required. The ID of the metric. Must not contain whitespaces and must be unique amongst all MetricSpecs. |
goal |
Required. The optimization goal of the metric. |
safety_config |
Used for safe search. In the case, the metric will be a safety metric. You must provide a separate metric for objective metric. |
GoalType
The available types of optimization goals.
| Enums | |
|---|---|
GOAL_TYPE_UNSPECIFIED |
Goal Type will default to maximize. |
MAXIMIZE |
Maximize the goal metric. |
MINIMIZE |
Minimize the goal metric. |
SafetyMetricConfig
Used in safe optimization to specify threshold levels and risk tolerance.
| Fields | |
|---|---|
safety_threshold |
Safety threshold (boundary value between safe and unsafe). NOTE that if you leave SafetyMetricConfig unset, a default value of 0 will be used. |
desired_min_safe_trials_fraction |
Desired minimum fraction of safe trials (over total number of trials) that should be targeted by the algorithm at any time during the study (best effort). This should be between 0.0 and 1.0 and a value of 0.0 means that there is no minimum and an algorithm proceeds without targeting any specific fraction. A value of 1.0 means that the algorithm attempts to only Suggest safe Trials. |
ObservationNoise
Describes the noise level of the repeated observations.
"Noisy" means that the repeated observations with the same Trial parameters may lead to different metric evaluations.
| Enums | |
|---|---|
OBSERVATION_NOISE_UNSPECIFIED |
The default noise level chosen by Vertex AI. |
LOW |
Vertex AI assumes that the objective function is (nearly) perfectly reproducible, and will never repeat the same Trial parameters. |
HIGH |
Vertex AI will estimate the amount of noise in metric evaluations, it may repeat the same Trial parameters more than once. |
ParameterSpec
Represents a single parameter to optimize.
| Fields | |
|---|---|
parameter_id |
Required. The ID of the parameter. Must not contain whitespaces and must be unique amongst all ParameterSpecs. |
scale_type |
How the parameter should be scaled. Leave unset for |
conditional_parameter_specs[] |
A conditional parameter node is active if the parameter's value matches the conditional node's parent_value_condition. If two items in conditional_parameter_specs have the same name, they must have disjoint parent_value_condition. |
Union field
|
|
double_value_spec |
The value spec for a 'DOUBLE' parameter. |
integer_value_spec |
The value spec for an 'INTEGER' parameter. |
categorical_value_spec |
The value spec for a 'CATEGORICAL' parameter. |
discrete_value_spec |
The value spec for a 'DISCRETE' parameter. |
CategoricalValueSpec
Value specification for a parameter in CATEGORICAL type.
| Fields | |
|---|---|
values[] |
Required. The list of possible categories. |
default_value |
A default value for a Currently only supported by the Vertex AI Vizier service. Not supported by HyperparameterTuningJob or TrainingPipeline. |
ConditionalParameterSpec
Represents a parameter spec with condition from its parent parameter.
| Fields | |
|---|---|
parameter_spec |
Required. The spec for a conditional parameter. |
Union field parent_value_condition. A set of parameter values from the parent ParameterSpec's feasible space. parent_value_condition can be only one of the following: |
|
parent_discrete_values |
The spec for matching values from a parent parameter of |
parent_int_values |
The spec for matching values from a parent parameter of |
parent_categorical_values |
The spec for matching values from a parent parameter of |
CategoricalValueCondition
Represents the spec to match categorical values from parent parameter.
| Fields | |
|---|---|
values[] |
Required. Matches values of the parent parameter of 'CATEGORICAL' type. All values must exist in |
DiscreteValueCondition
Represents the spec to match discrete values from parent parameter.
| Fields | |
|---|---|
values[] |
Required. Matches values of the parent parameter of 'DISCRETE' type. All values must exist in The Epsilon of the value matching is 1e-10. |
IntValueCondition
Represents the spec to match integer values from parent parameter.
| Fields | |
|---|---|
values[] |
Required. Matches values of the parent parameter of 'INTEGER' type. All values must lie in |
DiscreteValueSpec
Value specification for a parameter in DISCRETE type.
| Fields | |
|---|---|
values[] |
Required. A list of possible values. The list should be in increasing order and at least 1e-10 apart. For instance, this parameter might have possible settings of 1.5, 2.5, and 4.0. This list should not contain more than 1,000 values. |
default_value |
A default value for a Currently only supported by the Vertex AI Vizier service. Not supported by HyperparameterTuningJob or TrainingPipeline. |
DoubleValueSpec
Value specification for a parameter in DOUBLE type.
| Fields | |
|---|---|
min_value |
Required. Inclusive minimum value of the parameter. |
max_value |
Required. Inclusive maximum value of the parameter. |
default_value |
A default value for a Currently only supported by the Vertex AI Vizier service. Not supported by HyperparameterTuningJob or TrainingPipeline. |
IntegerValueSpec
Value specification for a parameter in INTEGER type.
| Fields | |
|---|---|
min_value |
Required. Inclusive minimum value of the parameter. |
max_value |
Required. Inclusive maximum value of the parameter. |
default_value |
A default value for an Currently only supported by the Vertex AI Vizier service. Not supported by HyperparameterTuningJob or TrainingPipeline. |
ScaleType
The type of scaling that should be applied to this parameter.
| Enums | |
|---|---|
SCALE_TYPE_UNSPECIFIED |
By default, no scaling is applied. |
UNIT_LINEAR_SCALE |
Scales the feasible space to (0, 1) linearly. |
UNIT_LOG_SCALE |
Scales the feasible space logarithmically to (0, 1). The entire feasible space must be strictly positive. |
UNIT_REVERSE_LOG_SCALE |
Scales the feasible space "reverse" logarithmically to (0, 1). The result is that values close to the top of the feasible space are spread out more than points near the bottom. The entire feasible space must be strictly positive. |
StudyStoppingConfig
The configuration (stopping conditions) for automated stopping of a Study. Conditions include trial budgets, time budgets, and convergence detection.
| Fields | |
|---|---|
should_stop_asap |
If true, a Study enters STOPPING_ASAP whenever it would normally enters STOPPING state. The bottom line is: set to true if you want to interrupt on-going evaluations of Trials as soon as the study stopping condition is met. (Please see Study.State documentation for the source of truth). |
minimum_runtime_constraint |
Each "stopping rule" in this proto specifies an "if" condition. Before Vizier would generate a new suggestion, it first checks each specified stopping rule, from top to bottom in this list. Note that the first few rules (e.g. minimum_runtime_constraint, min_num_trials) will prevent other stopping rules from being evaluated until they are met. For example, setting |
maximum_runtime_constraint |
If the specified time or duration has passed, stop the study. |
min_num_trials |
If there are fewer than this many COMPLETED trials, do not stop the study. |
max_num_trials |
If there are more than this many trials, stop the study. |
max_num_trials_no_progress |
If the objective value has not improved for this many consecutive trials, stop the study. WARNING: Effective only for single-objective studies. |
max_duration_no_progress |
If the objective value has not improved for this much time, stop the study. WARNING: Effective only for single-objective studies. |
TransferLearningConfig
This contains flag for manually disabling transfer learning for a study. The names of prior studies being used for transfer learning (if any) are also listed here.
| Fields | |
|---|---|
disable_transfer_learning |
Flag to to manually prevent vizier from using transfer learning on a new study. Otherwise, vizier will automatically determine whether or not to use transfer learning. |
prior_study_names[] |
Output only. Names of previously completed studies |
StudyTimeConstraint
Time-based Constraint for Study
| Fields | |
|---|---|
Union field
|
|
max_duration |
Counts the wallclock time passed since the creation of this Study. |
end_time |
Compares the wallclock time to this time. Must use UTC timezone. |
SuggestTrialsMetadata
Details of operations that perform Trials suggestion.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for suggesting Trials. |
client_id |
The identifier of the client that is requesting the suggestion. If multiple SuggestTrialsRequests have the same |
SuggestTrialsRequest
Request message for VizierService.SuggestTrials.
| Fields | |
|---|---|
parent |
Required. The project and location that the Study belongs to. Format: |
suggestion_count |
Required. The number of suggestions requested. It must be positive. |
client_id |
Required. The identifier of the client that is requesting the suggestion. If multiple SuggestTrialsRequests have the same |
contexts[] |
Optional. This allows you to specify the "context" for a Trial; a context is a slice (a subspace) of the search space. Typical uses for contexts: 1) You are using Vizier to tune a server for best performance, but there's a strong weekly cycle. The context specifies the day-of-week. This allows Tuesday to generalize from Wednesday without assuming that everything is identical. 2) Imagine you're optimizing some medical treatment for people. As they walk in the door, you know certain facts about them (e.g. sex, weight, height, blood-pressure). Put that information in the context, and Vizier will adapt its suggestions to the patient. 3) You want to do a fair A/B test efficiently. Specify the "A" and "B" conditions as contexts, and Vizier will generalize between "A" and "B" conditions. If they are similar, this will allow Vizier to converge to the optimum faster than if "A" and "B" were separate Studies. NOTE: You can also enter contexts as REQUESTED Trials, e.g. via the CreateTrial() RPC; that's the asynchronous option where you don't need a close association between contexts and suggestions. NOTE: All the Parameters you set in a context MUST be defined in the Study. NOTE: You must supply 0 or $suggestion_count contexts. If you don't supply any contexts, Vizier will make suggestions from the full search space specified in the StudySpec; if you supply a full set of context, each suggestion will match the corresponding context. NOTE: A Context with no features set matches anything, and allows suggestions from the full search space. NOTE: Contexts MUST lie within the search space specified in the StudySpec. It's an error if they don't. NOTE: Contexts preferentially match ACTIVE then REQUESTED trials before new suggestions are generated. NOTE: Generation of suggestions involves a match between a Context and (optionally) a REQUESTED trial; if that match is not fully specified, a suggestion will be geneated in the merged subspace. |
SuggestTrialsResponse
Response message for VizierService.SuggestTrials.
| Fields | |
|---|---|
trials[] |
A list of Trials. |
study_state |
The state of the Study. |
start_time |
The time at which the operation was started. |
end_time |
The time at which operation processing completed. |
SummarizationHelpfulnessInput
Input for summarization helpfulness metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for summarization helpfulness score metric. |
instance |
Required. Summarization helpfulness instance. |
SummarizationHelpfulnessInstance
Spec for summarization helpfulness instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Optional. Ground truth used to compare against the prediction. |
context |
Required. Text to be summarized. |
instruction |
Optional. Summarization prompt for LLM. |
SummarizationHelpfulnessResult
Spec for summarization helpfulness result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for summarization helpfulness score. |
score |
Output only. Summarization Helpfulness score. |
confidence |
Output only. Confidence for summarization helpfulness score. |
SummarizationHelpfulnessSpec
Spec for summarization helpfulness score metric.
| Fields | |
|---|---|
use_reference |
Optional. Whether to use instance.reference to compute summarization helpfulness. |
version |
Optional. Which version to use for evaluation. |
SummarizationQualityInput
Input for summarization quality metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for summarization quality score metric. |
instance |
Required. Summarization quality instance. |
SummarizationQualityInstance
Spec for summarization quality instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Optional. Ground truth used to compare against the prediction. |
context |
Required. Text to be summarized. |
instruction |
Required. Summarization prompt for LLM. |
SummarizationQualityResult
Spec for summarization quality result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for summarization quality score. |
score |
Output only. Summarization Quality score. |
confidence |
Output only. Confidence for summarization quality score. |
SummarizationQualitySpec
Spec for summarization quality score metric.
| Fields | |
|---|---|
use_reference |
Optional. Whether to use instance.reference to compute summarization quality. |
version |
Optional. Which version to use for evaluation. |
SummarizationVerbosityInput
Input for summarization verbosity metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for summarization verbosity score metric. |
instance |
Required. Summarization verbosity instance. |
SummarizationVerbosityInstance
Spec for summarization verbosity instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Optional. Ground truth used to compare against the prediction. |
context |
Required. Text to be summarized. |
instruction |
Optional. Summarization prompt for LLM. |
SummarizationVerbosityResult
Spec for summarization verbosity result.
| Fields | |
|---|---|
explanation |
Output only. Explanation for summarization verbosity score. |
score |
Output only. Summarization Verbosity score. |
confidence |
Output only. Confidence for summarization verbosity score. |
SummarizationVerbositySpec
Spec for summarization verbosity score metric.
| Fields | |
|---|---|
use_reference |
Optional. Whether to use instance.reference to compute summarization verbosity. |
version |
Optional. Which version to use for evaluation. |
SupervisedHyperParameters
Hyperparameters for SFT.
| Fields | |
|---|---|
epoch_count |
Optional. Number of complete passes the model makes over the entire training dataset during training. |
learning_rate_multiplier |
Optional. Multiplier for adjusting the default learning rate. |
adapter_size |
Optional. Adapter size for tuning. |
AdapterSize
Supported adapter sizes for tuning.
| Enums | |
|---|---|
ADAPTER_SIZE_UNSPECIFIED |
Adapter size is unspecified. |
ADAPTER_SIZE_ONE |
Adapter size 1. |
ADAPTER_SIZE_FOUR |
Adapter size 4. |
ADAPTER_SIZE_EIGHT |
Adapter size 8. |
ADAPTER_SIZE_SIXTEEN |
Adapter size 16. |
ADAPTER_SIZE_THIRTY_TWO |
Adapter size 32. |
SupervisedTuningDataStats
Tuning data statistics for Supervised Tuning.
| Fields | |
|---|---|
tuning_dataset_example_count |
Output only. Number of examples in the tuning dataset. |
total_tuning_character_count |
Output only. Number of tuning characters in the tuning dataset. |
total_billable_character_count |
Output only. Number of billable characters in the tuning dataset. |
total_billable_token_count |
Output only. Number of billable tokens in the tuning dataset. |
tuning_step_count |
Output only. Number of tuning steps for this Tuning Job. |
user_input_token_distribution |
Output only. Dataset distributions for the user input tokens. |
user_output_token_distribution |
Output only. Dataset distributions for the user output tokens. |
user_message_per_example_distribution |
Output only. Dataset distributions for the messages per example. |
user_dataset_examples[] |
Output only. Sample user messages in the training dataset uri. |
total_truncated_example_count |
Output only. The number of examples in the dataset that have been dropped. An example can be dropped for reasons including: too many tokens, contains an invalid image, contains too many images, etc. |
truncated_example_indices[] |
Output only. A partial sample of the indices (starting from 1) of the dropped examples. |
SupervisedTuningDatasetDistribution
Dataset distribution for Supervised Tuning.
| Fields | |
|---|---|
sum |
Output only. Sum of a given population of values. |
billable_sum |
Output only. Sum of a given population of values that are billable. |
min |
Output only. The minimum of the population values. |
max |
Output only. The maximum of the population values. |
mean |
Output only. The arithmetic mean of the values in the population. |
median |
Output only. The median of the values in the population. |
p5 |
Output only. The 5th percentile of the values in the population. |
p95 |
Output only. The 95th percentile of the values in the population. |
buckets[] |
Output only. Defines the histogram bucket. |
DatasetBucket
Dataset bucket used to create a histogram for the distribution given a population of values.
| Fields | |
|---|---|
count |
Output only. Number of values in the bucket. |
left |
Output only. Left bound of the bucket. |
right |
Output only. Right bound of the bucket. |
SupervisedTuningSpec
Tuning Spec for Supervised Tuning for first party models.
| Fields | |
|---|---|
training_dataset_uri |
Required. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file. |
validation_dataset_uri |
Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file. |
hyper_parameters |
Optional. Hyperparameters for SFT. |
SyncFeatureViewRequest
Request message for FeatureOnlineStoreAdminService.SyncFeatureView.
| Fields | |
|---|---|
feature_view |
Required. Format: |
SyncFeatureViewResponse
Response message for FeatureOnlineStoreAdminService.SyncFeatureView.
| Fields | |
|---|---|
feature_view_sync |
Format: |
TFRecordDestination
The storage details for TFRecord output content.
| Fields | |
|---|---|
gcs_destination |
Required. Google Cloud Storage location. |
Tensor
A tensor value type.
| Fields | |
|---|---|
dtype |
The data type of tensor. |
shape[] |
Shape of the tensor. |
bool_val[] |
Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to "dtype" can be set. The values hold the flattened representation of the tensor in row major order. |
string_val[] |
|
bytes_val[] |
|
float_val[] |
|
double_val[] |
|
int_val[] |
|
int64_val[] |
|
uint_val[] |
|
uint64_val[] |
|
list_val[] |
A list of tensor values. |
struct_val |
A map of string to tensor. |
tensor_val |
Serialized raw tensor content. |
DataType
Data type of the tensor.
| Enums | |
|---|---|
DATA_TYPE_UNSPECIFIED |
Not a legal value for DataType. Used to indicate a DataType field has not been set. |
BOOL |
Data types that all computation devices are expected to be capable to support. |
STRING |
|
FLOAT |
|
DOUBLE |
|
INT8 |
|
INT16 |
|
INT32 |
|
INT64 |
|
UINT8 |
|
UINT16 |
|
UINT32 |
|
UINT64 |
|
Tensorboard
Tensorboard is a physical database that stores users' training metrics. A default Tensorboard is provided in each region of a Google Cloud project. If needed users can also create extra Tensorboards in their projects.
| Fields | |
|---|---|
name |
Output only. Name of the Tensorboard. Format: |
display_name |
Required. User provided name of this Tensorboard. |
description |
Description of this Tensorboard. |
encryption_spec |
Customer-managed encryption key spec for a Tensorboard. If set, this Tensorboard and all sub-resources of this Tensorboard will be secured by this key. |
blob_storage_path_prefix |
Output only. Consumer project Cloud Storage path prefix used to store blob data, which can either be a bucket or directory. Does not end with a '/'. |
run_count |
Output only. The number of Runs stored in this Tensorboard. |
create_time |
Output only. Timestamp when this Tensorboard was created. |
update_time |
Output only. Timestamp when this Tensorboard was last updated. |
labels |
The labels with user-defined metadata to organize your Tensorboards. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Tensorboard (System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
etag |
Used to perform a consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
is_default |
Used to indicate if the TensorBoard instance is the default one. Each project & region can have at most one default TensorBoard instance. Creation of a default TensorBoard instance and updating an existing TensorBoard instance to be default will mark all other TensorBoard instances (if any) as non default. |
satisfies_pzs |
Output only. Reserved for future use. |
satisfies_pzi |
Output only. Reserved for future use. |
TensorboardBlob
One blob (e.g, image, graph) viewable on a blob metric plot.
| Fields | |
|---|---|
id |
Output only. A URI safe key uniquely identifying a blob. Can be used to locate the blob stored in the Cloud Storage bucket of the consumer project. |
data |
Optional. The bytes of the blob is not present unless it's returned by the ReadTensorboardBlobData endpoint. |
TensorboardBlobSequence
One point viewable on a blob metric plot, but mostly just a wrapper message to work around repeated fields can't be used directly within oneof fields.
| Fields | |
|---|---|
values[] |
List of blobs contained within the sequence. |
TensorboardExperiment
A TensorboardExperiment is a group of TensorboardRuns, that are typically the results of a training job run, in a Tensorboard.
| Fields | |
|---|---|
name |
Output only. Name of the TensorboardExperiment. Format: |
display_name |
User provided name of this TensorboardExperiment. |
description |
Description of this TensorboardExperiment. |
create_time |
Output only. Timestamp when this TensorboardExperiment was created. |
update_time |
Output only. Timestamp when this TensorboardExperiment was last updated. |
labels |
The labels with user-defined metadata to organize your TensorboardExperiment. Label keys and values cannot be longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Dataset (System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with
|
etag |
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
source |
Immutable. Source of the TensorboardExperiment. Example: a custom training job. |
TensorboardRun
TensorboardRun maps to a specific execution of a training job with a given set of hyperparameter values, model definition, dataset, etc
| Fields | |
|---|---|
name |
Output only. Name of the TensorboardRun. Format: |
display_name |
Required. User provided name of this TensorboardRun. This value must be unique among all TensorboardRuns belonging to the same parent TensorboardExperiment. |
description |
Description of this TensorboardRun. |
create_time |
Output only. Timestamp when this TensorboardRun was created. |
update_time |
Output only. Timestamp when this TensorboardRun was last updated. |
labels |
The labels with user-defined metadata to organize your TensorboardRuns. This field will be used to filter and visualize Runs in the Tensorboard UI. For example, a Vertex AI training job can set a label aiplatform.googleapis.com/training_job_id=xxxxx to all the runs created within that job. An end user can set a label experiment_id=xxxxx for all the runs produced in a Jupyter notebook. These runs can be grouped by a label value and visualized together in the Tensorboard UI. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one TensorboardRun (System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. |
etag |
Used to perform a consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
TensorboardTensor
One point viewable on a tensor metric plot.
| Fields | |
|---|---|
value |
Required. Serialized form of https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/framework/tensor.proto |
version_number |
Optional. Version number of TensorProto used to serialize |
TensorboardTimeSeries
TensorboardTimeSeries maps to times series produced in training runs
| Fields | |
|---|---|
name |
Output only. Name of the TensorboardTimeSeries. |
display_name |
Required. User provided name of this TensorboardTimeSeries. This value should be unique among all TensorboardTimeSeries resources belonging to the same TensorboardRun resource (parent resource). |
description |
Description of this TensorboardTimeSeries. |
value_type |
Required. Immutable. Type of TensorboardTimeSeries value. |
create_time |
Output only. Timestamp when this TensorboardTimeSeries was created. |
update_time |
Output only. Timestamp when this TensorboardTimeSeries was last updated. |
etag |
Used to perform a consistent read-modify-write updates. If not set, a blind "overwrite" update happens. |
plugin_name |
Immutable. Name of the plugin this time series pertain to. Such as Scalar, Tensor, Blob |
plugin_data |
Data of the current plugin, with the size limited to 65KB. |
metadata |
Output only. Scalar, Tensor, or Blob metadata for this TensorboardTimeSeries. |
Metadata
Describes metadata for a TensorboardTimeSeries.
| Fields | |
|---|---|
max_step |
Output only. Max step index of all data points within a TensorboardTimeSeries. |
max_wall_time |
Output only. Max wall clock timestamp of all data points within a TensorboardTimeSeries. |
max_blob_sequence_length |
Output only. The largest blob sequence length (number of blobs) of all data points in this time series, if its ValueType is BLOB_SEQUENCE. |
ValueType
An enum representing the value type of a TensorboardTimeSeries.
| Enums | |
|---|---|
VALUE_TYPE_UNSPECIFIED |
The value type is unspecified. |
SCALAR |
Used for TensorboardTimeSeries that is a list of scalars. E.g. accuracy of a model over epochs/time. |
TENSOR |
Used for TensorboardTimeSeries that is a list of tensors. E.g. histograms of weights of layer in a model over epoch/time. |
BLOB_SEQUENCE |
Used for TensorboardTimeSeries that is a list of blob sequences. E.g. set of sample images with labels over epochs/time. |
ThresholdConfig
The config for feature monitoring threshold.
| Fields | |
|---|---|
Union field
|
|
value |
Specify a threshold value that can trigger the alert. If this threshold config is for feature distribution distance: 1. For categorical feature, the distribution distance is calculated by L-inifinity norm. 2. For numerical feature, the distribution distance is calculated by Jensen–Shannon divergence. Each feature must have a non-zero threshold if they need to be monitored. Otherwise no alert will be triggered for that feature. |
TimeSeriesData
All the data stored in a TensorboardTimeSeries.
| Fields | |
|---|---|
tensorboard_time_series_id |
Required. The ID of the TensorboardTimeSeries, which will become the final component of the TensorboardTimeSeries' resource name |
value_type |
Required. Immutable. The value type of this time series. All the values in this time series data must match this value type. |
values[] |
Required. Data points in this time series. |
TimeSeriesDataPoint
A TensorboardTimeSeries data point.
| Fields | |
|---|---|
wall_time |
Wall clock timestamp when this data point is generated by the end user. |
step |
Step index of this data point within the run. |
Union field value. Value of this time series data point. value can be only one of the following: |
|
scalar |
A scalar value. |
tensor |
A tensor value. |
blobs |
A blob sequence value. |
TimestampSplit
Assigns input data to training, validation, and test sets based on a provided timestamps. The youngest data pieces are assigned to training set, next to validation set, and the oldest to the test set.
Supported only for tabular Datasets.
| Fields | |
|---|---|
training_fraction |
The fraction of the input data that is to be used to train the Model. |
validation_fraction |
The fraction of the input data that is to be used to validate the Model. |
test_fraction |
The fraction of the input data that is to be used to evaluate the Model. |
key |
Required. The key is a name of one of the Dataset's data columns. The values of the key (the values in the column) must be in RFC 3339 |
TokensInfo
Tokens info with a list of tokens and the corresponding list of token ids.
| Fields | |
|---|---|
tokens[] |
A list of tokens from the input. |
token_ids[] |
A list of token ids from the input. |
role |
Optional. Optional fields for the role from the corresponding Content. |
Tool
Tool details that the model may use to generate response.
A Tool is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
| Fields | |
|---|---|
function_declarations[] |
Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating |
retrieval |
Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. |
google_search |
Optional. GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google. |
google_search_retrieval |
Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search. |
code_execution |
Optional. CodeExecution tool type. Enables the model to execute code as part of generation. |
CodeExecution
This type has no fields.
Tool that executes code generated by the model, and automatically returns the result to the model.
See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool.
GoogleSearch
This type has no fields.
GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google.
ToolCall
Spec for tool call.
| Fields | |
|---|---|
tool_name |
Required. Spec for tool name |
tool_input |
Optional. Spec for tool input |
ToolCallValidInput
Input for tool call valid metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for tool call valid metric. |
instances[] |
Required. Repeated tool call valid instances. |
ToolCallValidInstance
Spec for tool call valid instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Required. Ground truth used to compare against the prediction. |
ToolCallValidMetricValue
Tool call valid metric value for an instance.
| Fields | |
|---|---|
score |
Output only. Tool call valid score. |
ToolCallValidResults
Results for tool call valid metric.
| Fields | |
|---|---|
tool_call_valid_metric_values[] |
Output only. Tool call valid metric values. |
ToolCallValidSpec
This type has no fields.
Spec for tool call valid metric.
ToolConfig
Tool config. This config is shared for all tools provided in the request.
| Fields | |
|---|---|
function_calling_config |
Optional. Function calling config. |
retrieval_config |
Optional. Retrieval config. |
ToolNameMatchInput
Input for tool name match metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for tool name match metric. |
instances[] |
Required. Repeated tool name match instances. |
ToolNameMatchInstance
Spec for tool name match instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Required. Ground truth used to compare against the prediction. |
ToolNameMatchMetricValue
Tool name match metric value for an instance.
| Fields | |
|---|---|
score |
Output only. Tool name match score. |
ToolNameMatchResults
Results for tool name match metric.
| Fields | |
|---|---|
tool_name_match_metric_values[] |
Output only. Tool name match metric values. |
ToolNameMatchSpec
This type has no fields.
Spec for tool name match metric.
ToolParameterKVMatchInput
Input for tool parameter key value match metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for tool parameter key value match metric. |
instances[] |
Required. Repeated tool parameter key value match instances. |
ToolParameterKVMatchInstance
Spec for tool parameter key value match instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Required. Ground truth used to compare against the prediction. |
ToolParameterKVMatchMetricValue
Tool parameter key value match metric value for an instance.
| Fields | |
|---|---|
score |
Output only. Tool parameter key value match score. |
ToolParameterKVMatchResults
Results for tool parameter key value match metric.
| Fields | |
|---|---|
tool_parameter_kv_match_metric_values[] |
Output only. Tool parameter key value match metric values. |
ToolParameterKVMatchSpec
Spec for tool parameter key value match metric.
| Fields | |
|---|---|
use_strict_string_match |
Optional. Whether to use STRICT string match on parameter values. |
ToolParameterKeyMatchInput
Input for tool parameter key match metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for tool parameter key match metric. |
instances[] |
Required. Repeated tool parameter key match instances. |
ToolParameterKeyMatchInstance
Spec for tool parameter key match instance.
| Fields | |
|---|---|
prediction |
Required. Output of the evaluated model. |
reference |
Required. Ground truth used to compare against the prediction. |
ToolParameterKeyMatchMetricValue
Tool parameter key match metric value for an instance.
| Fields | |
|---|---|
score |
Output only. Tool parameter key match score. |
ToolParameterKeyMatchResults
Results for tool parameter key match metric.
| Fields | |
|---|---|
tool_parameter_key_match_metric_values[] |
Output only. Tool parameter key match metric values. |
ToolParameterKeyMatchSpec
This type has no fields.
Spec for tool parameter key match metric.
ToolUseExample
A single example of the tool usage.
| Fields | |
|---|---|
display_name |
Required. The display name for example. |
query |
Required. Query that should be routed to this tool. |
request_params |
Request parameters used for executing this tool. |
response_params |
Response parameters generated by this tool. |
response_summary |
Summary of the tool response to the user query. |
Union field Target. Target tool to use. Target can be only one of the following: |
|
extension_operation |
Extension operation to call. |
function_name |
Function name to call. |
ExtensionOperation
Identifies one operation of the extension.
| Fields | |
|---|---|
extension |
Resource name of the extension. |
operation_id |
Required. Operation ID of the extension. |
TrainingPipeline
The TrainingPipeline orchestrates tasks associated with training a Model. It always executes the training task, and optionally may also export data from Vertex AI's Dataset which becomes the training input, upload the Model to Vertex AI, and evaluate the Model.
| Fields | |
|---|---|
name |
Output only. Resource name of the TrainingPipeline. |
display_name |
Required. The user-defined name of this TrainingPipeline. |
input_data_config |
Specifies Vertex AI owned input data that may be used for training the Model. The TrainingPipeline's |
training_task_definition |
Required. A Google Cloud Storage path to the YAML file that defines the training task which is responsible for producing the model artifact, and may also include additional auxiliary work. The definition files that can be used here are found in gs://google-cloud-aiplatform/schema/trainingjob/definition/. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access. |
training_task_inputs |
Required. The training task's parameter(s), as specified in the |
training_task_metadata |
Output only. The metadata information as specified in the |
model_to_upload |
Describes the Model that may be uploaded (via |
model_id |
Optional. The ID to use for the uploaded Model, which will become the final component of the model resource name. This value may be up to 63 characters, and valid characters are |
parent_model |
Optional. When specify this field, the |
state |
Output only. The detailed state of the pipeline. |
error |
Output only. Only populated when the pipeline's state is |
create_time |
Output only. Time when the TrainingPipeline was created. |
start_time |
Output only. Time when the TrainingPipeline for the first time entered the |
end_time |
Output only. Time when the TrainingPipeline entered any of the following states: |
update_time |
Output only. Time when the TrainingPipeline was most recently updated. |
labels |
The labels with user-defined metadata to organize TrainingPipelines. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
encryption_spec |
Customer-managed encryption key spec for a TrainingPipeline. If set, this TrainingPipeline will be secured by this key. Note: Model trained by this TrainingPipeline is also secured by this key if |
Trajectory
Spec for trajectory.
| Fields | |
|---|---|
tool_calls[] |
Required. Tool calls in the trajectory. |
TrajectoryAnyOrderMatchInput
Instances and metric spec for TrajectoryAnyOrderMatch metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for TrajectoryAnyOrderMatch metric. |
instances[] |
Required. Repeated TrajectoryAnyOrderMatch instance. |
TrajectoryAnyOrderMatchInstance
Spec for TrajectoryAnyOrderMatch instance.
| Fields | |
|---|---|
predicted_trajectory |
Required. Spec for predicted tool call trajectory. |
reference_trajectory |
Required. Spec for reference tool call trajectory. |
TrajectoryAnyOrderMatchMetricValue
TrajectoryAnyOrderMatch metric value for an instance.
| Fields | |
|---|---|
score |
Output only. TrajectoryAnyOrderMatch score. |
TrajectoryAnyOrderMatchResults
Results for TrajectoryAnyOrderMatch metric.
| Fields | |
|---|---|
trajectory_any_order_match_metric_values[] |
Output only. TrajectoryAnyOrderMatch metric values. |
TrajectoryAnyOrderMatchSpec
This type has no fields.
Spec for TrajectoryAnyOrderMatch metric - returns 1 if all tool calls in the reference trajectory appear in the predicted trajectory in any order, else 0.
TrajectoryExactMatchInput
Instances and metric spec for TrajectoryExactMatch metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for TrajectoryExactMatch metric. |
instances[] |
Required. Repeated TrajectoryExactMatch instance. |
TrajectoryExactMatchInstance
Spec for TrajectoryExactMatch instance.
| Fields | |
|---|---|
predicted_trajectory |
Required. Spec for predicted tool call trajectory. |
reference_trajectory |
Required. Spec for reference tool call trajectory. |
TrajectoryExactMatchMetricValue
TrajectoryExactMatch metric value for an instance.
| Fields | |
|---|---|
score |
Output only. TrajectoryExactMatch score. |
TrajectoryExactMatchResults
Results for TrajectoryExactMatch metric.
| Fields | |
|---|---|
trajectory_exact_match_metric_values[] |
Output only. TrajectoryExactMatch metric values. |
TrajectoryExactMatchSpec
This type has no fields.
Spec for TrajectoryExactMatch metric - returns 1 if tool calls in the reference trajectory exactly match the predicted trajectory, else 0.
TrajectoryInOrderMatchInput
Instances and metric spec for TrajectoryInOrderMatch metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for TrajectoryInOrderMatch metric. |
instances[] |
Required. Repeated TrajectoryInOrderMatch instance. |
TrajectoryInOrderMatchInstance
Spec for TrajectoryInOrderMatch instance.
| Fields | |
|---|---|
predicted_trajectory |
Required. Spec for predicted tool call trajectory. |
reference_trajectory |
Required. Spec for reference tool call trajectory. |
TrajectoryInOrderMatchMetricValue
TrajectoryInOrderMatch metric value for an instance.
| Fields | |
|---|---|
score |
Output only. TrajectoryInOrderMatch score. |
TrajectoryInOrderMatchResults
Results for TrajectoryInOrderMatch metric.
| Fields | |
|---|---|
trajectory_in_order_match_metric_values[] |
Output only. TrajectoryInOrderMatch metric values. |
TrajectoryInOrderMatchSpec
This type has no fields.
Spec for TrajectoryInOrderMatch metric - returns 1 if tool calls in the reference trajectory appear in the predicted trajectory in the same order, else 0.
TrajectoryPrecisionInput
Instances and metric spec for TrajectoryPrecision metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for TrajectoryPrecision metric. |
instances[] |
Required. Repeated TrajectoryPrecision instance. |
TrajectoryPrecisionInstance
Spec for TrajectoryPrecision instance.
| Fields | |
|---|---|
predicted_trajectory |
Required. Spec for predicted tool call trajectory. |
reference_trajectory |
Required. Spec for reference tool call trajectory. |
TrajectoryPrecisionMetricValue
TrajectoryPrecision metric value for an instance.
| Fields | |
|---|---|
score |
Output only. TrajectoryPrecision score. |
TrajectoryPrecisionResults
Results for TrajectoryPrecision metric.
| Fields | |
|---|---|
trajectory_precision_metric_values[] |
Output only. TrajectoryPrecision metric values. |
TrajectoryPrecisionSpec
This type has no fields.
Spec for TrajectoryPrecision metric - returns a float score based on average precision of individual tool calls.
TrajectoryRecallInput
Instances and metric spec for TrajectoryRecall metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for TrajectoryRecall metric. |
instances[] |
Required. Repeated TrajectoryRecall instance. |
TrajectoryRecallInstance
Spec for TrajectoryRecall instance.
| Fields | |
|---|---|
predicted_trajectory |
Required. Spec for predicted tool call trajectory. |
reference_trajectory |
Required. Spec for reference tool call trajectory. |
TrajectoryRecallMetricValue
TrajectoryRecall metric value for an instance.
| Fields | |
|---|---|
score |
Output only. TrajectoryRecall score. |
TrajectoryRecallResults
Results for TrajectoryRecall metric.
| Fields | |
|---|---|
trajectory_recall_metric_values[] |
Output only. TrajectoryRecall metric values. |
TrajectoryRecallSpec
This type has no fields.
Spec for TrajectoryRecall metric - returns a float score based on average recall of individual tool calls.
TrajectorySingleToolUseInput
Instances and metric spec for TrajectorySingleToolUse metric.
| Fields | |
|---|---|
metric_spec |
Required. Spec for TrajectorySingleToolUse metric. |
instances[] |
Required. Repeated TrajectorySingleToolUse instance. |
TrajectorySingleToolUseInstance
Spec for TrajectorySingleToolUse instance.
| Fields | |
|---|---|
predicted_trajectory |
Required. Spec for predicted tool call trajectory. |
TrajectorySingleToolUseMetricValue
TrajectorySingleToolUse metric value for an instance.
| Fields | |
|---|---|
score |
Output only. TrajectorySingleToolUse score. |
TrajectorySingleToolUseResults
Results for TrajectorySingleToolUse metric.
| Fields | |
|---|---|
trajectory_single_tool_use_metric_values[] |
Output only. TrajectorySingleToolUse metric values. |
TrajectorySingleToolUseSpec
Spec for TrajectorySingleToolUse metric - returns 1 if tool is present in the predicted trajectory, else 0.
| Fields | |
|---|---|
tool_name |
Required. Spec for tool name to be checked for in the predicted trajectory. |
Trial
A message representing a Trial. A Trial contains a unique set of Parameters that has been or will be evaluated, along with the objective metrics got by running the Trial.
| Fields | |
|---|---|
name |
Output only. Resource name of the Trial assigned by the service. |
id |
Output only. The identifier of the Trial assigned by the service. |
state |
Output only. The detailed state of the Trial. |
parameters[] |
Output only. The parameters of the Trial. |
final_measurement |
Output only. The final measurement containing the objective value. |
measurements[] |
Output only. A list of measurements that are strictly lexicographically ordered by their induced tuples (steps, elapsed_duration). These are used for early stopping computations. |
start_time |
Output only. Time when the Trial was started. |
end_time |
Output only. Time when the Trial's status changed to |
client_id |
Output only. The identifier of the client that originally requested this Trial. Each client is identified by a unique client_id. When a client asks for a suggestion, Vertex AI Vizier will assign it a Trial. The client should evaluate the Trial, complete it, and report back to Vertex AI Vizier. If suggestion is asked again by same client_id before the Trial is completed, the same Trial will be returned. Multiple clients with different client_ids can ask for suggestions simultaneously, each of them will get their own Trial. |
infeasible_reason |
Output only. A human readable string describing why the Trial is infeasible. This is set only if Trial state is |
custom_job |
Output only. The CustomJob name linked to the Trial. It's set for a HyperparameterTuningJob's Trial. |
web_access_uris |
Output only. URIs for accessing interactive shells (one URI for each training node). Only available if this trial is part of a The keys are names of each node used for the trial; for example, The values are the URIs for each node's interactive shell. |
Parameter
A message representing a parameter to be tuned.
| Fields | |
|---|---|
parameter_id |
Output only. The ID of the parameter. The parameter should be defined in |
value |
Output only. The value of the parameter. |
State
Describes a Trial state.
| Enums | |
|---|---|
STATE_UNSPECIFIED |
The Trial state is unspecified. |
REQUESTED |
Indicates that a specific Trial has been requested, but it has not yet been suggested by the service. |
ACTIVE |
Indicates that the Trial has been suggested. |
STOPPING |
Indicates that the Trial should stop according to the service. |
SUCCEEDED |
Indicates that the Trial is completed successfully. |
INFEASIBLE |
Indicates that the Trial should not be attempted again. The service will set a Trial to INFEASIBLE when it's done but missing the final_measurement. |
TrialContext
| Fields | |
|---|---|
description |
A human-readable field which can store a description of this context. This will become part of the resulting Trial's description field. |
parameters[] |
If/when a Trial is generated or selected from this Context, its Parameters will match any parameters specified here. (I.e. if this context specifies parameter name:'a' int_value:3, then a resulting Trial will have int_value:3 for its parameter named 'a'.) Note that we first attempt to match existing REQUESTED Trials with contexts, and if there are no matches, we generate suggestions in the subspace defined by the parameters specified here. NOTE: a Context without any Parameters matches the entire feasible search space. |
TunedModel
The Model Registry Model and Online Prediction Endpoint associated with this TuningJob.
| Fields | |
|---|---|
model |
Output only. The resource name of the TunedModel. Format: |
endpoint |
Output only. A resource name of an Endpoint. Format: |
TunedModelRef
TunedModel Reference for legacy model migration.
| Fields | |
|---|---|
Union field tuned_model_ref. The Tuned Model Reference for the model. tuned_model_ref can be only one of the following: |
|
tuned_model |
Support migration from model registry. |
tuning_job |
Support migration from tuning job list page, from gemini-1.0-pro-002 to 1.5 and above. |
pipeline_job |
Support migration from tuning job list page, from bison model to gemini model. |
TuningDataStats
The tuning data statistic values for TuningJob.
| Fields | |
|---|---|
Union field
|
|
supervised_tuning_data_stats |
The SFT Tuning data stats. |
distillation_data_stats |
Output only. Statistics for distillation. |
TuningJob
Represents a TuningJob that runs with Google owned models.
| Fields | |
|---|---|
name |
Output only. Identifier. Resource name of a TuningJob. Format: |
tuned_model_display_name |
Optional. The display name of the |
description |
Optional. The description of the |
state |
Output only. The detailed state of the job. |
create_time |
Output only. Time when the |
start_time |
Output only. Time when the |
end_time |
Output only. Time when the TuningJob entered any of the following |
update_time |
Output only. Time when the |
error |
Output only. Only populated when job's state is |
labels |
Optional. The labels with user-defined metadata to organize Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. |
experiment |
Output only. The Experiment associated with this |
tuned_model |
Output only. The tuned model resources associated with this |
tuning_data_stats |
Output only. The tuning data statistics associated with this |
pipeline_job |
Output only. The resource name of the PipelineJob associated with the |
encryption_spec |
Customer-managed encryption key options for a TuningJob. If this is set, then all resources created by the TuningJob will be encrypted with the provided encryption key. |
service_account |
The service account that the tuningJob workload runs as. If not specified, the Vertex AI Secure Fine-Tuned Service Agent in the project will be used. See https://cloud.google.com/iam/docs/service-agents#vertex-ai-secure-fine-tuning-service-agent Users starting the pipeline must have the |
Union field
|
|
base_model |
The base model that is being tuned, e.g., "gemini-1.0-pro-002". . |
Union field
|
|
supervised_tuning_spec |
Tuning Spec for Supervised Fine Tuning. |
distillation_spec |
Tuning Spec for Distillation. |
partner_model_tuning_spec |
Tuning Spec for open sourced and third party Partner models. |
Type
Type contains the list of OpenAPI data types as defined by https://swagger.io/docs/specification/data-models/data-types/
| Enums | |
|---|---|
TYPE_UNSPECIFIED |
Not specified, should not be used. |
STRING |
OpenAPI string type |
NUMBER |
OpenAPI number type |
INTEGER |
OpenAPI integer type |
BOOLEAN |
OpenAPI boolean type |
ARRAY |
OpenAPI array type |
OBJECT |
OpenAPI object type |
UndeployIndexOperationMetadata
Runtime operation information for IndexEndpointService.UndeployIndex.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
UndeployIndexRequest
Request message for IndexEndpointService.UndeployIndex.
| Fields | |
|---|---|
index_endpoint |
Required. The name of the IndexEndpoint resource from which to undeploy an Index. Format: |
deployed_index_id |
Required. The ID of the DeployedIndex to be undeployed from the IndexEndpoint. |
UndeployIndexResponse
This type has no fields.
Response message for IndexEndpointService.UndeployIndex.
UndeployModelOperationMetadata
Runtime operation information for EndpointService.UndeployModel.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
UndeployModelRequest
Request message for EndpointService.UndeployModel.
| Fields | |
|---|---|
endpoint |
Required. The name of the Endpoint resource from which to undeploy a Model. Format: |
deployed_model_id |
Required. The ID of the DeployedModel to be undeployed from the Endpoint. |
traffic_split |
If this field is provided, then the Endpoint's |
UndeployModelResponse
This type has no fields.
Response message for EndpointService.UndeployModel.
UndeploySolverOperationMetadata
Runtime operation information for SolverService.UndeploySolver.
| Fields | |
|---|---|
generic_metadata |
The generic operation information. |
UnmanagedContainerModel
Contains model information necessary to perform batch prediction without requiring a full model import.
| Fields | |
|---|---|
artifact_uri |
The path to the directory containing the Model artifact and any of its supporting files. |
predict_schemata |
Contains the schemata used in Model's predictions and explanations |
container_spec |
Input only. The specification of the container that is to be used when deploying this Model. |
UpdateArtifactRequest
Request message for MetadataService.UpdateArtifact.
| Fields | |
|---|---|
artifact |
Required. The Artifact containing updates. The Artifact's |
update_mask |
Optional. A FieldMask indicating which fields should be updated. |
allow_missing |
If set to true, and the |
UpdateCachedContentRequest
Request message for GenAiCacheService.UpdateCachedContent. Only expire_time or ttl can be updated.
| Fields | |
|---|---|
cached_content |
Required. The cached content to update |
update_mask |
Required. The list of fields to update. |
UpdateContextRequest
Request message for MetadataService.UpdateContext.
| Fields | |
|---|---|
context |
Required. The Context containing updates. The Context's |
update_mask |
Optional. A FieldMask indicating which fields should be updated. |
allow_missing |
If set to true, and the |
UpdateDatasetRequest
Request message for DatasetService.UpdateDataset.
| Fields | |
|---|---|
dataset |
Required. The Dataset which replaces the resource on the server. |
update_mask |
Required. The update mask applies to the resource. For the
|
UpdateDatasetVersionRequest
Request message for DatasetService.UpdateDatasetVersion.
| Fields | |
|---|---|
dataset_version |
Required. The DatasetVersion which replaces the resource on the server. |
update_mask |
Required. The update mask applies to the resource. For the
|
UpdateDeploymentResourcePoolOperationMetadata
Runtime operation information for UpdateDeploymentResourcePool method.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
UpdateDeploymentResourcePoolRequest
Request message for UpdateDeploymentResourcePool method.
| Fields | |
|---|---|
deployment_resource_pool |
Required. The DeploymentResourcePool to update. The DeploymentResourcePool's |
update_mask |
Required. The list of fields to update. |
UpdateEndpointLongRunningRequest
Request message for EndpointService.UpdateEndpointLongRunning.
| Fields | |
|---|---|
endpoint |
Required. The Endpoint which replaces the resource on the server. Currently we only support updating the |
UpdateEndpointOperationMetadata
Runtime operation information for EndpointService.UpdateEndpointLongRunning.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
UpdateEndpointRequest
Request message for EndpointService.UpdateEndpoint.
| Fields | |
|---|---|
endpoint |
Required. The Endpoint which replaces the resource on the server. |
update_mask |
Required. The update mask applies to the resource. See |
UpdateEntityTypeRequest
Request message for FeaturestoreService.UpdateEntityType.
| Fields | |
|---|---|
entity_type |
Required. The EntityType's |
update_mask |
Field mask is used to specify the fields to be overwritten in the EntityType resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then only the non-empty fields present in the request will be overwritten. Set the update_mask to Updatable fields:
|
UpdateExecutionRequest
Request message for MetadataService.UpdateExecution.
| Fields | |
|---|---|
execution |
Required. The Execution containing updates. The Execution's |
update_mask |
Optional. A FieldMask indicating which fields should be updated. |
allow_missing |
If set to true, and the |
UpdateExplanationDatasetOperationMetadata
Runtime operation information for ModelService.UpdateExplanationDataset.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
UpdateExplanationDatasetRequest
Request message for ModelService.UpdateExplanationDataset.
| Fields | |
|---|---|
model |
Required. The resource name of the Model to update. Format: |
examples |
The example config containing the location of the dataset. |
UpdateExplanationDatasetResponse
This type has no fields.
Response message of ModelService.UpdateExplanationDataset operation.
UpdateExtensionRequest
Request message for ExtensionRegistryService.UpdateExtension.
| Fields | |
|---|---|
extension |
Required. The Extension which replaces the resource on the server. |
update_mask |
Required. Mask specifying which fields to update. Supported fields:
|
UpdateFeatureGroupOperationMetadata
Details of operations that perform update FeatureGroup.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for FeatureGroup. |
UpdateFeatureGroupRequest
Request message for FeatureRegistryService.UpdateFeatureGroup.
| Fields | |
|---|---|
feature_group |
Required. The FeatureGroup's |
update_mask |
Field mask is used to specify the fields to be overwritten in the FeatureGroup resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then only the non-empty fields present in the request will be overwritten. Set the update_mask to Updatable fields:
|
UpdateFeatureMonitorOperationMetadata
Details of operations that perform update FeatureMonitor.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for FeatureMonitor. |
UpdateFeatureMonitorRequest
Request message for FeatureRegistryService.UpdateFeatureMonitor.
| Fields | |
|---|---|
feature_monitor |
Required. The FeatureMonitor's |
update_mask |
Optional. Field mask is used to specify the fields to be overwritten in the FeatureMonitor resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then only the non-empty fields present in the request will be overwritten. Set the update_mask to Updatable fields:
|
UpdateFeatureOnlineStoreOperationMetadata
Details of operations that perform update FeatureOnlineStore.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for FeatureOnlineStore. |
UpdateFeatureOnlineStoreRequest
Request message for FeatureOnlineStoreAdminService.UpdateFeatureOnlineStore.
| Fields | |
|---|---|
feature_online_store |
Required. The FeatureOnlineStore's |
update_mask |
Field mask is used to specify the fields to be overwritten in the FeatureOnlineStore resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then only the non-empty fields present in the request will be overwritten. Set the update_mask to Updatable fields:
|
UpdateFeatureOperationMetadata
Details of operations that perform update Feature.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Feature Update. |
UpdateFeatureRequest
Request message for FeaturestoreService.UpdateFeature. Request message for FeatureRegistryService.UpdateFeature.
| Fields | |
|---|---|
feature |
Required. The Feature's |
update_mask |
Field mask is used to specify the fields to be overwritten in the Features resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then only the non-empty fields present in the request will be overwritten. Set the update_mask to Updatable fields:
|
UpdateFeatureViewOperationMetadata
Details of operations that perform update FeatureView.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for FeatureView Update. |
UpdateFeatureViewRequest
Request message for FeatureOnlineStoreAdminService.UpdateFeatureView.
| Fields | |
|---|---|
feature_view |
Required. The FeatureView's |
update_mask |
Field mask is used to specify the fields to be overwritten in the FeatureView resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then only the non-empty fields present in the request will be overwritten. Set the update_mask to Updatable fields:
|
UpdateFeaturestoreOperationMetadata
Details of operations that perform update Featurestore.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Featurestore. |
UpdateFeaturestoreRequest
Request message for FeaturestoreService.UpdateFeaturestore.
| Fields | |
|---|---|
featurestore |
Required. The Featurestore's |
update_mask |
Field mask is used to specify the fields to be overwritten in the Featurestore resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then only the non-empty fields present in the request will be overwritten. Set the update_mask to Updatable fields:
|
UpdateIndexEndpointRequest
Request message for IndexEndpointService.UpdateIndexEndpoint.
| Fields | |
|---|---|
index_endpoint |
Required. The IndexEndpoint which replaces the resource on the server. |
update_mask |
Required. The update mask applies to the resource. See |
UpdateIndexOperationMetadata
Runtime operation information for IndexService.UpdateIndex.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
nearest_neighbor_search_operation_metadata |
The operation metadata with regard to Matching Engine Index operation. |
UpdateIndexRequest
Request message for IndexService.UpdateIndex.
| Fields | |
|---|---|
index |
Required. The Index which updates the resource on the server. |
update_mask |
The update mask applies to the resource. For the |
UpdateModelDeploymentMonitoringJobOperationMetadata
Runtime operation information for JobService.UpdateModelDeploymentMonitoringJob.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
UpdateModelDeploymentMonitoringJobRequest
Request message for JobService.UpdateModelDeploymentMonitoringJob.
| Fields | |
|---|---|
model_deployment_monitoring_job |
Required. The model monitoring configuration which replaces the resource on the server. |
update_mask |
Required. The update mask is used to specify the fields to be overwritten in the ModelDeploymentMonitoringJob resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then only the non-empty fields present in the request will be overwritten. Set the update_mask to Updatable fields:
|
UpdateModelMonitorOperationMetadata
Runtime operation information for ModelMonitoringService.UpdateModelMonitor.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
UpdateModelMonitorRequest
Request message for ModelMonitoringService.UpdateModelMonitor.
| Fields | |
|---|---|
model_monitor |
Required. The model monitoring configuration which replaces the resource on the server. |
update_mask |
Required. Mask specifying which fields to update. |
UpdateModelRequest
Request message for ModelService.UpdateModel.
| Fields | |
|---|---|
model |
Required. The Model which replaces the resource on the server. When Model Versioning is enabled, the model.name will be used to determine whether to update the model or model version. 1. model.name with the @ value, e.g. models/123@1, refers to a version specific update. 2. model.name without the @ value, e.g. models/123, refers to a model update. 3. model.name with @-, e.g. models/123@-, refers to a model update. 4. Supported model fields: display_name, description; supported version-specific fields: version_description. Labels are supported in both scenarios. Both the model labels and the version labels are merged when a model is returned. When updating labels, if the request is for model-specific update, model label gets updated. Otherwise, version labels get updated. 5. A model name or model version name fields update mismatch will cause a precondition error. 6. One request cannot update both the model and the version fields. You must update them separately. |
update_mask |
Required. The update mask applies to the resource. For the |
UpdateNotebookRuntimeTemplateRequest
Request message for NotebookService.UpdateNotebookRuntimeTemplate.
| Fields | |
|---|---|
notebook_runtime_template |
Required. The NotebookRuntimeTemplate to update. |
update_mask |
Required. The update mask applies to the resource. For the
|
UpdatePersistentResourceOperationMetadata
Details of operations that perform update PersistentResource.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for PersistentResource. |
progress_message |
Progress Message for Update LRO |
UpdatePersistentResourceRequest
Request message for UpdatePersistentResource method.
| Fields | |
|---|---|
persistent_resource |
Required. The PersistentResource to update. The PersistentResource's |
update_mask |
Required. Specify the fields to be overwritten in the PersistentResource by the update method. |
UpdateRagCorpusOperationMetadata
Runtime operation information for VertexRagDataService.UpdateRagCorpus.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
UpdateRagCorpusRequest
Request message for VertexRagDataService.UpdateRagCorpus.
| Fields | |
|---|---|
rag_corpus |
Required. The RagCorpus which replaces the resource on the server. |
UpdateReasoningEngineOperationMetadata
Details of ReasoningEngineService.UpdateReasoningEngine operation.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
UpdateReasoningEngineRequest
Request message for ReasoningEngineService.UpdateReasoningEngine.
| Fields | |
|---|---|
reasoning_engine |
Required. The ReasoningEngine which replaces the resource on the server. |
update_mask |
Optional. Mask specifying which fields to update. |
UpdateScheduleRequest
Request message for ScheduleService.UpdateSchedule.
| Fields | |
|---|---|
schedule |
Required. The Schedule which replaces the resource on the server. The following restrictions will be applied:
|
update_mask |
Required. The update mask applies to the resource. See |
UpdateSpecialistPoolOperationMetadata
Runtime operation metadata for SpecialistPoolService.UpdateSpecialistPool.
| Fields | |
|---|---|
specialist_pool |
Output only. The name of the SpecialistPool to which the specialists are being added. Format: |
generic_metadata |
The operation generic information. |
UpdateSpecialistPoolRequest
Request message for SpecialistPoolService.UpdateSpecialistPool.
| Fields | |
|---|---|
specialist_pool |
Required. The SpecialistPool which replaces the resource on the server. |
update_mask |
Required. The update mask applies to the resource. |
UpdateTensorboardExperimentRequest
Request message for TensorboardService.UpdateTensorboardExperiment.
| Fields | |
|---|---|
update_mask |
Required. Field mask is used to specify the fields to be overwritten in the TensorboardExperiment resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field is overwritten if it's in the mask. If the user does not provide a mask then all fields are overwritten if new values are specified. |
tensorboard_experiment |
Required. The TensorboardExperiment's |
UpdateTensorboardOperationMetadata
Details of operations that perform update Tensorboard.
| Fields | |
|---|---|
generic_metadata |
Operation metadata for Tensorboard. |
UpdateTensorboardRequest
Request message for TensorboardService.UpdateTensorboard.
| Fields | |
|---|---|
update_mask |
Required. Field mask is used to specify the fields to be overwritten in the Tensorboard resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field is overwritten if it's in the mask. If the user does not provide a mask then all fields are overwritten if new values are specified. |
tensorboard |
Required. The Tensorboard's |
UpdateTensorboardRunRequest
Request message for TensorboardService.UpdateTensorboardRun.
| Fields | |
|---|---|
update_mask |
Required. Field mask is used to specify the fields to be overwritten in the TensorboardRun resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field is overwritten if it's in the mask. If the user does not provide a mask then all fields are overwritten if new values are specified. |
tensorboard_run |
Required. The TensorboardRun's |
UpdateTensorboardTimeSeriesRequest
Request message for TensorboardService.UpdateTensorboardTimeSeries.
| Fields | |
|---|---|
update_mask |
Required. Field mask is used to specify the fields to be overwritten in the TensorboardTimeSeries resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field is overwritten if it's in the mask. If the user does not provide a mask then all fields are overwritten if new values are specified. |
tensorboard_time_series |
Required. The TensorboardTimeSeries' |
UpgradeNotebookRuntimeOperationMetadata
Metadata information for NotebookService.UpgradeNotebookRuntime.
| Fields | |
|---|---|
generic_metadata |
The operation generic information. |
progress_message |
A human-readable message that shows the intermediate progress details of NotebookRuntime. |
UpgradeNotebookRuntimeRequest
Request message for NotebookService.UpgradeNotebookRuntime.
| Fields | |
|---|---|
name |
Required. The name of the NotebookRuntime resource to be upgrade. Instead of checking whether the name is in valid NotebookRuntime resource name format, directly throw NotFound exception if there is no such NotebookRuntime in spanner. |
UpgradeNotebookRuntimeResponse
This type has no fields.
Response message for NotebookService.UpgradeNotebookRuntime.
UploadModelOperationMetadata
Details of ModelService.UploadModel operation.
| Fields | |
|---|---|
generic_metadata |
The common part of the operation metadata. |
UploadModelRequest
Request message for ModelService.UploadModel.
| Fields | |
|---|---|
parent |
Required. The resource name of the Location into which to upload the Model. Format: |
parent_model |
Optional. The resource name of the model into which to upload the version. Only specify this field when uploading a new version. |
model_id |
Optional. The ID to use for the uploaded Model, which will become the final component of the model resource name. This value may be up to 63 characters, and valid characters are |
model |
Required. The Model to create. |
service_account |
Optional. The user-provided custom service account to use to do the model upload. If empty, Vertex AI Service Agent will be used to access resources needed to upload the model. This account must belong to the target project where the model is uploaded to, i.e., the project specified in the |
UploadModelResponse
Response message of ModelService.UploadModel operation.
| Fields | |
|---|---|
model |
The name of the uploaded Model resource. Format: |
model_version_id |
Output only. The version ID of the model that is uploaded. |
UploadRagFileConfig
Config for uploading RagFile.
| Fields | |
|---|---|
rag_file_chunking_config |
Specifies the size and overlap of chunks after uploading RagFile. |
rag_file_transformation_config |
Specifies the transformation config for RagFiles. |
UpsertDatapointsRequest
Request message for IndexService.UpsertDatapoints
| Fields | |
|---|---|
index |
Required. The name of the Index resource to be updated. Format: |
datapoints[] |
A list of datapoints to be created/updated. |
update_mask |
Optional. Update mask is used to specify the fields to be overwritten in the datapoints by the update. The fields specified in the update_mask are relative to each IndexDatapoint inside datapoints, not the full request. Updatable fields:
|
UpsertDatapointsResponse
This type has no fields.
Response message for IndexService.UpsertDatapoints
UserActionReference
References an API call. It contains more information about long running operation and Jobs that are triggered by the API call.
| Fields | |
|---|---|
method |
The method name of the API RPC call. For example, "/google.cloud.aiplatform.{apiVersion}.DatasetService.CreateDataset" |
Union field
|
|
operation |
For API calls that return a long running operation. Resource name of the long running operation. Format: |
data_labeling_job |
For API calls that start a LabelingJob. Resource name of the LabelingJob. Format: |
Value
Value is the value of the field.
| Fields | |
|---|---|
Union field
|
|
int_value |
An integer value. |
double_value |
A double value. |
string_value |
A string value. |
VertexAISearch
Retrieve from Vertex AI Search datastore or engine for grounding. datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder
| Fields | |
|---|---|
datastore |
Optional. Fully-qualified Vertex AI Search data store resource ID. Format: |
VertexAiSearchConfig
Config for the Vertex AI Search.
| Fields | |
|---|---|
serving_config |
Vertex AI Search Serving Config resource full name. For example, |
VertexRagStore
Retrieve from Vertex RAG Store for grounding.
| Fields | |
|---|---|
rag_corpora[] |
Optional. Deprecated. Please use rag_resources instead. |
rag_resources[] |
Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support. |
rag_retrieval_config |
Optional. The retrieval config for the Rag query. |
similarity_top_k |
Optional. Number of top k results to return from the selected corpora. |
vector_distance_threshold |
Optional. Only return results with vector distance smaller than the threshold. |
RagResource
The definition of the Rag resource.
| Fields | |
|---|---|
rag_corpus |
Optional. RagCorpora resource name. Format: |
rag_file_ids[] |
Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field. |
VideoMetadata
Metadata describes the input video content.
| Fields | |
|---|---|
start_offset |
Optional. The start offset of the video. |
end_offset |
Optional. The end offset of the video. |
VoiceConfig
The configuration for the voice to use.
| Fields | |
|---|---|
Union field voice_config. The configuration for the speaker to use. voice_config can be only one of the following: |
|
prebuilt_voice_config |
The configuration for the prebuilt voice to use. |
WorkerPoolSpec
Represents the spec of a worker pool in a job.
| Fields | |
|---|---|
machine_spec |
Optional. Immutable. The specification of a single machine. |
replica_count |
Optional. The number of worker replicas to use for this worker pool. |
nfs_mounts[] |
Optional. List of NFS mount spec. |
disk_spec |
Disk spec. |
Union field task. The custom task to be executed in this worker pool. task can be only one of the following: |
|
container_spec |
The custom container task. |
python_package_spec |
The Python packaged task. |
WriteFeatureValuesPayload
Contains Feature values to be written for a specific entity.
| Fields | |
|---|---|
entity_id |
Required. The ID of the entity. |
feature_values |
Required. Feature values to be written, mapping from Feature ID to value. Up to 100,000 |
WriteFeatureValuesRequest
Request message for FeaturestoreOnlineServingService.WriteFeatureValues.
| Fields | |
|---|---|
entity_type |
Required. The resource name of the EntityType for the entities being written. Value format: |
payloads[] |
Required. The entities to be written. Up to 100,000 feature values can be written across all |
WriteFeatureValuesResponse
This type has no fields.
Response message for FeaturestoreOnlineServingService.WriteFeatureValues.
WriteTensorboardExperimentDataRequest
Request message for TensorboardService.WriteTensorboardExperimentData.
| Fields | |
|---|---|
tensorboard_experiment |
Required. The resource name of the TensorboardExperiment to write data to. Format: |
write_run_data_requests[] |
Required. Requests containing per-run TensorboardTimeSeries data to write. |
WriteTensorboardExperimentDataResponse
This type has no fields.
Response message for TensorboardService.WriteTensorboardExperimentData.
WriteTensorboardRunDataRequest
Request message for TensorboardService.WriteTensorboardRunData.
| Fields | |
|---|---|
tensorboard_run |
Required. The resource name of the TensorboardRun to write data to. Format: |
time_series_data[] |
Required. The TensorboardTimeSeries data to write. Values with in a time series are indexed by their step value. Repeated writes to the same step will overwrite the existing value for that step. The upper limit of data points per write request is 5000. |
WriteTensorboardRunDataResponse
This type has no fields.
Response message for TensorboardService.WriteTensorboardRunData.
XraiAttribution
An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825
Supported only by image Models.
| Fields | |
|---|---|
step_count |
Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range. Valid range of its value is [1, 100], inclusively. |
smooth_grad_config |
Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf |
blur_baseline_config |
Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 |