Cloud AI Platform v1beta1 API - Namespace Google.Cloud.AIPlatform.V1Beta1 (1.0.0-beta08)

Parameters that configure the active learning pipeline. Active learning will label the data incrementally by several iterations. For every iteration, it will select a batch of data based on the sampling strategy.

Request message for [MetadataService.AddContextArtifactsAndExecutions][google.cloud.aiplatform.v1beta1.MetadataService.AddContextArtifactsAndExecutions].

Response message for [MetadataService.AddContextArtifactsAndExecutions][google.cloud.aiplatform.v1beta1.MetadataService.AddContextArtifactsAndExecutions].

Request message for [MetadataService.AddContextChildren][google.cloud.aiplatform.v1beta1.MetadataService.AddContextChildren].

Response message for [MetadataService.AddContextChildren][google.cloud.aiplatform.v1beta1.MetadataService.AddContextChildren].

Request message for [MetadataService.AddExecutionEvents][google.cloud.aiplatform.v1beta1.MetadataService.AddExecutionEvents].

Response message for [MetadataService.AddExecutionEvents][google.cloud.aiplatform.v1beta1.MetadataService.AddExecutionEvents].

Request message for [VizierService.AddTrialMeasurement][google.cloud.aiplatform.v1beta1.VizierService.AddTrialMeasurement].

Resource name for the AnnotatedDataset resource.

Used to assign specific AnnotationSpec to a particular area of a DataItem or the whole part of the DataItem.

Resource name for the Annotation resource.

Identifies a concept with which DataItems may be annotated with.

Resource name for the AnnotationSpec resource.

The generic reusable api auth config.

Container for nested types declared in the ApiAuth message type.

The API secret.

Instance of a general artifact.

Container for nested types declared in the Artifact message type.

Resource name for the Artifact resource.

The definition of a artifact type in MLMD.

Metadata information for [NotebookService.AssignNotebookRuntime][google.cloud.aiplatform.v1beta1.NotebookService.AssignNotebookRuntime].

Request message for [NotebookService.AssignNotebookRuntime][google.cloud.aiplatform.v1beta1.NotebookService.AssignNotebookRuntime].

Attribution that explains a particular prediction output.

Auth configuration to run the extension.

Container for nested types declared in the AuthConfig message type.

Config for authentication with API key.

Config for Google Service Account Authentication.

Config for HTTP Basic Authentication.

Config for user oauth.

Config for user OIDC auth.

Resource name for the AutoMLDataset resource.

Resource name for the AutoMLModel resource.

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.

The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.

The storage details for Avro input content.

Runtime operation information for [PipelineService.BatchCancelPipelineJobs][google.cloud.aiplatform.v1beta1.PipelineService.BatchCancelPipelineJobs].

Request message for [PipelineService.BatchCancelPipelineJobs][google.cloud.aiplatform.v1beta1.PipelineService.BatchCancelPipelineJobs].

Response message for [PipelineService.BatchCancelPipelineJobs][google.cloud.aiplatform.v1beta1.PipelineService.BatchCancelPipelineJobs].

Details of operations that perform batch create Features.

Request message for [FeaturestoreService.BatchCreateFeatures][google.cloud.aiplatform.v1beta1.FeaturestoreService.BatchCreateFeatures].

Response message for [FeaturestoreService.BatchCreateFeatures][google.cloud.aiplatform.v1beta1.FeaturestoreService.BatchCreateFeatures].

Request message for [TensorboardService.BatchCreateTensorboardRuns][google.cloud.aiplatform.v1beta1.TensorboardService.BatchCreateTensorboardRuns].

Response message for [TensorboardService.BatchCreateTensorboardRuns][google.cloud.aiplatform.v1beta1.TensorboardService.BatchCreateTensorboardRuns].

Request message for [TensorboardService.BatchCreateTensorboardTimeSeries][google.cloud.aiplatform.v1beta1.TensorboardService.BatchCreateTensorboardTimeSeries].

Response message for [TensorboardService.BatchCreateTensorboardTimeSeries][google.cloud.aiplatform.v1beta1.TensorboardService.BatchCreateTensorboardTimeSeries].

A description of resources that are used for performing batch operations, are dedicated to a Model, and need manual configuration.

Request message for [PipelineService.BatchDeletePipelineJobs][google.cloud.aiplatform.v1beta1.PipelineService.BatchDeletePipelineJobs].

Response message for [PipelineService.BatchDeletePipelineJobs][google.cloud.aiplatform.v1beta1.PipelineService.BatchDeletePipelineJobs].

Request message for [ModelService.BatchImportEvaluatedAnnotations][google.cloud.aiplatform.v1beta1.ModelService.BatchImportEvaluatedAnnotations]

Response message for [ModelService.BatchImportEvaluatedAnnotations][google.cloud.aiplatform.v1beta1.ModelService.BatchImportEvaluatedAnnotations]

Request message for [ModelService.BatchImportModelEvaluationSlices][google.cloud.aiplatform.v1beta1.ModelService.BatchImportModelEvaluationSlices]

Response message for [ModelService.BatchImportModelEvaluationSlices][google.cloud.aiplatform.v1beta1.ModelService.BatchImportModelEvaluationSlices]

Runtime operation information for [MigrationService.BatchMigrateResources][google.cloud.aiplatform.v1beta1.MigrationService.BatchMigrateResources].

Container for nested types declared in the BatchMigrateResourcesOperationMetadata message type.

Represents a partial result in batch migration operation for one [MigrateResourceRequest][google.cloud.aiplatform.v1beta1.MigrateResourceRequest].

Request message for [MigrationService.BatchMigrateResources][google.cloud.aiplatform.v1beta1.MigrationService.BatchMigrateResources].

Response message for [MigrationService.BatchMigrateResources][google.cloud.aiplatform.v1beta1.MigrationService.BatchMigrateResources].

A job that uses a [Model][google.cloud.aiplatform.v1beta1.BatchPredictionJob.model] to produce predictions on multiple [input instances][google.cloud.aiplatform.v1beta1.BatchPredictionJob.input_config]. If predictions for significant portion of the instances fail, the job may finish without attempting predictions for all remaining instances.

Container for nested types declared in the BatchPredictionJob message type.

Configures the input to [BatchPredictionJob][google.cloud.aiplatform.v1beta1.BatchPredictionJob]. See [Model.supported_input_storage_formats][google.cloud.aiplatform.v1beta1.Model.supported_input_storage_formats] for Model's supported input formats, and how instances should be expressed via any of them.

Configuration defining how to transform batch prediction input instances to the instances that the Model accepts.

Configures the output of [BatchPredictionJob][google.cloud.aiplatform.v1beta1.BatchPredictionJob]. See [Model.supported_output_storage_formats][google.cloud.aiplatform.v1beta1.Model.supported_output_storage_formats] for supported output formats, and how predictions are expressed via any of them.

Further describes this job's output. Supplements [output_config][google.cloud.aiplatform.v1beta1.BatchPredictionJob.output_config].

Resource name for the BatchPredictionJob resource.

Details of operations that batch reads Feature values.

Request message for [FeaturestoreService.BatchReadFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreService.BatchReadFeatureValues].

Container for nested types declared in the BatchReadFeatureValuesRequest message type.

Selects Features of an EntityType to read values of and specifies read settings.

Describe pass-through fields in read_instance source.

Response message for [FeaturestoreService.BatchReadFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreService.BatchReadFeatureValues].

Request message for [TensorboardService.BatchReadTensorboardTimeSeriesData][google.cloud.aiplatform.v1beta1.TensorboardService.BatchReadTensorboardTimeSeriesData].

Response message for [TensorboardService.BatchReadTensorboardTimeSeriesData][google.cloud.aiplatform.v1beta1.TensorboardService.BatchReadTensorboardTimeSeriesData].

The BigQuery location for the output content.

The BigQuery location for the input content.

Input for bleu metric.

Spec for bleu instance.

Bleu metric value for an instance.

Results for bleu metric.

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.

Content blob.

It's preferred to send as [text][google.cloud.aiplatform.v1beta1.Part.text] directly rather than raw bytes.

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

A list of boolean values.

A resource used in LLM queries for users to explicitly specify what to cache and how to cache.

Container for nested types declared in the CachedContent message type.

Metadata on the usage of the cached content.

Resource name for the CachedContent resource.

Request message for [JobService.CancelBatchPredictionJob][google.cloud.aiplatform.v1beta1.JobService.CancelBatchPredictionJob].

Request message for [JobService.CancelCustomJob][google.cloud.aiplatform.v1beta1.JobService.CancelCustomJob].

Request message for [JobService.CancelDataLabelingJob][google.cloud.aiplatform.v1beta1.JobService.CancelDataLabelingJob].

Request message for [JobService.CancelHyperparameterTuningJob][google.cloud.aiplatform.v1beta1.JobService.CancelHyperparameterTuningJob].

Request message for [JobService.CancelNasJob][google.cloud.aiplatform.v1beta1.JobService.CancelNasJob].

Request message for [PipelineService.CancelPipelineJob][google.cloud.aiplatform.v1beta1.PipelineService.CancelPipelineJob].

Request message for [PipelineService.CancelTrainingPipeline][google.cloud.aiplatform.v1beta1.PipelineService.CancelTrainingPipeline].

Request message for [GenAiTuningService.CancelTuningJob][google.cloud.aiplatform.v1beta1.GenAiTuningService.CancelTuningJob].

A response candidate generated from the model.

Container for nested types declared in the Candidate message type.

Request message for [PredictionService.ChatCompletions]

This message will be placed in the metadata field of a google.longrunning.Operation associated with a CheckTrialEarlyStoppingState request.

Request message for [VizierService.CheckTrialEarlyStoppingState][google.cloud.aiplatform.v1beta1.VizierService.CheckTrialEarlyStoppingState].

Response message for [VizierService.CheckTrialEarlyStoppingState][google.cloud.aiplatform.v1beta1.VizierService.CheckTrialEarlyStoppingState].

Source attributions for content.

A collection of source attributions for a piece of content.

Input for coherence metric.

Spec for coherence instance.

Spec for coherence result.

Spec for coherence score metric.

Request message for [VizierService.CompleteTrial][google.cloud.aiplatform.v1beta1.VizierService.CompleteTrial].

Success and error statistics of processing multiple entities (for example, DataItems or structured data rows) in batch.

Request message for ComputeTokens RPC call.

Response message for ComputeTokens RPC call.

The Container Registry location for the container image.

The spec of a Container.

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.

Instance of a general context.

Resource name for the Context resource.

Details of [ModelService.CopyModel][google.cloud.aiplatform.v1beta1.ModelService.CopyModel] operation.

Request message for [ModelService.CopyModel][google.cloud.aiplatform.v1beta1.ModelService.CopyModel].

Response message of [ModelService.CopyModel][google.cloud.aiplatform.v1beta1.ModelService.CopyModel] operation.

RagCorpus status.

Container for nested types declared in the CorpusStatus message type.

Request message for [PredictionService.CountTokens][google.cloud.aiplatform.v1beta1.PredictionService.CountTokens].

Response message for [PredictionService.CountTokens][google.cloud.aiplatform.v1beta1.PredictionService.CountTokens].

Request message for [MetadataService.CreateArtifact][google.cloud.aiplatform.v1beta1.MetadataService.CreateArtifact].

Request message for [JobService.CreateBatchPredictionJob][google.cloud.aiplatform.v1beta1.JobService.CreateBatchPredictionJob].

Request message for [GenAiCacheService.CreateCachedContent][google.cloud.aiplatform.v1beta1.GenAiCacheService.CreateCachedContent].

Request message for [MetadataService.CreateContext][google.cloud.aiplatform.v1beta1.MetadataService.CreateContext].

Request message for [JobService.CreateCustomJob][google.cloud.aiplatform.v1beta1.JobService.CreateCustomJob].

Request message for [JobService.CreateDataLabelingJob][google.cloud.aiplatform.v1beta1.JobService.CreateDataLabelingJob].

Runtime operation information for [DatasetService.CreateDataset][google.cloud.aiplatform.v1beta1.DatasetService.CreateDataset].

Request message for [DatasetService.CreateDataset][google.cloud.aiplatform.v1beta1.DatasetService.CreateDataset].

Runtime operation information for [DatasetService.CreateDatasetVersion][google.cloud.aiplatform.v1beta1.DatasetService.CreateDatasetVersion].

Request message for [DatasetService.CreateDatasetVersion][google.cloud.aiplatform.v1beta1.DatasetService.CreateDatasetVersion].

Runtime operation information for CreateDeploymentResourcePool method.

Request message for CreateDeploymentResourcePool method.

Runtime operation information for [EndpointService.CreateEndpoint][google.cloud.aiplatform.v1beta1.EndpointService.CreateEndpoint].

Request message for [EndpointService.CreateEndpoint][google.cloud.aiplatform.v1beta1.EndpointService.CreateEndpoint].

Details of operations that perform create EntityType.

Request message for [FeaturestoreService.CreateEntityType][google.cloud.aiplatform.v1beta1.FeaturestoreService.CreateEntityType].

Request message for [MetadataService.CreateExecution][google.cloud.aiplatform.v1beta1.MetadataService.CreateExecution].

Details of operations that perform create FeatureGroup.

Request message for [FeatureRegistryService.CreateFeatureGroup][google.cloud.aiplatform.v1beta1.FeatureRegistryService.CreateFeatureGroup].

Details of operations that perform create FeatureOnlineStore.

Request message for [FeatureOnlineStoreAdminService.CreateFeatureOnlineStore][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.CreateFeatureOnlineStore].

Details of operations that perform create Feature.

Request message for [FeaturestoreService.CreateFeature][google.cloud.aiplatform.v1beta1.FeaturestoreService.CreateFeature]. Request message for [FeatureRegistryService.CreateFeature][google.cloud.aiplatform.v1beta1.FeatureRegistryService.CreateFeature].

Details of operations that perform create FeatureView.

Request message for [FeatureOnlineStoreAdminService.CreateFeatureView][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.CreateFeatureView].

Details of operations that perform create Featurestore.

Request message for [FeaturestoreService.CreateFeaturestore][google.cloud.aiplatform.v1beta1.FeaturestoreService.CreateFeaturestore].

Request message for [JobService.CreateHyperparameterTuningJob][google.cloud.aiplatform.v1beta1.JobService.CreateHyperparameterTuningJob].

Runtime operation information for [IndexEndpointService.CreateIndexEndpoint][google.cloud.aiplatform.v1beta1.IndexEndpointService.CreateIndexEndpoint].

Request message for [IndexEndpointService.CreateIndexEndpoint][google.cloud.aiplatform.v1beta1.IndexEndpointService.CreateIndexEndpoint].

Runtime operation information for [IndexService.CreateIndex][google.cloud.aiplatform.v1beta1.IndexService.CreateIndex].

Request message for [IndexService.CreateIndex][google.cloud.aiplatform.v1beta1.IndexService.CreateIndex].

Request message for [MetadataService.CreateMetadataSchema][google.cloud.aiplatform.v1beta1.MetadataService.CreateMetadataSchema].

Details of operations that perform [MetadataService.CreateMetadataStore][google.cloud.aiplatform.v1beta1.MetadataService.CreateMetadataStore].

Request message for [MetadataService.CreateMetadataStore][google.cloud.aiplatform.v1beta1.MetadataService.CreateMetadataStore].

Request message for [JobService.CreateModelDeploymentMonitoringJob][google.cloud.aiplatform.v1beta1.JobService.CreateModelDeploymentMonitoringJob].

Runtime operation information for [ModelMonitoringService.CreateModelMonitor][google.cloud.aiplatform.v1beta1.ModelMonitoringService.CreateModelMonitor].

Request message for [ModelMonitoringService.CreateModelMonitor][google.cloud.aiplatform.v1beta1.ModelMonitoringService.CreateModelMonitor].

Request message for [ModelMonitoringService.CreateModelMonitoringJob][google.cloud.aiplatform.v1beta1.ModelMonitoringService.CreateModelMonitoringJob].

Request message for [JobService.CreateNasJob][google.cloud.aiplatform.v1beta1.JobService.CreateNasJob].

Metadata information for [NotebookService.CreateNotebookExecutionJob][google.cloud.aiplatform.v1beta1.NotebookService.CreateNotebookExecutionJob].

Request message for [NotebookService.CreateNotebookExecutionJob]

Metadata information for [NotebookService.CreateNotebookRuntimeTemplate][google.cloud.aiplatform.v1beta1.NotebookService.CreateNotebookRuntimeTemplate].

Request message for [NotebookService.CreateNotebookRuntimeTemplate][google.cloud.aiplatform.v1beta1.NotebookService.CreateNotebookRuntimeTemplate].

Details of operations that perform create PersistentResource.

Request message for [PersistentResourceService.CreatePersistentResource][google.cloud.aiplatform.v1beta1.PersistentResourceService.CreatePersistentResource].

Request message for [PipelineService.CreatePipelineJob][google.cloud.aiplatform.v1beta1.PipelineService.CreatePipelineJob].

Runtime operation information for [VertexRagDataService.CreateRagCorpus][google.cloud.aiplatform.v1beta1.VertexRagDataService.CreateRagCorpus].

Request message for [VertexRagDataService.CreateRagCorpus][google.cloud.aiplatform.v1beta1.VertexRagDataService.CreateRagCorpus].

Details of [ReasoningEngineService.CreateReasoningEngine][google.cloud.aiplatform.v1beta1.ReasoningEngineService.CreateReasoningEngine] operation.

Request message for [ReasoningEngineService.CreateReasoningEngine][google.cloud.aiplatform.v1beta1.ReasoningEngineService.CreateReasoningEngine].

Details of operations that perform create FeatureGroup.

Request message for [ScheduleService.CreateSchedule][google.cloud.aiplatform.v1beta1.ScheduleService.CreateSchedule].

Runtime operation information for [SpecialistPoolService.CreateSpecialistPool][google.cloud.aiplatform.v1beta1.SpecialistPoolService.CreateSpecialistPool].

Request message for [SpecialistPoolService.CreateSpecialistPool][google.cloud.aiplatform.v1beta1.SpecialistPoolService.CreateSpecialistPool].

Request message for [VizierService.CreateStudy][google.cloud.aiplatform.v1beta1.VizierService.CreateStudy].

Request message for [TensorboardService.CreateTensorboardExperiment][google.cloud.aiplatform.v1beta1.TensorboardService.CreateTensorboardExperiment].

Details of operations that perform create Tensorboard.

Request message for [TensorboardService.CreateTensorboard][google.cloud.aiplatform.v1beta1.TensorboardService.CreateTensorboard].

Request message for [TensorboardService.CreateTensorboardRun][google.cloud.aiplatform.v1beta1.TensorboardService.CreateTensorboardRun].

Request message for [TensorboardService.CreateTensorboardTimeSeries][google.cloud.aiplatform.v1beta1.TensorboardService.CreateTensorboardTimeSeries].

Request message for [PipelineService.CreateTrainingPipeline][google.cloud.aiplatform.v1beta1.PipelineService.CreateTrainingPipeline].

Request message for [VizierService.CreateTrial][google.cloud.aiplatform.v1beta1.VizierService.CreateTrial].

Request message for [GenAiTuningService.CreateTuningJob][google.cloud.aiplatform.v1beta1.GenAiTuningService.CreateTuningJob].

The storage details for CSV output content.

The storage details for CSV input content.

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).

Resource name for the CustomJob resource.

Represents the spec of a CustomJob.

A piece of data in a Dataset. Could be an image, a video, a document or plain text.

Resource name for the DataItem resource.

A container for a single DataItem and Annotations on it.

Resource name for the DataLabelingDataset resource.

DataLabelingJob is used to trigger a human labeling job on unlabeled data from the following Dataset:

Resource name for the DataLabelingJob resource.

A collection of DataItems and Annotations on them.

Distribution computed over a tuning dataset.

Container for nested types declared in the DatasetDistribution message type.

Dataset bucket used to create a histogram for the distribution given a population of values.

Resource name for the Dataset resource.

The service that manages Vertex AI Dataset and its child resources.

Base class for server-side implementations of DatasetService

Client for DatasetService

DatasetService client wrapper, for convenient use.

Builder class for DatasetServiceClient to provide simple configuration of credentials, endpoint etc.

DatasetService client wrapper implementation, for convenient use.

Settings for DatasetServiceClient instances.

Statistics computed over a tuning dataset.

Describes the dataset version.

Resource name for the DatasetVersion resource.

A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration.

Request message for [MetadataService.DeleteArtifact][google.cloud.aiplatform.v1beta1.MetadataService.DeleteArtifact].

Request message for [JobService.DeleteBatchPredictionJob][google.cloud.aiplatform.v1beta1.JobService.DeleteBatchPredictionJob].

Request message for [GenAiCacheService.DeleteCachedContent][google.cloud.aiplatform.v1beta1.GenAiCacheService.DeleteCachedContent].

Request message for [MetadataService.DeleteContext][google.cloud.aiplatform.v1beta1.MetadataService.DeleteContext].

Request message for [JobService.DeleteCustomJob][google.cloud.aiplatform.v1beta1.JobService.DeleteCustomJob].

Request message for [JobService.DeleteDataLabelingJob][google.cloud.aiplatform.v1beta1.JobService.DeleteDataLabelingJob].

Request message for [DatasetService.DeleteDataset][google.cloud.aiplatform.v1beta1.DatasetService.DeleteDataset].

Request message for [DatasetService.DeleteDatasetVersion][google.cloud.aiplatform.v1beta1.DatasetService.DeleteDatasetVersion].

Request message for DeleteDeploymentResourcePool method.

Request message for [EndpointService.DeleteEndpoint][google.cloud.aiplatform.v1beta1.EndpointService.DeleteEndpoint].

Request message for [FeaturestoreService.DeleteEntityTypes][].

Request message for [MetadataService.DeleteExecution][google.cloud.aiplatform.v1beta1.MetadataService.DeleteExecution].

Request message for [ExtensionRegistryService.DeleteExtension][google.cloud.aiplatform.v1beta1.ExtensionRegistryService.DeleteExtension].

Request message for [FeatureRegistryService.DeleteFeatureGroup][google.cloud.aiplatform.v1beta1.FeatureRegistryService.DeleteFeatureGroup].

Request message for [FeatureOnlineStoreAdminService.DeleteFeatureOnlineStore][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.DeleteFeatureOnlineStore].

Request message for [FeaturestoreService.DeleteFeature][google.cloud.aiplatform.v1beta1.FeaturestoreService.DeleteFeature]. Request message for [FeatureRegistryService.DeleteFeature][google.cloud.aiplatform.v1beta1.FeatureRegistryService.DeleteFeature].

Details of operations that delete Feature values.

Request message for [FeaturestoreService.DeleteFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreService.DeleteFeatureValues].

Container for nested types declared in the DeleteFeatureValuesRequest message type.

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.

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.

Response message for [FeaturestoreService.DeleteFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreService.DeleteFeatureValues].

Container for nested types declared in the DeleteFeatureValuesResponse message type.

Response message if the request uses the SelectEntity option.

Response message if the request uses the SelectTimeRangeAndFeature option.

Request message for [FeatureOnlineStoreAdminService.DeleteFeatureViews][].

Request message for [FeaturestoreService.DeleteFeaturestore][google.cloud.aiplatform.v1beta1.FeaturestoreService.DeleteFeaturestore].

Request message for [JobService.DeleteHyperparameterTuningJob][google.cloud.aiplatform.v1beta1.JobService.DeleteHyperparameterTuningJob].

Request message for [IndexEndpointService.DeleteIndexEndpoint][google.cloud.aiplatform.v1beta1.IndexEndpointService.DeleteIndexEndpoint].

Request message for [IndexService.DeleteIndex][google.cloud.aiplatform.v1beta1.IndexService.DeleteIndex].

Details of operations that perform [MetadataService.DeleteMetadataStore][google.cloud.aiplatform.v1beta1.MetadataService.DeleteMetadataStore].

Request message for [MetadataService.DeleteMetadataStore][google.cloud.aiplatform.v1beta1.MetadataService.DeleteMetadataStore].

Request message for [JobService.DeleteModelDeploymentMonitoringJob][google.cloud.aiplatform.v1beta1.JobService.DeleteModelDeploymentMonitoringJob].

Request message for [ModelMonitoringService.DeleteModelMonitor][google.cloud.aiplatform.v1beta1.ModelMonitoringService.DeleteModelMonitor].

Request message for [ModelMonitoringService.DeleteModelMonitoringJob][google.cloud.aiplatform.v1beta1.ModelMonitoringService.DeleteModelMonitoringJob].

Request message for [ModelService.DeleteModel][google.cloud.aiplatform.v1beta1.ModelService.DeleteModel].

Request message for [ModelService.DeleteModelVersion][google.cloud.aiplatform.v1beta1.ModelService.DeleteModelVersion].

Request message for [JobService.DeleteNasJob][google.cloud.aiplatform.v1beta1.JobService.DeleteNasJob].

Request message for [NotebookService.DeleteNotebookExecutionJob]

Request message for [NotebookService.DeleteNotebookRuntime][google.cloud.aiplatform.v1beta1.NotebookService.DeleteNotebookRuntime].

Request message for [NotebookService.DeleteNotebookRuntimeTemplate][google.cloud.aiplatform.v1beta1.NotebookService.DeleteNotebookRuntimeTemplate].

Details of operations that perform deletes of any entities.

Request message for [PersistentResourceService.DeletePersistentResource][google.cloud.aiplatform.v1beta1.PersistentResourceService.DeletePersistentResource].

Request message for [PipelineService.DeletePipelineJob][google.cloud.aiplatform.v1beta1.PipelineService.DeletePipelineJob].

Request message for [VertexRagDataService.DeleteRagCorpus][google.cloud.aiplatform.v1beta1.VertexRagDataService.DeleteRagCorpus].

Request message for [VertexRagDataService.DeleteRagFile][google.cloud.aiplatform.v1beta1.VertexRagDataService.DeleteRagFile].

Request message for [ReasoningEngineService.DeleteReasoningEngine][google.cloud.aiplatform.v1beta1.ReasoningEngineService.DeleteReasoningEngine].

Request message for [DatasetService.DeleteSavedQuery][google.cloud.aiplatform.v1beta1.DatasetService.DeleteSavedQuery].

Request message for [ScheduleService.DeleteSchedule][google.cloud.aiplatform.v1beta1.ScheduleService.DeleteSchedule].

Request message for [SpecialistPoolService.DeleteSpecialistPool][google.cloud.aiplatform.v1beta1.SpecialistPoolService.DeleteSpecialistPool].

Request message for [VizierService.DeleteStudy][google.cloud.aiplatform.v1beta1.VizierService.DeleteStudy].

Request message for [TensorboardService.DeleteTensorboardExperiment][google.cloud.aiplatform.v1beta1.TensorboardService.DeleteTensorboardExperiment].

Request message for [TensorboardService.DeleteTensorboard][google.cloud.aiplatform.v1beta1.TensorboardService.DeleteTensorboard].

Request message for [TensorboardService.DeleteTensorboardRun][google.cloud.aiplatform.v1beta1.TensorboardService.DeleteTensorboardRun].

Request message for [TensorboardService.DeleteTensorboardTimeSeries][google.cloud.aiplatform.v1beta1.TensorboardService.DeleteTensorboardTimeSeries].

Request message for [PipelineService.DeleteTrainingPipeline][google.cloud.aiplatform.v1beta1.PipelineService.DeleteTrainingPipeline].

Request message for [VizierService.DeleteTrial][google.cloud.aiplatform.v1beta1.VizierService.DeleteTrial].

Runtime operation information for [IndexEndpointService.DeployIndex][google.cloud.aiplatform.v1beta1.IndexEndpointService.DeployIndex].

Request message for [IndexEndpointService.DeployIndex][google.cloud.aiplatform.v1beta1.IndexEndpointService.DeployIndex].

Response message for [IndexEndpointService.DeployIndex][google.cloud.aiplatform.v1beta1.IndexEndpointService.DeployIndex].

Runtime operation information for [EndpointService.DeployModel][google.cloud.aiplatform.v1beta1.EndpointService.DeployModel].

Request message for [EndpointService.DeployModel][google.cloud.aiplatform.v1beta1.EndpointService.DeployModel].

Response message for [EndpointService.DeployModel][google.cloud.aiplatform.v1beta1.EndpointService.DeployModel].

A deployment of an Index. IndexEndpoints contain one or more DeployedIndexes.

Used to set up the auth on the DeployedIndex's private endpoint.

Container for nested types declared in the DeployedIndexAuthConfig message type.

Configuration for an authentication provider, including support for JSON Web Token (JWT).

Points to a DeployedIndex.

A deployment of a Model. Endpoints contain one or more DeployedModels.

Points to a DeployedModel.

A description of resources that can be shared by multiple DeployedModels, whose underlying specification consists of a DedicatedResources.

Resource name for the DeploymentResourcePool resource.

A service that manages the DeploymentResourcePool resource.

Base class for server-side implementations of DeploymentResourcePoolService

Client for DeploymentResourcePoolService

DeploymentResourcePoolService client wrapper, for convenient use.

Builder class for DeploymentResourcePoolServiceClient to provide simple configuration of credentials, endpoint etc.

DeploymentResourcePoolService client wrapper implementation, for convenient use.

Settings for DeploymentResourcePoolServiceClient instances.

Request message for [PredictionService.DirectPredict][google.cloud.aiplatform.v1beta1.PredictionService.DirectPredict].

Response message for [PredictionService.DirectPredict][google.cloud.aiplatform.v1beta1.PredictionService.DirectPredict].

Request message for [PredictionService.DirectRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.DirectRawPredict].

Response message for [PredictionService.DirectRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.DirectRawPredict].

The input content is encapsulated and uploaded in the request.

Represents the spec of disk options.

Statistics computed for datasets used for distillation.

Hyperparameters for Distillation.

Tuning Spec for Distillation.

A list of double values.

Describes the options to customize dynamic retrieval.

Container for nested types declared in the DynamicRetrievalConfig message type.

Represents a customer-managed encryption key spec that can be applied to a top-level resource.

Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.

Resource name for the Endpoint resource.

A service for managing Vertex AI's Endpoints.

Base class for server-side implementations of EndpointService

Client for EndpointService

EndpointService client wrapper, for convenient use.

Builder class for EndpointServiceClient to provide simple configuration of credentials, endpoint etc.

EndpointService client wrapper implementation, for convenient use.

Settings for EndpointServiceClient instances.

Selector for entityId. Getting ids from the given source.

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.

Resource name for the EntityType resource.

Represents an environment variable present in a Container or Python Module.

Model error analysis for each annotation.

Container for nested types declared in the ErrorAnalysisAnnotation message type.

Attributed items for a given annotation, typically representing neighbors from the training sets constrained by the query type.

Request message for EvaluationService.EvaluateInstances.

Response message for EvaluationService.EvaluateInstances.

True positive, false positive, or false negative.

EvaluatedAnnotation is only available under ModelEvaluationSlice with slice of annotationSpec dimension.

Container for nested types declared in the EvaluatedAnnotation message type.

Explanation result of the prediction produced by the Model.

Vertex AI Online Evaluation Service.

Base class for server-side implementations of EvaluationService

Client for EvaluationService

EvaluationService client wrapper, for convenient use.

Builder class for EvaluationServiceClient to provide simple configuration of credentials, endpoint etc.

EvaluationService client wrapper implementation, for convenient use.

Settings for EvaluationServiceClient instances.

An edge describing the relationship between an Artifact and an Execution in a lineage graph.

Container for nested types declared in the Event message type.

Input for exact match metric.

Spec for exact match instance.

Exact match metric value for an instance.

Results for exact match metric.

Spec for exact match metric - returns 1 if prediction and reference exactly matches, otherwise 0.

Example-based explainability that returns the nearest neighbors from the provided dataset.

Container for nested types declared in the Examples message type.

The Cloud Storage input instances.

Container for nested types declared in the ExampleGcsSource message type.

Overrides for example-based explanations.

Container for nested types declared in the ExamplesOverride message type.

Restrictions namespace for example-based explanations overrides.

Request message for [ExtensionExecutionService.ExecuteExtension][google.cloud.aiplatform.v1beta1.ExtensionExecutionService.ExecuteExtension].

Response message for [ExtensionExecutionService.ExecuteExtension][google.cloud.aiplatform.v1beta1.ExtensionExecutionService.ExecuteExtension].

Instance of a general execution.

Container for nested types declared in the Execution message type.

Resource name for the Execution resource.

Request message for [PredictionService.Explain][google.cloud.aiplatform.v1beta1.PredictionService.Explain].

Response message for [PredictionService.Explain][google.cloud.aiplatform.v1beta1.PredictionService.Explain].

Container for nested types declared in the ExplainResponse message type.

This message is a wrapper grouping Concurrent Explanations.

Explanation of a prediction (provided in [PredictResponse.predictions][google.cloud.aiplatform.v1beta1.PredictResponse.predictions]) produced by the Model on a given [instance][google.cloud.aiplatform.v1beta1.ExplainRequest.instances].

Metadata describing the Model's input and output for explanation.

Container for nested types declared in the ExplanationMetadata message type.

Metadata of the input of a feature.

Fields other than [InputMetadata.input_baselines][google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.input_baselines] are applicable only for Models that are using Vertex AI-provided images for Tensorflow.

Container for nested types declared in the InputMetadata message type.

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.

Visualization configurations for image explanation.

Container for nested types declared in the Visualization message type.

Metadata of the prediction output to be explained.

The [ExplanationMetadata][google.cloud.aiplatform.v1beta1.ExplanationMetadata] entries that can be overridden at [online explanation][google.cloud.aiplatform.v1beta1.PredictionService.Explain] time.

Container for nested types declared in the ExplanationMetadataOverride message type.

The [input metadata][google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata] entries to be overridden.

Parameters to configure explaining for Model's predictions.

Specification of Model explanation.

The [ExplanationSpec][google.cloud.aiplatform.v1beta1.ExplanationSpec] entries that can be overridden at [online explanation][google.cloud.aiplatform.v1beta1.PredictionService.Explain] time.

Describes what part of the Dataset is to be exported, the destination of the export and how to export.

Runtime operation information for [DatasetService.ExportData][google.cloud.aiplatform.v1beta1.DatasetService.ExportData].

Request message for [DatasetService.ExportData][google.cloud.aiplatform.v1beta1.DatasetService.ExportData].

Response message for [DatasetService.ExportData][google.cloud.aiplatform.v1beta1.DatasetService.ExportData].

Details of operations that exports Features values.

Request message for [FeaturestoreService.ExportFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreService.ExportFeatureValues].

Container for nested types declared in the ExportFeatureValuesRequest message type.

Describes exporting all historical Feature values of all entities of the EntityType between [start_time, end_time].

Describes exporting the latest Feature values of all entities of the EntityType between [start_time, snapshot_time].

Response message for [FeaturestoreService.ExportFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreService.ExportFeatureValues].

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.

Details of [ModelService.ExportModel][google.cloud.aiplatform.v1beta1.ModelService.ExportModel] operation.

Container for nested types declared in the ExportModelOperationMetadata message type.

Further describes the output of the ExportModel. Supplements [ExportModelRequest.OutputConfig][google.cloud.aiplatform.v1beta1.ExportModelRequest.OutputConfig].

Request message for [ModelService.ExportModel][google.cloud.aiplatform.v1beta1.ModelService.ExportModel].

Container for nested types declared in the ExportModelRequest message type.

Output configuration for the Model export.

Response message of [ModelService.ExportModel][google.cloud.aiplatform.v1beta1.ModelService.ExportModel] operation.

Request message for [TensorboardService.ExportTensorboardTimeSeriesData][google.cloud.aiplatform.v1beta1.TensorboardService.ExportTensorboardTimeSeriesData].

Response message for [TensorboardService.ExportTensorboardTimeSeriesData][google.cloud.aiplatform.v1beta1.TensorboardService.ExportTensorboardTimeSeriesData].

Extensions are tools for large language models to access external data, run computations, etc.

A service for Extension execution.

Base class for server-side implementations of ExtensionExecutionService

Client for ExtensionExecutionService

ExtensionExecutionService client wrapper, for convenient use.

Builder class for ExtensionExecutionServiceClient to provide simple configuration of credentials, endpoint etc.

ExtensionExecutionService client wrapper implementation, for convenient use.

Settings for ExtensionExecutionServiceClient instances.

Manifest spec of an Extension needed for runtime execution.

Container for nested types declared in the ExtensionManifest message type.

The API specification shown to the LLM.

Resource name for the Extension resource.

Operation of an extension.

PrivateExtensionConfig configuration for the extension.

A service for managing Vertex AI's Extension registry.

Base class for server-side implementations of ExtensionRegistryService

Client for ExtensionRegistryService

ExtensionRegistryService client wrapper, for convenient use.

Builder class for ExtensionRegistryServiceClient to provide simple configuration of credentials, endpoint etc.

ExtensionRegistryService client wrapper implementation, for convenient use.

Settings for ExtensionRegistryServiceClient instances.

Configuration for faster model deployment.

Feature Metadata information. For example, color is a feature that describes an apple.

Container for nested types declared in the Feature message type.

A list of historical [SnapshotAnalysis][google.cloud.aiplatform.v1beta1.FeaturestoreMonitoringConfig.SnapshotAnalysis] or [ImportFeaturesAnalysis][google.cloud.aiplatform.v1beta1.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis] stats requested by user, sorted by [FeatureStatsAnomaly.start_time][google.cloud.aiplatform.v1beta1.FeatureStatsAnomaly.start_time] descending.

Container for nested types declared in the MonitoringStatsAnomaly message type.

Vertex AI Feature Group.

Container for nested types declared in the FeatureGroup message type.

Input source type for BigQuery Tables and Views.

Container for nested types declared in the BigQuery message type.

Resource name for the FeatureGroup resource.

Resource name for the Feature resource.

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.

Container for nested types declared in the FeatureNoiseSigma message type.

Noise sigma for a single feature.

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.

Container for nested types declared in the FeatureOnlineStore message type.

Container for nested types declared in the Bigtable message type.

The dedicated serving endpoint for this FeatureOnlineStore. Only need to set when you choose Optimized storage type. Public endpoint is provisioned by default.

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.

Optimized storage type

The service that handles CRUD and List for resources for FeatureOnlineStore.

Base class for server-side implementations of FeatureOnlineStoreAdminService

Client for FeatureOnlineStoreAdminService

FeatureOnlineStoreAdminService client wrapper, for convenient use.

Builder class for FeatureOnlineStoreAdminServiceClient to provide simple configuration of credentials, endpoint etc.

FeatureOnlineStoreAdminService client wrapper implementation, for convenient use.

Settings for FeatureOnlineStoreAdminServiceClient instances.

Resource name for the FeatureOnlineStore resource.

A service for fetching feature values from the online store.

Base class for server-side implementations of FeatureOnlineStoreService

Client for FeatureOnlineStoreService

FeatureOnlineStoreService client wrapper, for convenient use.

Bidirectional streaming methods for StreamingFetchFeatureValues(CallSettings, BidirectionalStreamingSettings).

Builder class for FeatureOnlineStoreServiceClient to provide simple configuration of credentials, endpoint etc.

FeatureOnlineStoreService client wrapper implementation, for convenient use.

Settings for FeatureOnlineStoreServiceClient instances.

The service that handles CRUD and List for resources for FeatureRegistry.

Base class for server-side implementations of FeatureRegistryService

Client for FeatureRegistryService

FeatureRegistryService client wrapper, for convenient use.

Builder class for FeatureRegistryServiceClient to provide simple configuration of credentials, endpoint etc.

FeatureRegistryService client wrapper implementation, for convenient use.

Settings for FeatureRegistryServiceClient instances.

Selector for Features of an EntityType.

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.

Value for a feature.

Container for nested types declared in the FeatureValue message type.

Metadata of feature value.

A destination location for Feature values and format.

Container for list of values.

FeatureView is representation of values that the FeatureOnlineStore will serve based on its syncConfig.

Container for nested types declared in the FeatureView message type.

A Feature Registry source for features that need to be synced to Online Store.

Container for nested types declared in the FeatureRegistrySource message type.

Features belonging to a single feature group that will be synced to Online Store.

Configuration for vector indexing.

Container for nested types declared in the IndexConfig message type.

Configuration options for using brute force search.

Configuration options for the tree-AH algorithm.

Configuration for Sync. Only one option is set.

Deprecated. Use [IndexConfig][google.cloud.aiplatform.v1beta1.FeatureView.IndexConfig] instead.

Container for nested types declared in the VectorSearchConfig message type.

A Vertex Rag source for features that need to be synced to Online Store.

Lookup key for a feature view.

Container for nested types declared in the FeatureViewDataKey message type.

ID that is comprised from several parts (columns).

Resource name for the FeatureView resource.

FeatureViewSync is a representation of sync operation which copies data from data source to Feature View in Online Store.

Container for nested types declared in the FeatureViewSync message type.

Summary from the Sync job. For continuous syncs, the summary is updated periodically. For batch syncs, it gets updated on completion of the sync.

Resource name for the FeatureViewSync resource.

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.

Container for nested types declared in the Featurestore message type.

OnlineServingConfig specifies the details for provisioning online serving resources.

Container for nested types declared in the OnlineServingConfig message type.

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).

Configuration of how features in Featurestore are monitored.

Container for nested types declared in the FeaturestoreMonitoringConfig message type.

Configuration of the Featurestore's ImportFeature Analysis Based Monitoring. This type of analysis generates statistics for values of each Feature imported by every [ImportFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreService.ImportFeatureValues] operation.

Container for nested types declared in the ImportFeaturesAnalysis message type.

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.

The config for Featurestore Monitoring threshold.

Resource name for the Featurestore resource.

A service for serving online feature values.

Base class for server-side implementations of FeaturestoreOnlineServingService

Client for FeaturestoreOnlineServingService

FeaturestoreOnlineServingService client wrapper, for convenient use.

Server streaming methods for StreamingReadFeatureValues(StreamingReadFeatureValuesRequest, CallSettings).

Builder class for FeaturestoreOnlineServingServiceClient to provide simple configuration of credentials, endpoint etc.

FeaturestoreOnlineServingService client wrapper implementation, for convenient use.

Settings for FeaturestoreOnlineServingServiceClient instances.

The service that handles CRUD and List for resources for Featurestore.

Base class for server-side implementations of FeaturestoreService

Client for FeaturestoreService

FeaturestoreService client wrapper, for convenient use.

Builder class for FeaturestoreServiceClient to provide simple configuration of credentials, endpoint etc.

FeaturestoreService client wrapper implementation, for convenient use.

Settings for FeaturestoreServiceClient instances.

Request message for [FeatureOnlineStoreService.FetchFeatureValues][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreService.FetchFeatureValues]. All the features under the requested feature view will be returned.

Container for nested types declared in the FetchFeatureValuesRequest message type.

Response message for [FeatureOnlineStoreService.FetchFeatureValues][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreService.FetchFeatureValues]

Container for nested types declared in the FetchFeatureValuesResponse message type.

Response structure in the format of key (feature name) and (feature) value pair.

Container for nested types declared in the FeatureNameValuePairList message type.

Feature name & value pair.

URI based data.

RagFile status.

Container for nested types declared in the FileStatus message type.

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.

The request message for [MatchService.FindNeighbors][google.cloud.aiplatform.v1beta1.MatchService.FindNeighbors].

Container for nested types declared in the FindNeighborsRequest message type.

A query to find a number of the nearest neighbors (most similar vectors) of a vector.

Container for nested types declared in the Query message type.

Parameters for RRF algorithm that combines search results.

The response message for [MatchService.FindNeighbors][google.cloud.aiplatform.v1beta1.MatchService.FindNeighbors].

Container for nested types declared in the FindNeighborsResponse message type.

Nearest neighbors for one query.

A neighbor of the query vector.

Input for fluency metric.

Spec for fluency instance.

Spec for fluency result.

Spec for fluency score metric.

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.

Input for fulfillment metric.

Spec for fulfillment instance.

Spec for fulfillment result.

Spec for fulfillment metric.

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.

Function calling config.

Container for nested types declared in the FunctionCallingConfig message type.

Structured representation of a function declaration as defined by the OpenAPI 3.0 specification. Included in this declaration are the function name and parameters. 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.

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.

The Google Cloud Storage location where the output is to be written to.

The Google Cloud Storage location for the input content.

Service for managing Vertex AI's CachedContent resource.

Base class for server-side implementations of GenAiCacheService

Client for GenAiCacheService

GenAiCacheService client wrapper, for convenient use.

Builder class for GenAiCacheServiceClient to provide simple configuration of credentials, endpoint etc.

GenAiCacheService client wrapper implementation, for convenient use.

Settings for GenAiCacheServiceClient instances.

A service for creating and managing GenAI Tuning Jobs.

Base class for server-side implementations of GenAiTuningService

Client for GenAiTuningService

GenAiTuningService client wrapper, for convenient use.

Builder class for GenAiTuningServiceClient to provide simple configuration of credentials, endpoint etc.

GenAiTuningService client wrapper implementation, for convenient use.

Settings for GenAiTuningServiceClient instances.

Request message for [PredictionService.GenerateContent].

Response message for [PredictionService.GenerateContent].

Container for nested types declared in the GenerateContentResponse message type.

Content filter results for a prompt sent in the request.

Container for nested types declared in the PromptFeedback message type.

Usage metadata about response(s).

Generate video response.

Generation config.

Container for nested types declared in the GenerationConfig message type.

The configuration for routing the request to a specific model.

Container for nested types declared in the RoutingConfig message type.

When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference.

Container for nested types declared in the AutoRoutingMode message type.

When manual routing is set, the specified model will be used directly.

Generic Metadata shared by all operations.

Contains information about the source of the models generated from Generative AI Studio.

Request message for [DatasetService.GetAnnotationSpec][google.cloud.aiplatform.v1beta1.DatasetService.GetAnnotationSpec].

Request message for [MetadataService.GetArtifact][google.cloud.aiplatform.v1beta1.MetadataService.GetArtifact].

Request message for [JobService.GetBatchPredictionJob][google.cloud.aiplatform.v1beta1.JobService.GetBatchPredictionJob].

Request message for [GenAiCacheService.GetCachedContent][google.cloud.aiplatform.v1beta1.GenAiCacheService.GetCachedContent].

Request message for [MetadataService.GetContext][google.cloud.aiplatform.v1beta1.MetadataService.GetContext].

Request message for [JobService.GetCustomJob][google.cloud.aiplatform.v1beta1.JobService.GetCustomJob].

Request message for [JobService.GetDataLabelingJob][google.cloud.aiplatform.v1beta1.JobService.GetDataLabelingJob].

Request message for [DatasetService.GetDataset][google.cloud.aiplatform.v1beta1.DatasetService.GetDataset].

Request message for [DatasetService.GetDatasetVersion][google.cloud.aiplatform.v1beta1.DatasetService.GetDatasetVersion].

Request message for GetDeploymentResourcePool method.

Request message for [EndpointService.GetEndpoint][google.cloud.aiplatform.v1beta1.EndpointService.GetEndpoint]

Request message for [FeaturestoreService.GetEntityType][google.cloud.aiplatform.v1beta1.FeaturestoreService.GetEntityType].

Request message for [MetadataService.GetExecution][google.cloud.aiplatform.v1beta1.MetadataService.GetExecution].

Request message for [ExtensionRegistryService.GetExtension][google.cloud.aiplatform.v1beta1.ExtensionRegistryService.GetExtension].

Request message for [FeatureRegistryService.GetFeatureGroup][google.cloud.aiplatform.v1beta1.FeatureRegistryService.GetFeatureGroup].

Request message for [FeatureOnlineStoreAdminService.GetFeatureOnlineStore][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.GetFeatureOnlineStore].

Request message for [FeaturestoreService.GetFeature][google.cloud.aiplatform.v1beta1.FeaturestoreService.GetFeature]. Request message for [FeatureRegistryService.GetFeature][google.cloud.aiplatform.v1beta1.FeatureRegistryService.GetFeature].

Request message for [FeatureOnlineStoreAdminService.GetFeatureView][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.GetFeatureView].

Request message for [FeatureOnlineStoreAdminService.GetFeatureViewSync][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.GetFeatureViewSync].

Request message for [FeaturestoreService.GetFeaturestore][google.cloud.aiplatform.v1beta1.FeaturestoreService.GetFeaturestore].

Request message for [JobService.GetHyperparameterTuningJob][google.cloud.aiplatform.v1beta1.JobService.GetHyperparameterTuningJob].

Request message for [IndexEndpointService.GetIndexEndpoint][google.cloud.aiplatform.v1beta1.IndexEndpointService.GetIndexEndpoint]

Request message for [IndexService.GetIndex][google.cloud.aiplatform.v1beta1.IndexService.GetIndex]

Request message for [MetadataService.GetMetadataSchema][google.cloud.aiplatform.v1beta1.MetadataService.GetMetadataSchema].

Request message for [MetadataService.GetMetadataStore][google.cloud.aiplatform.v1beta1.MetadataService.GetMetadataStore].

Request message for [JobService.GetModelDeploymentMonitoringJob][google.cloud.aiplatform.v1beta1.JobService.GetModelDeploymentMonitoringJob].

Request message for [ModelService.GetModelEvaluation][google.cloud.aiplatform.v1beta1.ModelService.GetModelEvaluation].

Request message for [ModelService.GetModelEvaluationSlice][google.cloud.aiplatform.v1beta1.ModelService.GetModelEvaluationSlice].

Request message for [ModelMonitoringService.GetModelMonitor][google.cloud.aiplatform.v1beta1.ModelMonitoringService.GetModelMonitor].

Request message for [ModelMonitoringService.GetModelMonitoringJob][google.cloud.aiplatform.v1beta1.ModelMonitoringService.GetModelMonitoringJob].

Request message for [ModelService.GetModel][google.cloud.aiplatform.v1beta1.ModelService.GetModel].

Request message for [JobService.GetNasJob][google.cloud.aiplatform.v1beta1.JobService.GetNasJob].

Request message for [JobService.GetNasTrialDetail][google.cloud.aiplatform.v1beta1.JobService.GetNasTrialDetail].

Request message for [NotebookService.GetNotebookExecutionJob]

Request message for [NotebookService.GetNotebookRuntime][google.cloud.aiplatform.v1beta1.NotebookService.GetNotebookRuntime]

Request message for [NotebookService.GetNotebookRuntimeTemplate][google.cloud.aiplatform.v1beta1.NotebookService.GetNotebookRuntimeTemplate]

Request message for [PersistentResourceService.GetPersistentResource][google.cloud.aiplatform.v1beta1.PersistentResourceService.GetPersistentResource].

Request message for [PipelineService.GetPipelineJob][google.cloud.aiplatform.v1beta1.PipelineService.GetPipelineJob].

Request message for [ModelGardenService.GetPublisherModel][google.cloud.aiplatform.v1beta1.ModelGardenService.GetPublisherModel]

Request message for [VertexRagDataService.GetRagCorpus][google.cloud.aiplatform.v1beta1.VertexRagDataService.GetRagCorpus]

Request message for [VertexRagDataService.GetRagFile][google.cloud.aiplatform.v1beta1.VertexRagDataService.GetRagFile]

Request message for [ReasoningEngineService.GetReasoningEngine][google.cloud.aiplatform.v1beta1.ReasoningEngineService.GetReasoningEngine].

Request message for [ScheduleService.GetSchedule][google.cloud.aiplatform.v1beta1.ScheduleService.GetSchedule].

Request message for [SpecialistPoolService.GetSpecialistPool][google.cloud.aiplatform.v1beta1.SpecialistPoolService.GetSpecialistPool].

Request message for [VizierService.GetStudy][google.cloud.aiplatform.v1beta1.VizierService.GetStudy].

Request message for [TensorboardService.GetTensorboardExperiment][google.cloud.aiplatform.v1beta1.TensorboardService.GetTensorboardExperiment].

Request message for [TensorboardService.GetTensorboard][google.cloud.aiplatform.v1beta1.TensorboardService.GetTensorboard].

Request message for [TensorboardService.GetTensorboardRun][google.cloud.aiplatform.v1beta1.TensorboardService.GetTensorboardRun].

Request message for [TensorboardService.GetTensorboardTimeSeries][google.cloud.aiplatform.v1beta1.TensorboardService.GetTensorboardTimeSeries].

Request message for [PipelineService.GetTrainingPipeline][google.cloud.aiplatform.v1beta1.PipelineService.GetTrainingPipeline].

Request message for [VizierService.GetTrial][google.cloud.aiplatform.v1beta1.VizierService.GetTrial].

Request message for [GenAiTuningService.GetTuningJob][google.cloud.aiplatform.v1beta1.GenAiTuningService.GetTuningJob].

The Google Drive location for the input content.

Container for nested types declared in the GoogleDriveSource message type.

The type and ID of the Google Drive resource.

Container for nested types declared in the ResourceId message type.

Tool to retrieve public web data for grounding, powered by Google.

Input for groundedness metric.

Spec for groundedness instance.

Spec for groundedness result.

Spec for groundedness metric.

Grounding chunk.

Container for nested types declared in the GroundingChunk message type.

Chunk from context retrieved by the retrieval tools.

Chunk from the web.

Metadata returned to client when grounding is enabled.

Grounding support.

Represents a HyperparameterTuningJob. A HyperparameterTuningJob has a Study specification and multiple CustomJobs with identical CustomJob specification.

Resource name for the HyperparameterTuningJob resource.

Matcher for Features of an EntityType by Feature ID.

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.

Runtime operation information for [DatasetService.ImportData][google.cloud.aiplatform.v1beta1.DatasetService.ImportData].

Request message for [DatasetService.ImportData][google.cloud.aiplatform.v1beta1.DatasetService.ImportData].

Response message for [DatasetService.ImportData][google.cloud.aiplatform.v1beta1.DatasetService.ImportData].

Details of [ExtensionRegistryService.ImportExtension][google.cloud.aiplatform.v1beta1.ExtensionRegistryService.ImportExtension] operation.

Request message for [ExtensionRegistryService.ImportExtension][google.cloud.aiplatform.v1beta1.ExtensionRegistryService.ImportExtension].

Details of operations that perform import Feature values.

Request message for [FeaturestoreService.ImportFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreService.ImportFeatureValues].

Container for nested types declared in the ImportFeatureValuesRequest message type.

Defines the Feature value(s) to import.

Response message for [FeaturestoreService.ImportFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreService.ImportFeatureValues].

Request message for [ModelService.ImportModelEvaluation][google.cloud.aiplatform.v1beta1.ModelService.ImportModelEvaluation]

Config for importing RagFiles.

Runtime operation information for [VertexRagDataService.ImportRagFiles][google.cloud.aiplatform.v1beta1.VertexRagDataService.ImportRagFiles].

Request message for [VertexRagDataService.ImportRagFiles][google.cloud.aiplatform.v1beta1.VertexRagDataService.ImportRagFiles].

Response message for [VertexRagDataService.ImportRagFiles][google.cloud.aiplatform.v1beta1.VertexRagDataService.ImportRagFiles].

A representation of a collection of database items organized in a way that allows for approximate nearest neighbor (a.k.a ANN) algorithms search.

Container for nested types declared in the Index message type.

A datapoint of Index.

Container for nested types declared in the IndexDatapoint message type.

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.

This field allows restricts to be based on numeric comparisons rather than categorical tokens.

Container for nested types declared in the NumericRestriction message type.

Restriction of a datapoint which describe its attributes(tokens) from each of several attribute categories(namespaces).

Feature embedding vector for sparse index. An array of numbers whose values are located in the specified dimensions.

Indexes are deployed into it. An IndexEndpoint can have multiple DeployedIndexes.

Resource name for the IndexEndpoint resource.

A service for managing Vertex AI's IndexEndpoints.

Base class for server-side implementations of IndexEndpointService

Client for IndexEndpointService

IndexEndpointService client wrapper, for convenient use.

Builder class for IndexEndpointServiceClient to provide simple configuration of credentials, endpoint etc.

IndexEndpointService client wrapper implementation, for convenient use.

Settings for IndexEndpointServiceClient instances.

Resource name for the Index resource.

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.

A service for creating and managing Vertex AI's Index resources.

Base class for server-side implementations of IndexService

Client for IndexService

IndexService client wrapper, for convenient use.

Builder class for IndexServiceClient to provide simple configuration of credentials, endpoint etc.

IndexService client wrapper implementation, for convenient use.

Settings for IndexServiceClient instances.

Stats of the Index.

Specifies Vertex AI owned input data to be used for training, and possibly evaluating, the Model.

A list of int64 values.

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

The Jira source for the ImportRagFilesRequest.

Container for nested types declared in the JiraSource message type.

JiraQueries contains the Jira queries and corresponding authentication.

A service for creating and managing Vertex AI's jobs.

Base class for server-side implementations of JobService

Client for JobService

JobService client wrapper, for convenient use.

Builder class for JobServiceClient to provide simple configuration of credentials, endpoint etc.

JobService client wrapper implementation, for convenient use.

Settings for JobServiceClient instances.

Contains information about the Large Model.

A subgraph of the overall lineage graph. Event edges connect Artifact and Execution nodes.

Request message for [DatasetService.ListAnnotations][google.cloud.aiplatform.v1beta1.DatasetService.ListAnnotations].

Response message for [DatasetService.ListAnnotations][google.cloud.aiplatform.v1beta1.DatasetService.ListAnnotations].

Request message for [MetadataService.ListArtifacts][google.cloud.aiplatform.v1beta1.MetadataService.ListArtifacts].

Response message for [MetadataService.ListArtifacts][google.cloud.aiplatform.v1beta1.MetadataService.ListArtifacts].

Request message for [JobService.ListBatchPredictionJobs][google.cloud.aiplatform.v1beta1.JobService.ListBatchPredictionJobs].

Response message for [JobService.ListBatchPredictionJobs][google.cloud.aiplatform.v1beta1.JobService.ListBatchPredictionJobs]

Request to list CachedContents.

Response with a list of CachedContents.

Request message for [MetadataService.ListContexts][google.cloud.aiplatform.v1beta1.MetadataService.ListContexts]

Response message for [MetadataService.ListContexts][google.cloud.aiplatform.v1beta1.MetadataService.ListContexts].

Request message for [JobService.ListCustomJobs][google.cloud.aiplatform.v1beta1.JobService.ListCustomJobs].

Response message for [JobService.ListCustomJobs][google.cloud.aiplatform.v1beta1.JobService.ListCustomJobs]

Request message for [DatasetService.ListDataItems][google.cloud.aiplatform.v1beta1.DatasetService.ListDataItems].

Response message for [DatasetService.ListDataItems][google.cloud.aiplatform.v1beta1.DatasetService.ListDataItems].

Request message for [JobService.ListDataLabelingJobs][google.cloud.aiplatform.v1beta1.JobService.ListDataLabelingJobs].

Response message for [JobService.ListDataLabelingJobs][google.cloud.aiplatform.v1beta1.JobService.ListDataLabelingJobs].

Request message for [DatasetService.ListDatasetVersions][google.cloud.aiplatform.v1beta1.DatasetService.ListDatasetVersions].

Response message for [DatasetService.ListDatasetVersions][google.cloud.aiplatform.v1beta1.DatasetService.ListDatasetVersions].

Request message for [DatasetService.ListDatasets][google.cloud.aiplatform.v1beta1.DatasetService.ListDatasets].

Response message for [DatasetService.ListDatasets][google.cloud.aiplatform.v1beta1.DatasetService.ListDatasets].

Request message for ListDeploymentResourcePools method.

Response message for ListDeploymentResourcePools method.

Request message for [EndpointService.ListEndpoints][google.cloud.aiplatform.v1beta1.EndpointService.ListEndpoints].

Response message for [EndpointService.ListEndpoints][google.cloud.aiplatform.v1beta1.EndpointService.ListEndpoints].

Request message for [FeaturestoreService.ListEntityTypes][google.cloud.aiplatform.v1beta1.FeaturestoreService.ListEntityTypes].

Response message for [FeaturestoreService.ListEntityTypes][google.cloud.aiplatform.v1beta1.FeaturestoreService.ListEntityTypes].

Request message for [MetadataService.ListExecutions][google.cloud.aiplatform.v1beta1.MetadataService.ListExecutions].

Response message for [MetadataService.ListExecutions][google.cloud.aiplatform.v1beta1.MetadataService.ListExecutions].

Request message for [ExtensionRegistryService.ListExtensions][google.cloud.aiplatform.v1beta1.ExtensionRegistryService.ListExtensions].

Response message for [ExtensionRegistryService.ListExtensions][google.cloud.aiplatform.v1beta1.ExtensionRegistryService.ListExtensions]

Request message for [FeatureRegistryService.ListFeatureGroups][google.cloud.aiplatform.v1beta1.FeatureRegistryService.ListFeatureGroups].

Response message for [FeatureRegistryService.ListFeatureGroups][google.cloud.aiplatform.v1beta1.FeatureRegistryService.ListFeatureGroups].

Request message for [FeatureOnlineStoreAdminService.ListFeatureOnlineStores][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.ListFeatureOnlineStores].

Response message for [FeatureOnlineStoreAdminService.ListFeatureOnlineStores][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.ListFeatureOnlineStores].

Request message for [FeatureOnlineStoreAdminService.ListFeatureViewSyncs][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.ListFeatureViewSyncs].

Response message for [FeatureOnlineStoreAdminService.ListFeatureViewSyncs][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.ListFeatureViewSyncs].

Request message for [FeatureOnlineStoreAdminService.ListFeatureViews][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.ListFeatureViews].

Response message for [FeatureOnlineStoreAdminService.ListFeatureViews][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.ListFeatureViews].

Request message for [FeaturestoreService.ListFeatures][google.cloud.aiplatform.v1beta1.FeaturestoreService.ListFeatures]. Request message for [FeatureRegistryService.ListFeatures][google.cloud.aiplatform.v1beta1.FeatureRegistryService.ListFeatures].

Response message for [FeaturestoreService.ListFeatures][google.cloud.aiplatform.v1beta1.FeaturestoreService.ListFeatures]. Response message for [FeatureRegistryService.ListFeatures][google.cloud.aiplatform.v1beta1.FeatureRegistryService.ListFeatures].

Request message for [FeaturestoreService.ListFeaturestores][google.cloud.aiplatform.v1beta1.FeaturestoreService.ListFeaturestores].

Response message for [FeaturestoreService.ListFeaturestores][google.cloud.aiplatform.v1beta1.FeaturestoreService.ListFeaturestores].

Request message for [JobService.ListHyperparameterTuningJobs][google.cloud.aiplatform.v1beta1.JobService.ListHyperparameterTuningJobs].

Response message for [JobService.ListHyperparameterTuningJobs][google.cloud.aiplatform.v1beta1.JobService.ListHyperparameterTuningJobs]

Request message for [IndexEndpointService.ListIndexEndpoints][google.cloud.aiplatform.v1beta1.IndexEndpointService.ListIndexEndpoints].

Response message for [IndexEndpointService.ListIndexEndpoints][google.cloud.aiplatform.v1beta1.IndexEndpointService.ListIndexEndpoints].

Request message for [IndexService.ListIndexes][google.cloud.aiplatform.v1beta1.IndexService.ListIndexes].

Response message for [IndexService.ListIndexes][google.cloud.aiplatform.v1beta1.IndexService.ListIndexes].

Request message for [MetadataService.ListMetadataSchemas][google.cloud.aiplatform.v1beta1.MetadataService.ListMetadataSchemas].

Response message for [MetadataService.ListMetadataSchemas][google.cloud.aiplatform.v1beta1.MetadataService.ListMetadataSchemas].

Request message for [MetadataService.ListMetadataStores][google.cloud.aiplatform.v1beta1.MetadataService.ListMetadataStores].

Response message for [MetadataService.ListMetadataStores][google.cloud.aiplatform.v1beta1.MetadataService.ListMetadataStores].

Request message for [JobService.ListModelDeploymentMonitoringJobs][google.cloud.aiplatform.v1beta1.JobService.ListModelDeploymentMonitoringJobs].

Response message for [JobService.ListModelDeploymentMonitoringJobs][google.cloud.aiplatform.v1beta1.JobService.ListModelDeploymentMonitoringJobs].

Request message for [ModelService.ListModelEvaluationSlices][google.cloud.aiplatform.v1beta1.ModelService.ListModelEvaluationSlices].

Response message for [ModelService.ListModelEvaluationSlices][google.cloud.aiplatform.v1beta1.ModelService.ListModelEvaluationSlices].

Request message for [ModelService.ListModelEvaluations][google.cloud.aiplatform.v1beta1.ModelService.ListModelEvaluations].

Response message for [ModelService.ListModelEvaluations][google.cloud.aiplatform.v1beta1.ModelService.ListModelEvaluations].

Request message for [ModelMonitoringService.ListModelMonitoringJobs][google.cloud.aiplatform.v1beta1.ModelMonitoringService.ListModelMonitoringJobs].

Response message for [ModelMonitoringService.ListModelMonitoringJobs][google.cloud.aiplatform.v1beta1.ModelMonitoringService.ListModelMonitoringJobs].

Request message for [ModelMonitoringService.ListModelMonitors][google.cloud.aiplatform.v1beta1.ModelMonitoringService.ListModelMonitors].

Response message for [ModelMonitoringService.ListModelMonitors][google.cloud.aiplatform.v1beta1.ModelMonitoringService.ListModelMonitors]

Request message for [ModelService.ListModelVersions][google.cloud.aiplatform.v1beta1.ModelService.ListModelVersions].

Response message for [ModelService.ListModelVersions][google.cloud.aiplatform.v1beta1.ModelService.ListModelVersions]

Request message for [ModelService.ListModels][google.cloud.aiplatform.v1beta1.ModelService.ListModels].

Response message for [ModelService.ListModels][google.cloud.aiplatform.v1beta1.ModelService.ListModels]

Request message for [JobService.ListNasJobs][google.cloud.aiplatform.v1beta1.JobService.ListNasJobs].

Response message for [JobService.ListNasJobs][google.cloud.aiplatform.v1beta1.JobService.ListNasJobs]

Request message for [JobService.ListNasTrialDetails][google.cloud.aiplatform.v1beta1.JobService.ListNasTrialDetails].

Response message for [JobService.ListNasTrialDetails][google.cloud.aiplatform.v1beta1.JobService.ListNasTrialDetails]

Request message for [NotebookService.ListNotebookExecutionJobs]

Response message for [NotebookService.CreateNotebookExecutionJob]

Request message for [NotebookService.ListNotebookRuntimeTemplates][google.cloud.aiplatform.v1beta1.NotebookService.ListNotebookRuntimeTemplates].

Response message for [NotebookService.ListNotebookRuntimeTemplates][google.cloud.aiplatform.v1beta1.NotebookService.ListNotebookRuntimeTemplates].

Request message for [NotebookService.ListNotebookRuntimes][google.cloud.aiplatform.v1beta1.NotebookService.ListNotebookRuntimes].

Response message for [NotebookService.ListNotebookRuntimes][google.cloud.aiplatform.v1beta1.NotebookService.ListNotebookRuntimes].

Request message for [VizierService.ListOptimalTrials][google.cloud.aiplatform.v1beta1.VizierService.ListOptimalTrials].

Response message for [VizierService.ListOptimalTrials][google.cloud.aiplatform.v1beta1.VizierService.ListOptimalTrials].

Request message for [PersistentResourceService.ListPersistentResource][].

Response message for [PersistentResourceService.ListPersistentResources][google.cloud.aiplatform.v1beta1.PersistentResourceService.ListPersistentResources]

Request message for [PipelineService.ListPipelineJobs][google.cloud.aiplatform.v1beta1.PipelineService.ListPipelineJobs].

Response message for [PipelineService.ListPipelineJobs][google.cloud.aiplatform.v1beta1.PipelineService.ListPipelineJobs]

Request message for [ModelGardenService.ListPublisherModels][google.cloud.aiplatform.v1beta1.ModelGardenService.ListPublisherModels].

Response message for [ModelGardenService.ListPublisherModels][google.cloud.aiplatform.v1beta1.ModelGardenService.ListPublisherModels].

Request message for [VertexRagDataService.ListRagCorpora][google.cloud.aiplatform.v1beta1.VertexRagDataService.ListRagCorpora].

Response message for [VertexRagDataService.ListRagCorpora][google.cloud.aiplatform.v1beta1.VertexRagDataService.ListRagCorpora].

Request message for [VertexRagDataService.ListRagFiles][google.cloud.aiplatform.v1beta1.VertexRagDataService.ListRagFiles].

Response message for [VertexRagDataService.ListRagFiles][google.cloud.aiplatform.v1beta1.VertexRagDataService.ListRagFiles].

Request message for [ReasoningEngineService.ListReasoningEngines][google.cloud.aiplatform.v1beta1.ReasoningEngineService.ListReasoningEngines].

Response message for [ReasoningEngineService.ListReasoningEngines][google.cloud.aiplatform.v1beta1.ReasoningEngineService.ListReasoningEngines]

Request message for [DatasetService.ListSavedQueries][google.cloud.aiplatform.v1beta1.DatasetService.ListSavedQueries].

Response message for [DatasetService.ListSavedQueries][google.cloud.aiplatform.v1beta1.DatasetService.ListSavedQueries].

Request message for [ScheduleService.ListSchedules][google.cloud.aiplatform.v1beta1.ScheduleService.ListSchedules].

Response message for [ScheduleService.ListSchedules][google.cloud.aiplatform.v1beta1.ScheduleService.ListSchedules]

Request message for [SpecialistPoolService.ListSpecialistPools][google.cloud.aiplatform.v1beta1.SpecialistPoolService.ListSpecialistPools].

Response message for [SpecialistPoolService.ListSpecialistPools][google.cloud.aiplatform.v1beta1.SpecialistPoolService.ListSpecialistPools].

Request message for [VizierService.ListStudies][google.cloud.aiplatform.v1beta1.VizierService.ListStudies].

Response message for [VizierService.ListStudies][google.cloud.aiplatform.v1beta1.VizierService.ListStudies].

Request message for [TensorboardService.ListTensorboardExperiments][google.cloud.aiplatform.v1beta1.TensorboardService.ListTensorboardExperiments].

Response message for [TensorboardService.ListTensorboardExperiments][google.cloud.aiplatform.v1beta1.TensorboardService.ListTensorboardExperiments].

Request message for [TensorboardService.ListTensorboardRuns][google.cloud.aiplatform.v1beta1.TensorboardService.ListTensorboardRuns].

Response message for [TensorboardService.ListTensorboardRuns][google.cloud.aiplatform.v1beta1.TensorboardService.ListTensorboardRuns].

Request message for [TensorboardService.ListTensorboardTimeSeries][google.cloud.aiplatform.v1beta1.TensorboardService.ListTensorboardTimeSeries].

Response message for [TensorboardService.ListTensorboardTimeSeries][google.cloud.aiplatform.v1beta1.TensorboardService.ListTensorboardTimeSeries].

Request message for [TensorboardService.ListTensorboards][google.cloud.aiplatform.v1beta1.TensorboardService.ListTensorboards].

Response message for [TensorboardService.ListTensorboards][google.cloud.aiplatform.v1beta1.TensorboardService.ListTensorboards].

Request message for [PipelineService.ListTrainingPipelines][google.cloud.aiplatform.v1beta1.PipelineService.ListTrainingPipelines].

Response message for [PipelineService.ListTrainingPipelines][google.cloud.aiplatform.v1beta1.PipelineService.ListTrainingPipelines]

Request message for [VizierService.ListTrials][google.cloud.aiplatform.v1beta1.VizierService.ListTrials].

Response message for [VizierService.ListTrials][google.cloud.aiplatform.v1beta1.VizierService.ListTrials].

Request message for [GenAiTuningService.ListTuningJobs][google.cloud.aiplatform.v1beta1.GenAiTuningService.ListTuningJobs].

Response message for [GenAiTuningService.ListTuningJobs][google.cloud.aiplatform.v1beta1.GenAiTuningService.ListTuningJobs]

Service for LLM related utility functions.

Base class for server-side implementations of LlmUtilityService

Client for LlmUtilityService

LlmUtilityService client wrapper, for convenient use.

Builder class for LlmUtilityServiceClient to provide simple configuration of credentials, endpoint etc.

LlmUtilityService client wrapper implementation, for convenient use.

Settings for LlmUtilityServiceClient instances.

Logprobs Result

Container for nested types declared in the LogprobsResult message type.

Candidate for the logprobs token and score.

Candidates with top log probabilities at each decoding step.

Request message for [VizierService.LookupStudy][google.cloud.aiplatform.v1beta1.VizierService.LookupStudy].

Specification of a single machine.

Manual batch tuning parameters.

MatchService is a Google managed service for efficient vector similarity search at scale.

Base class for server-side implementations of MatchService

Client for MatchService

MatchService client wrapper, for convenient use.

Builder class for MatchServiceClient to provide simple configuration of credentials, endpoint etc.

MatchService client wrapper implementation, for convenient use.

Settings for MatchServiceClient instances.

A message representing a Measurement of a Trial. A Measurement contains the Metrics got by executing a Trial using suggested hyperparameter values.

Container for nested types declared in the Measurement message type.

A message representing a metric in the measurement.

Request message for [ModelService.MergeVersionAliases][google.cloud.aiplatform.v1beta1.ModelService.MergeVersionAliases].

Instance of a general MetadataSchema.

Container for nested types declared in the MetadataSchema message type.

Resource name for the MetadataSchema resource.

Service for reading and writing metadata entries.

Base class for server-side implementations of MetadataService

Client for MetadataService

MetadataService client wrapper, for convenient use.

Builder class for MetadataServiceClient to provide simple configuration of credentials, endpoint etc.

MetadataService client wrapper implementation, for convenient use.

Settings for MetadataServiceClient instances.

Instance of a metadata store. Contains a set of metadata that can be queried.

Container for nested types declared in the MetadataStore message type.

Represents Dataplex integration settings.

Represents state information for a MetadataStore.

Resource name for the MetadataStore resource.

Represents one resource that exists in automl.googleapis.com, datalabeling.googleapis.com or ml.googleapis.com.

Container for nested types declared in the MigratableResource message type.

Represents one Dataset in automl.googleapis.com.

Represents one Model in automl.googleapis.com.

Represents one Dataset in datalabeling.googleapis.com.

Container for nested types declared in the DataLabelingDataset message type.

Represents one AnnotatedDataset in datalabeling.googleapis.com.

Represents one model Version in ml.googleapis.com.

Config of migrating one resource from automl.googleapis.com, datalabeling.googleapis.com and ml.googleapis.com to Vertex AI.

Container for nested types declared in the MigrateResourceRequest message type.

Config for migrating Dataset in automl.googleapis.com to Vertex AI's Dataset.

Config for migrating Model in automl.googleapis.com to Vertex AI's Model.

Config for migrating Dataset in datalabeling.googleapis.com to Vertex AI's Dataset.

Container for nested types declared in the MigrateDataLabelingDatasetConfig message type.

Config for migrating AnnotatedDataset in datalabeling.googleapis.com to Vertex AI's SavedQuery.

Config for migrating version in ml.googleapis.com to Vertex AI's Model.

Describes a successfully migrated resource.

A service that migrates resources from automl.googleapis.com, datalabeling.googleapis.com and ml.googleapis.com to Vertex AI.

Base class for server-side implementations of MigrationService

Client for MigrationService

MigrationService client wrapper, for convenient use.

Builder class for MigrationServiceClient to provide simple configuration of credentials, endpoint etc.

MigrationService client wrapper implementation, for convenient use.

Settings for MigrationServiceClient instances.

A trained machine learning Model.

Container for nested types declared in the Model message type.

User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models.

Represents export format supported by the Model. All formats export to Google Cloud Storage.

Container for nested types declared in the ExportFormat message type.

Contains information about the original Model if this Model is a copy.

Specification of a container for serving predictions. Some fields in this message correspond to fields in the Kubernetes Container v1 core specification.

ModelDeploymentMonitoringBigQueryTable specifies the BigQuery table name as well as some information of the logs stored in this table.

Container for nested types declared in the ModelDeploymentMonitoringBigQueryTable message type.

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.

Container for nested types declared in the ModelDeploymentMonitoringJob message type.

All metadata of most recent monitoring pipelines.

Resource name for the ModelDeploymentMonitoringJob resource.

ModelDeploymentMonitoringObjectiveConfig contains the pair of deployed_model_id to ModelMonitoringObjectiveConfig.

The config for scheduling monitoring job.

A collection of metrics calculated by comparing Model's predictions on all of the test data against annotations from the test data.

Container for nested types declared in the ModelEvaluation message type.

Configuration for bias detection.

Resource name for the ModelEvaluation resource.

A collection of metrics calculated by comparing Model's predictions on a slice of the test data against ground truth annotations.

Container for nested types declared in the ModelEvaluationSlice message type.

Definition of a slice.

Container for nested types declared in the Slice message type.

Specification for how the data should be sliced.

Container for nested types declared in the SliceSpec message type.

A range of values for slice(s). low is inclusive, high is exclusive.

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.

Single value that supports strings and floats.

Resource name for the ModelEvaluationSlice resource.

Aggregated explanation metrics for a Model over a set of instances.

The interface of Model Garden Service.

Base class for server-side implementations of ModelGardenService

Client for ModelGardenService

ModelGardenService client wrapper, for convenient use.

Builder class for ModelGardenServiceClient to provide simple configuration of credentials, endpoint etc.

ModelGardenService client wrapper implementation, for convenient use.

Settings for ModelGardenServiceClient instances.

Contains information about the source of the models generated from Model Garden.

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.

Container for nested types declared in the ModelMonitor message type.

The monitoring target refers to the entity that is subject to analysis. e.g. Vertex AI Model version.

Container for nested types declared in the ModelMonitoringTarget message type.

Model in Vertex AI Model Registry.

Resource name for the ModelMonitor resource.

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.

Monitoring alert triggered condition.

The alert config for model monitoring.

Container for nested types declared in the ModelMonitoringAlertConfig message type.

The config for email alert.

Represents a single model monitoring anomaly.

Container for nested types declared in the ModelMonitoringAnomaly message type.

Tabular anomaly details.

The model monitoring configuration used for Batch Prediction Job.

Model monitoring data input spec.

Container for nested types declared in the ModelMonitoringInput message type.

Data from Vertex AI Batch prediction job output.

Input dataset spec.

Container for nested types declared in the ModelMonitoringDataset message type.

Dataset spec for data sotred in BigQuery.

Dataset spec for data stored in Google Cloud Storage.

Container for nested types declared in the ModelMonitoringGcsSource message type.

Time offset setting.

Data from Vertex AI Endpoint request response logging.

Represents a model monitoring job that analyze dataset using different monitoring algorithm.

Represent the execution details of the job.

Container for nested types declared in the ModelMonitoringJobExecutionDetail message type.

Processed dataset information.

Resource name for the ModelMonitoringJob resource.

Notification spec(email, notification channel) for model monitoring statistics/alerts.

Container for nested types declared in the ModelMonitoringNotificationSpec message type.

The config for email alerts.

Google Cloud Notification Channel config.

The objective configuration for model monitoring, including the information needed to detect anomalies for one particular model.

Container for nested types declared in the ModelMonitoringObjectiveConfig message type.

The config for integrating with Vertex Explainable AI. Only applicable if the Model has explanation_spec populated.

Container for nested types declared in the ExplanationConfig message type.

Output from [BatchPredictionJob][google.cloud.aiplatform.v1beta1.BatchPredictionJob] for Model Monitoring baseline dataset, which can be used to generate baseline attribution scores.

Container for nested types declared in the ExplanationBaseline message type.

The config for Prediction data drift detection.

Training Dataset information.

The config for Training & Prediction data skew detection. It specifies the training dataset sources and the skew detection parameters.

Monitoring objectives spec.

Container for nested types declared in the ModelMonitoringObjectiveSpec message type.

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.

Feature attribution monitoring spec.

Tabular monitoring objective.

Specification for the export destination of monitoring results, including metrics, logs, etc.

The Model Monitoring Schema definition.

Container for nested types declared in the ModelMonitoringSchema message type.

Schema field definition.

A service for creating and managing Vertex AI Model moitoring. This includes ModelMonitor resources, ModelMonitoringJob resources.

Base class for server-side implementations of ModelMonitoringService

Client for ModelMonitoringService

ModelMonitoringService client wrapper, for convenient use.

Builder class for ModelMonitoringServiceClient to provide simple configuration of credentials, endpoint etc.

ModelMonitoringService client wrapper implementation, for convenient use.

Settings for ModelMonitoringServiceClient instances.

Monitoring monitoring job spec. It outlines the specifications for monitoring objectives, notifications, and result exports.

Represents the collection of statistics for a metric.

Statistics and anomalies generated by Model Monitoring.

Container for nested types declared in the ModelMonitoringStatsAnomalies message type.

Historical Stats (and Anomalies) for a specific Feature.

Represents a single statistics data point.

Container for nested types declared in the ModelMonitoringStatsDataPoint message type.

Typed value of the statistics.

Container for nested types declared in the TypedValue message type.

Summary statistics for a population of values.

A collection of data points that describes the time-varying values of a tabular metric.

Resource name for the Model resource.

A service for managing Vertex AI's machine learning Models.

Base class for server-side implementations of ModelService

Client for ModelService

ModelService client wrapper, for convenient use.

Builder class for ModelServiceClient to provide simple configuration of credentials, endpoint etc.

ModelService client wrapper implementation, for convenient use.

Settings for ModelServiceClient instances.

Detail description of the source information of the model.

Container for nested types declared in the ModelSourceInfo message type.

Runtime operation information for [IndexEndpointService.MutateDeployedIndex][google.cloud.aiplatform.v1beta1.IndexEndpointService.MutateDeployedIndex].

Request message for [IndexEndpointService.MutateDeployedIndex][google.cloud.aiplatform.v1beta1.IndexEndpointService.MutateDeployedIndex].

Response message for [IndexEndpointService.MutateDeployedIndex][google.cloud.aiplatform.v1beta1.IndexEndpointService.MutateDeployedIndex].

Runtime operation information for [EndpointService.MutateDeployedModel][google.cloud.aiplatform.v1beta1.EndpointService.MutateDeployedModel].

Request message for [EndpointService.MutateDeployedModel][google.cloud.aiplatform.v1beta1.EndpointService.MutateDeployedModel].

Response message for [EndpointService.MutateDeployedModel][google.cloud.aiplatform.v1beta1.EndpointService.MutateDeployedModel].

Represents a Neural Architecture Search (NAS) job.

Resource name for the NasJob resource.

Represents a uCAIP NasJob output.

Container for nested types declared in the NasJobOutput message type.

The output of a multi-trial Neural Architecture Search (NAS) jobs.

Represents the spec of a NasJob.

Container for nested types declared in the NasJobSpec message type.

The spec of multi-trial Neural Architecture Search (NAS).

Container for nested types declared in the MultiTrialAlgorithmSpec message type.

Represents a metric to optimize.

Container for nested types declared in the MetricSpec message type.

Represent spec for search trials.

Represent spec for train trials.

Represents a uCAIP NasJob trial.

Container for nested types declared in the NasTrial message type.

Represents a NasTrial details along with its parameters. If there is a corresponding train NasTrial, the train NasTrial is also returned.

Resource name for the NasTrialDetail resource.

A query to find a number of similar entities.

Container for nested types declared in the NearestNeighborQuery message type.

The embedding vector.

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

Container for nested types declared in the NumericFilter message type.

Parameters that can be overrided in each query to tune query latency and recall.

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.

Runtime operation metadata with regard to Matching Engine Index.

Container for nested types declared in the NearestNeighborSearchOperationMetadata message type.

Container for nested types declared in the RecordError message type.

Nearest neighbors for one query.

Container for nested types declared in the NearestNeighbors message type.

A neighbor of the query vector.

Neighbors for example-based explanations.

Resource name for the NetworkAttachment resource.

Resource name for the Network resource.

Network spec.

Represents a mount configuration for Network File System (NFS) to mount.

The euc configuration of NotebookRuntimeTemplate.

NotebookExecutionJob represents an instance of a notebook execution.

Container for nested types declared in the NotebookExecutionJob message type.

The Dataform Repository containing the input notebook.

The content of the input notebook in ipynb format.

The Cloud Storage uri for the input notebook.

Resource name for the NotebookExecutionJob resource.

The idle shutdown configuration of NotebookRuntimeTemplate, which contains the idle_timeout as required field.

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.

Container for nested types declared in the NotebookRuntime message type.

Resource name for the NotebookRuntime resource.

A template that specifies runtime configurations such as machine type, runtime version, network configurations, etc. Multiple runtimes can be created from a runtime template.

Resource name for the NotebookRuntimeTemplate resource.

Points to a NotebookRuntimeTemplateRef.

The interface for Vertex Notebook service (a.k.a. Colab on Workbench).

Base class for server-side implementations of NotebookService

Client for NotebookService

NotebookService client wrapper, for convenient use.

Builder class for NotebookServiceClient to provide simple configuration of credentials, endpoint etc.

NotebookService client wrapper implementation, for convenient use.

Settings for NotebookServiceClient instances.

Resource name for the NotificationChannel resource.

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.

PSC config that is used to automatically create forwarding rule via ServiceConnectionMap.

Input for pairwise metric.

Pairwise metric instance. Usually one instance corresponds to one row in an evaluation dataset.

Spec for pairwise metric result.

Spec for pairwise metric.

Input for pairwise question answering quality metric.

Spec for pairwise question answering quality instance.

Spec for pairwise question answering quality result.

Spec for pairwise question answering quality score metric.

Input for pairwise summarization quality metric.

Spec for pairwise summarization quality instance.

Spec for pairwise summarization quality result.

Spec for pairwise summarization quality score metric.

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.

Tuning spec for Partner models.

Request message for [JobService.PauseModelDeploymentMonitoringJob][google.cloud.aiplatform.v1beta1.JobService.PauseModelDeploymentMonitoringJob].

Request message for [ScheduleService.PauseSchedule][google.cloud.aiplatform.v1beta1.ScheduleService.PauseSchedule].

Represents the spec of [persistent disk][https://cloud.google.com/compute/docs/disks/persistent-disks] options.

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.

Container for nested types declared in the PersistentResource message type.

Resource name for the PersistentResource resource.

A service for managing Vertex AI's machine learning PersistentResource.

Base class for server-side implementations of PersistentResourceService

Client for PersistentResourceService

PersistentResourceService client wrapper, for convenient use.

Builder class for PersistentResourceServiceClient to provide simple configuration of credentials, endpoint etc.

PersistentResourceService client wrapper implementation, for convenient use.

Settings for PersistentResourceServiceClient instances.

An instance of a machine learning PipelineJob.

Container for nested types declared in the PipelineJob message type.

The runtime config of a PipelineJob.

Container for nested types declared in the RuntimeConfig message type.

The default runtime for the PipelineJob.

The type of an input artifact.

Persistent resource based runtime detail. For more information, refer to https://cloud.google.com/vertex-ai/docs/training/persistent-resource-overview

Container for nested types declared in the PersistentResourceRuntimeDetail message type.

The runtime detail of PipelineJob.

Resource name for the PipelineJob resource.

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).

Base class for server-side implementations of PipelineService

Client for PipelineService

PipelineService client wrapper, for convenient use.

Builder class for PipelineServiceClient to provide simple configuration of credentials, endpoint etc.

PipelineService client wrapper implementation, for convenient use.

Settings for PipelineServiceClient instances.

The runtime detail of a task execution.

Container for nested types declared in the PipelineTaskDetail message type.

A list of artifact metadata.

A single record of the task status.

The runtime detail of a pipeline executor.

Container for nested types declared in the PipelineTaskExecutorDetail message type.

The detail of a container execution. It contains the job names of the lifecycle of a container execution.

The detailed info for a custom job executor.

User provided rerun config to submit a rerun pipelinejob. This includes

1. Which task to rerun
2. User override input parameters and artifacts.

Container for nested types declared in the PipelineTaskRerunConfig message type.

A list of artifact metadata.

Runtime inputs data of the task.

Pipeline template metadata if [PipelineJob.template_uri][google.cloud.aiplatform.v1beta1.PipelineJob.template_uri] is from supported template registry. Currently, the only supported registry is Artifact Registry.

Input for pointwise metric.

Pointwise metric instance. Usually one instance corresponds to one row in an evaluation dataset.

Spec for pointwise metric result.

Spec for pointwise metric.

Represents a network port in a container.

Assigns input data to training, validation, and test sets based on the value of a provided key.

Supported only for tabular Datasets.

Metadata for PredictLongRunning long running operations.

Response message for [PredictionService.PredictLongRunning]

Request message for [PredictionService.Predict][google.cloud.aiplatform.v1beta1.PredictionService.Predict].

Configuration for logging request-response to a BigQuery table.

Response message for [PredictionService.Predict][google.cloud.aiplatform.v1beta1.PredictionService.Predict].

Contains the schemata used in Model's predictions and explanations via [PredictionService.Predict][google.cloud.aiplatform.v1beta1.PredictionService.Predict], [PredictionService.Explain][google.cloud.aiplatform.v1beta1.PredictionService.Explain] and [BatchPredictionJob][google.cloud.aiplatform.v1beta1.BatchPredictionJob].

A service for online predictions and explanations.

Base class for server-side implementations of PredictionService

Client for PredictionService

PredictionService client wrapper, for convenient use.

Server streaming methods for ChatCompletions(ChatCompletionsRequest, CallSettings).

Server streaming methods for ServerStreamingPredict(StreamingPredictRequest, CallSettings).

Bidirectional streaming methods for StreamDirectPredict(CallSettings, BidirectionalStreamingSettings).

Bidirectional streaming methods for StreamDirectRawPredict(CallSettings, BidirectionalStreamingSettings).

Server streaming methods for StreamGenerateContent(GenerateContentRequest, CallSettings).

Server streaming methods for StreamRawPredict(StreamRawPredictRequest, CallSettings).

Bidirectional streaming methods for StreamingPredict(CallSettings, BidirectionalStreamingSettings).

Bidirectional streaming methods for StreamingRawPredict(CallSettings, BidirectionalStreamingSettings).

Builder class for PredictionServiceClient to provide simple configuration of credentials, endpoint etc.

PredictionService client wrapper implementation, for convenient use.

Settings for PredictionServiceClient instances.

Preset configuration for example-based explanations

Container for nested types declared in the Presets message type.

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.

Represents configuration for private service connect.

Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic.

Container for nested types declared in the Probe message type.

ExecAction specifies a command to execute.

PscAutomatedEndpoints defines the output of the forwarding rule automatically created by each PscAutomationConfig.

Configuration for PSC-I.

A Model Garden Publisher Model.

Container for nested types declared in the PublisherModel message type.

Actions could take on this Publisher Model.

Container for nested types declared in the CallToAction message type.

Model metadata that is needed for UploadModel or DeployModel/CreateEndpoint requests.

Container for nested types declared in the Deploy message type.

Metadata information about the deployment for managing deployment config.

Configurations for PublisherModel GKE deployment

Open fine tuning pipelines.

Open notebooks.

The regional resource name or the URI. Key is region, e.g., us-central1, europe-west2, global, etc..

Rest API docs.

A named piece of documentation.

The information about the parent of a model.

Reference to a resource.

Resource name for the PublisherModel resource.

Details of operations that perform [MetadataService.PurgeArtifacts][google.cloud.aiplatform.v1beta1.MetadataService.PurgeArtifacts].

Request message for [MetadataService.PurgeArtifacts][google.cloud.aiplatform.v1beta1.MetadataService.PurgeArtifacts].

Response message for [MetadataService.PurgeArtifacts][google.cloud.aiplatform.v1beta1.MetadataService.PurgeArtifacts].

Details of operations that perform [MetadataService.PurgeContexts][google.cloud.aiplatform.v1beta1.MetadataService.PurgeContexts].

Request message for [MetadataService.PurgeContexts][google.cloud.aiplatform.v1beta1.MetadataService.PurgeContexts].

Response message for [MetadataService.PurgeContexts][google.cloud.aiplatform.v1beta1.MetadataService.PurgeContexts].

Details of operations that perform [MetadataService.PurgeExecutions][google.cloud.aiplatform.v1beta1.MetadataService.PurgeExecutions].

Request message for [MetadataService.PurgeExecutions][google.cloud.aiplatform.v1beta1.MetadataService.PurgeExecutions].

Response message for [MetadataService.PurgeExecutions][google.cloud.aiplatform.v1beta1.MetadataService.PurgeExecutions].

The spec of a Python packaged code.

Request message for [MetadataService.QueryArtifactLineageSubgraph][google.cloud.aiplatform.v1beta1.MetadataService.QueryArtifactLineageSubgraph].

Request message for [MetadataService.QueryContextLineageSubgraph][google.cloud.aiplatform.v1beta1.MetadataService.QueryContextLineageSubgraph].

Request message for QueryDeployedModels method.

Response message for QueryDeployedModels method.

Request message for [MetadataService.QueryExecutionInputsAndOutputs][google.cloud.aiplatform.v1beta1.MetadataService.QueryExecutionInputsAndOutputs].

Request message for [ExtensionExecutionService.QueryExtension][google.cloud.aiplatform.v1beta1.ExtensionExecutionService.QueryExtension].

Response message for [ExtensionExecutionService.QueryExtension][google.cloud.aiplatform.v1beta1.ExtensionExecutionService.QueryExtension].

Request message for [ReasoningEngineExecutionService.Query][].

Response message for [ReasoningEngineExecutionService.Query][]

Input for question answering correctness metric.

Spec for question answering correctness instance.

Spec for question answering correctness result.

Spec for question answering correctness metric.

Input for question answering helpfulness metric.

Spec for question answering helpfulness instance.

Spec for question answering helpfulness result.

Spec for question answering helpfulness metric.

Input for question answering quality metric.

Spec for question answering quality instance.

Spec for question answering quality result.

Spec for question answering quality score metric.

Input for question answering relevance metric.

Spec for question answering relevance instance.

Spec for question answering relevance result.

Spec for question answering relevance metric.

Relevant contexts for one query.

Container for nested types declared in the RagContexts message type.

A context of the query.

A RagCorpus is a RagFile container and a project can have multiple RagCorpora.

Resource name for the RagCorpus resource.

Config for the embedding model to use for RAG.

Container for nested types declared in the RagEmbeddingModelConfig message type.

Config for hybrid search.

Configuration for sparse emebdding generation.

Container for nested types declared in the SparseEmbeddingConfig message type.

Message for BM25 parameters.

Config representing a model hosted on Vertex Prediction Endpoint.

A RagFile contains user data for chunking, embedding and indexing.

Container for nested types declared in the RagFile message type.

Specifies the size and overlap of chunks for RagFiles.

Resource name for the RagFile resource.

Specifies the parsing config for RagFiles.

A query to retrieve relevant contexts.

Container for nested types declared in the RagQuery message type.

Configurations for hybrid search results ranking.

Config for the Vector DB to use for RAG.

Container for nested types declared in the RagVectorDbConfig message type.

The config for the Pinecone.

The config for the default RAG-managed Vector DB.

The config for the Vertex Feature Store.

The config for the Vertex Vector Search.

The config for the Weaviate.

Request message for [PredictionService.RawPredict][google.cloud.aiplatform.v1beta1.PredictionService.RawPredict].

Configuration for the Ray OSS Logs.

Configuration for the Ray metrics.

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.

Request message for [FeaturestoreOnlineServingService.ReadFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreOnlineServingService.ReadFeatureValues].

Response message for [FeaturestoreOnlineServingService.ReadFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreOnlineServingService.ReadFeatureValues].

Container for nested types declared in the ReadFeatureValuesResponse message type.

Entity view with Feature values.

Container for nested types declared in the EntityView message type.

Container to hold value(s), successive in time, for one Feature from the request.

Metadata for requested Features.

Response header with metadata for the requested [ReadFeatureValuesRequest.entity_type][google.cloud.aiplatform.v1beta1.ReadFeatureValuesRequest.entity_type] and Features.

The request message for [MatchService.ReadIndexDatapoints][google.cloud.aiplatform.v1beta1.MatchService.ReadIndexDatapoints].

The response message for [MatchService.ReadIndexDatapoints][google.cloud.aiplatform.v1beta1.MatchService.ReadIndexDatapoints].

Request message for [TensorboardService.ReadTensorboardBlobData][google.cloud.aiplatform.v1beta1.TensorboardService.ReadTensorboardBlobData].

Response message for [TensorboardService.ReadTensorboardBlobData][google.cloud.aiplatform.v1beta1.TensorboardService.ReadTensorboardBlobData].

Request message for [TensorboardService.ReadTensorboardSize][google.cloud.aiplatform.v1beta1.TensorboardService.ReadTensorboardSize].

Response message for [TensorboardService.ReadTensorboardSize][google.cloud.aiplatform.v1beta1.TensorboardService.ReadTensorboardSize].

Request message for [TensorboardService.ReadTensorboardTimeSeriesData][google.cloud.aiplatform.v1beta1.TensorboardService.ReadTensorboardTimeSeriesData].

Response message for [TensorboardService.ReadTensorboardTimeSeriesData][google.cloud.aiplatform.v1beta1.TensorboardService.ReadTensorboardTimeSeriesData].

Request message for [TensorboardService.ReadTensorboardUsage][google.cloud.aiplatform.v1beta1.TensorboardService.ReadTensorboardUsage].

Response message for [TensorboardService.ReadTensorboardUsage][google.cloud.aiplatform.v1beta1.TensorboardService.ReadTensorboardUsage].

Container for nested types declared in the ReadTensorboardUsageResponse message type.

Per month usage data

Per user usage data.

ReasoningEngine provides a customizable runtime for models to determine which actions to take and in which order.

A service for executing queries on Reasoning Engine.

Base class for server-side implementations of ReasoningEngineExecutionService

Client for ReasoningEngineExecutionService

ReasoningEngineExecutionService client wrapper, for convenient use.

Builder class for ReasoningEngineExecutionServiceClient to provide simple configuration of credentials, endpoint etc.

ReasoningEngineExecutionService client wrapper implementation, for convenient use.

Settings for ReasoningEngineExecutionServiceClient instances.

Resource name for the ReasoningEngine resource.

A service for managing Vertex AI's Reasoning Engines.

Base class for server-side implementations of ReasoningEngineService

Client for ReasoningEngineService

ReasoningEngineService client wrapper, for convenient use.

Builder class for ReasoningEngineServiceClient to provide simple configuration of credentials, endpoint etc.

ReasoningEngineService client wrapper implementation, for convenient use.

Settings for ReasoningEngineServiceClient instances.

ReasoningEngine configurations

Container for nested types declared in the ReasoningEngineSpec message type.

User provided package spec like pickled object and package requirements.

Runtime operation information for [GenAiTuningService.RebaseTunedModel][google.cloud.aiplatform.v1beta1.GenAiTuningService.RebaseTunedModel].

Request message for [GenAiTuningService.RebaseTunedModel][google.cloud.aiplatform.v1beta1.GenAiTuningService.RebaseTunedModel].

Details of operations that perform reboot PersistentResource.

Request message for [PersistentResourceService.RebootPersistentResource][google.cloud.aiplatform.v1beta1.PersistentResourceService.RebootPersistentResource].

Request message for [MetadataService.DeleteContextChildrenRequest][].

Response message for [MetadataService.RemoveContextChildren][google.cloud.aiplatform.v1beta1.MetadataService.RemoveContextChildren].

Request message for [IndexService.RemoveDatapoints][google.cloud.aiplatform.v1beta1.IndexService.RemoveDatapoints]

Response message for [IndexService.RemoveDatapoints][google.cloud.aiplatform.v1beta1.IndexService.RemoveDatapoints]

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.

Container for nested types declared in the ReservationAffinity message type.

Resource name for the Reservation resource.

Represents the spec of a group of resources of the same type, for example machine type, disk, and accelerators, in a PersistentResource.

Container for nested types declared in the ResourcePool message type.

The min/max number of replicas allowed if enabling autoscaling

Persistent Cluster runtime information as output

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.

Statistics information about resource consumption.

Runtime operation information for [DatasetService.RestoreDatasetVersion][google.cloud.aiplatform.v1beta1.DatasetService.RestoreDatasetVersion].

Request message for [DatasetService.RestoreDatasetVersion][google.cloud.aiplatform.v1beta1.DatasetService.RestoreDatasetVersion].

Request message for [JobService.ResumeModelDeploymentMonitoringJob][google.cloud.aiplatform.v1beta1.JobService.ResumeModelDeploymentMonitoringJob].

Request message for [ScheduleService.ResumeSchedule][google.cloud.aiplatform.v1beta1.ScheduleService.ResumeSchedule].

Defines a retrieval tool that model can call to access external knowledge.

Metadata related to retrieval in the grounding flow.

Request message for [VertexRagService.RetrieveContexts][google.cloud.aiplatform.v1beta1.VertexRagService.RetrieveContexts].

Container for nested types declared in the RetrieveContextsRequest message type.

The data source for Vertex RagStore.

Container for nested types declared in the VertexRagStore message type.

The definition of the Rag resource.

Response message for [VertexRagService.RetrieveContexts][google.cloud.aiplatform.v1beta1.VertexRagService.RetrieveContexts].

Input for rouge metric.

Spec for rouge instance.

Rouge metric value for an instance.

Results for rouge metric.

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.

The definition of a runtime artifact.

Runtime configuration to run the extension.

Container for nested types declared in the RuntimeConfig message type.

Input for safety metric.

Spec for safety instance.

Safety rating corresponding to the generated content.

Container for nested types declared in the SafetyRating message type.

Spec for safety result.

Safety settings.

Container for nested types declared in the SafetySetting message type.

Spec for safety metric.

Active learning data sampling config. For every active learning labeling iteration, it will select a batch of data based on the sampling strategy.

Container for nested types declared in the SampleConfig message type.

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.

Sampling Strategy for logging, can be for both training and prediction dataset.

Container for nested types declared in the SamplingStrategy message type.

Requests are randomly selected.

A SavedQuery is a view of the dataset. It references a subset of annotations by problem type and filters.

Resource name for the SavedQuery resource.

One point viewable on a scalar metric plot.

An instance of a Schedule periodically schedules runs to make API calls based on user specified time specification and API request type.

Container for nested types declared in the Schedule message type.

Status of a scheduled run.

Resource name for the Schedule resource.

A service for creating and managing Vertex AI's Schedule resources to periodically launch shceudled runs to make API calls.

Base class for server-side implementations of ScheduleService

Client for ScheduleService

ScheduleService client wrapper, for convenient use.

Builder class for ScheduleServiceClient to provide simple configuration of credentials, endpoint etc.

ScheduleService client wrapper implementation, for convenient use.

Settings for ScheduleServiceClient instances.

All parameters related to queuing and scheduling of custom jobs.

Container for nested types declared in the Scheduling message type.

Request message for [DatasetService.SearchDataItems][google.cloud.aiplatform.v1beta1.DatasetService.SearchDataItems].

Container for nested types declared in the SearchDataItemsRequest message type.

Expression that allows ranking results based on annotation's property.

Response message for [DatasetService.SearchDataItems][google.cloud.aiplatform.v1beta1.DatasetService.SearchDataItems].

Google search entry point.

Request message for [FeaturestoreService.SearchFeatures][google.cloud.aiplatform.v1beta1.FeaturestoreService.SearchFeatures].

Response message for [FeaturestoreService.SearchFeatures][google.cloud.aiplatform.v1beta1.FeaturestoreService.SearchFeatures].

Request message for [MigrationService.SearchMigratableResources][google.cloud.aiplatform.v1beta1.MigrationService.SearchMigratableResources].

Response message for [MigrationService.SearchMigratableResources][google.cloud.aiplatform.v1beta1.MigrationService.SearchMigratableResources].

Request message for [JobService.SearchModelDeploymentMonitoringStatsAnomalies][google.cloud.aiplatform.v1beta1.JobService.SearchModelDeploymentMonitoringStatsAnomalies].

Container for nested types declared in the SearchModelDeploymentMonitoringStatsAnomaliesRequest message type.

Stats requested for specific objective.

Response message for [JobService.SearchModelDeploymentMonitoringStatsAnomalies][google.cloud.aiplatform.v1beta1.JobService.SearchModelDeploymentMonitoringStatsAnomalies].

Request message for [ModelMonitoringService.SearchModelMonitoringAlerts][google.cloud.aiplatform.v1beta1.ModelMonitoringService.SearchModelMonitoringAlerts].

Response message for [ModelMonitoringService.SearchModelMonitoringAlerts][google.cloud.aiplatform.v1beta1.ModelMonitoringService.SearchModelMonitoringAlerts].

Filter for searching ModelMonitoringStats.

Container for nested types declared in the SearchModelMonitoringStatsFilter message type.

Tabular statistics filter.

Request message for [ModelMonitoringService.SearchModelMonitoringStats][google.cloud.aiplatform.v1beta1.ModelMonitoringService.SearchModelMonitoringStats].

Response message for [ModelMonitoringService.SearchModelMonitoringStats][google.cloud.aiplatform.v1beta1.ModelMonitoringService.SearchModelMonitoringStats].

The request message for [FeatureOnlineStoreService.SearchNearestEntities][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreService.SearchNearestEntities].

Response message for [FeatureOnlineStoreService.SearchNearestEntities][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreService.SearchNearestEntities]

Resource name for the SecretVersion resource.

Segment of the content.

Configuration for the use of custom service account to run the workloads.

Resource name for the Service resource.

The SharePointSources to pass to ImportRagFiles.

Container for nested types declared in the SharePointSources message type.

An individual SharePointSource.

A set of Shielded Instance options. See Images using supported Shielded VM features.

The Slack source for the ImportRagFilesRequest.

Container for nested types declared in the SlackSource message type.

SlackChannels contains the Slack channels and corresponding access token.

Container for nested types declared in the SlackChannels message type.

SlackChannel contains the Slack channel ID and the time range to import.

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

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.

Resource name for the SpecialistPool resource.

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.

Base class for server-side implementations of SpecialistPoolService

Client for SpecialistPoolService

SpecialistPoolService client wrapper, for convenient use.

Builder class for SpecialistPoolServiceClient to provide simple configuration of credentials, endpoint etc.

SpecialistPoolService client wrapper implementation, for convenient use.

Settings for SpecialistPoolServiceClient instances.

Metadata information for [NotebookService.StartNotebookRuntime][google.cloud.aiplatform.v1beta1.NotebookService.StartNotebookRuntime].

Request message for [NotebookService.StartNotebookRuntime][google.cloud.aiplatform.v1beta1.NotebookService.StartNotebookRuntime].

Response message for [NotebookService.StartNotebookRuntime][google.cloud.aiplatform.v1beta1.NotebookService.StartNotebookRuntime].

Request message for [VizierService.StopTrial][google.cloud.aiplatform.v1beta1.VizierService.StopTrial].

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.

Request message for [PredictionService.StreamDirectPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamDirectPredict].

The first message must contain [endpoint][google.cloud.aiplatform.v1beta1.StreamDirectPredictRequest.endpoint] field and optionally [input][]. The subsequent messages must contain [input][].

Response message for [PredictionService.StreamDirectPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamDirectPredict].

Request message for [PredictionService.StreamDirectRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamDirectRawPredict].

The first message must contain [endpoint][google.cloud.aiplatform.v1beta1.StreamDirectRawPredictRequest.endpoint] and [method_name][google.cloud.aiplatform.v1beta1.StreamDirectRawPredictRequest.method_name] fields and optionally [input][google.cloud.aiplatform.v1beta1.StreamDirectRawPredictRequest.input]. The subsequent messages must contain [input][google.cloud.aiplatform.v1beta1.StreamDirectRawPredictRequest.input]. [method_name][google.cloud.aiplatform.v1beta1.StreamDirectRawPredictRequest.method_name] in the subsequent messages have no effect.

Response message for [PredictionService.StreamDirectRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamDirectRawPredict].

Request message for [PredictionService.StreamRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamRawPredict].

Request message for [FeatureOnlineStoreService.StreamingFetchFeatureValues][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreService.StreamingFetchFeatureValues]. For the entities requested, all features under the requested feature view will be returned.

Response message for [FeatureOnlineStoreService.StreamingFetchFeatureValues][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreService.StreamingFetchFeatureValues].

Request message for [PredictionService.StreamingPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamingPredict].

The first message must contain [endpoint][google.cloud.aiplatform.v1beta1.StreamingPredictRequest.endpoint] field and optionally [input][]. The subsequent messages must contain [input][].

Response message for [PredictionService.StreamingPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamingPredict].

Request message for [PredictionService.StreamingRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamingRawPredict].

The first message must contain [endpoint][google.cloud.aiplatform.v1beta1.StreamingRawPredictRequest.endpoint] and [method_name][google.cloud.aiplatform.v1beta1.StreamingRawPredictRequest.method_name] fields and optionally [input][google.cloud.aiplatform.v1beta1.StreamingRawPredictRequest.input]. The subsequent messages must contain [input][google.cloud.aiplatform.v1beta1.StreamingRawPredictRequest.input]. [method_name][google.cloud.aiplatform.v1beta1.StreamingRawPredictRequest.method_name] in the subsequent messages have no effect.

Response message for [PredictionService.StreamingRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamingRawPredict].

Request message for [FeaturestoreOnlineServingService.StreamingFeatureValuesRead][].

A list of string values.

One field of a Struct (or object) type feature value.

Struct (or object) type feature value.

A message representing a Study.

Container for nested types declared in the Study message type.

Resource name for the Study resource.

Represents specification of a Study.

Container for nested types declared in the StudySpec message type.

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.

Configuration for ConvexStopPolicy.

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.

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.

Represents a metric to optimize.

Container for nested types declared in the MetricSpec message type.

Used in safe optimization to specify threshold levels and risk tolerance.

Represents a single parameter to optimize.

Container for nested types declared in the ParameterSpec message type.

Value specification for a parameter in CATEGORICAL type.

Represents a parameter spec with condition from its parent parameter.

Container for nested types declared in the ConditionalParameterSpec message type.

Represents the spec to match categorical values from parent parameter.

Represents the spec to match discrete values from parent parameter.

Represents the spec to match integer values from parent parameter.

Value specification for a parameter in DISCRETE type.

Value specification for a parameter in DOUBLE type.

Value specification for a parameter in INTEGER type.

The configuration (stopping conditions) for automated stopping of a Study. Conditions include trial budgets, time budgets, and convergence detection.

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.

Time-based Constraint for Study

Resource name for the Subnetwork resource.

Details of operations that perform Trials suggestion.

Request message for [VizierService.SuggestTrials][google.cloud.aiplatform.v1beta1.VizierService.SuggestTrials].

Response message for [VizierService.SuggestTrials][google.cloud.aiplatform.v1beta1.VizierService.SuggestTrials].

Input for summarization helpfulness metric.

Spec for summarization helpfulness instance.

Spec for summarization helpfulness result.

Spec for summarization helpfulness score metric.

Input for summarization quality metric.

Spec for summarization quality instance.

Spec for summarization quality result.

Spec for summarization quality score metric.

Input for summarization verbosity metric.

Spec for summarization verbosity instance.

Spec for summarization verbosity result.

Spec for summarization verbosity score metric.

Hyperparameters for SFT.

Container for nested types declared in the SupervisedHyperParameters message type.

Tuning data statistics for Supervised Tuning.

Dataset distribution for Supervised Tuning.

Container for nested types declared in the SupervisedTuningDatasetDistribution message type.

Dataset bucket used to create a histogram for the distribution given a population of values.

Tuning Spec for Supervised Tuning for first party models.

Request message for [FeatureOnlineStoreAdminService.SyncFeatureView][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.SyncFeatureView].

Response message for [FeatureOnlineStoreAdminService.SyncFeatureView][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.SyncFeatureView].

The storage details for TFRecord output content.

A tensor value type.

Container for nested types declared in the Tensor message type.

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.

One blob (e.g, image, graph) viewable on a blob metric plot.

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.

A TensorboardExperiment is a group of TensorboardRuns, that are typically the results of a training job run, in a Tensorboard.

Resource name for the TensorboardExperiment resource.

Resource name for the Tensorboard resource.

TensorboardRun maps to a specific execution of a training job with a given set of hyperparameter values, model definition, dataset, etc

Resource name for the TensorboardRun resource.

TensorboardService

Base class for server-side implementations of TensorboardService

Client for TensorboardService

TensorboardService client wrapper, for convenient use.

Server streaming methods for ReadTensorboardBlobData(ReadTensorboardBlobDataRequest, CallSettings).

Builder class for TensorboardServiceClient to provide simple configuration of credentials, endpoint etc.

TensorboardService client wrapper implementation, for convenient use.

Settings for TensorboardServiceClient instances.

One point viewable on a tensor metric plot.

TensorboardTimeSeries maps to times series produced in training runs

Container for nested types declared in the TensorboardTimeSeries message type.

Describes metadata for a TensorboardTimeSeries.

Resource name for the TensorboardTimeSeries resource.

The config for feature monitoring threshold.

All the data stored in a TensorboardTimeSeries.

A TensorboardTimeSeries data point.

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.

Tokens info with a list of tokens and the corresponding list of token ids.

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).

Input for tool call valid metric.

Spec for tool call valid instance.

Tool call valid metric value for an instance.

Results for tool call valid metric.

Spec for tool call valid metric.

Tool config. This config is shared for all tools provided in the request.

Input for tool name match metric.

Spec for tool name match instance.

Tool name match metric value for an instance.

Results for tool name match metric.

Spec for tool name match metric.

Input for tool parameter key value match metric.

Spec for tool parameter key value match instance.

Tool parameter key value match metric value for an instance.

Results for tool parameter key value match metric.

Spec for tool parameter key value match metric.

Input for tool parameter key match metric.

Spec for tool parameter key match instance.

Tool parameter key match metric value for an instance.

Results for tool parameter key match metric.

Spec for tool parameter key match metric.

A single example of the tool usage.

Container for nested types declared in the ToolUseExample message type.

Identifies one operation of the extension.

CMLE training config. For every active learning labeling iteration, system will train a machine learning model on CMLE. The trained model will be used by data sampling algorithm to select DataItems.

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][google.cloud.aiplatform.v1beta1.ModelService.UploadModel] the Model to Vertex AI, and evaluate the Model.

Resource name for the TrainingPipeline resource.

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.

Container for nested types declared in the Trial message type.

A message representing a parameter to be tuned.

Resource name for the Trial resource.

The Model Registry Model and Online Prediction Endpoint assiociated with this [TuningJob][google.cloud.aiplatform.v1.TuningJob].

TunedModel Reference for legacy model migration.

The tuning data statistic values for [TuningJob][google.cloud.aiplatform.v1.TuningJob].

Represents a TuningJob that runs with Google owned models.

Resource name for the TuningJob resource.

Runtime operation information for [IndexEndpointService.UndeployIndex][google.cloud.aiplatform.v1beta1.IndexEndpointService.UndeployIndex].

Request message for [IndexEndpointService.UndeployIndex][google.cloud.aiplatform.v1beta1.IndexEndpointService.UndeployIndex].

Response message for [IndexEndpointService.UndeployIndex][google.cloud.aiplatform.v1beta1.IndexEndpointService.UndeployIndex].

Runtime operation information for [EndpointService.UndeployModel][google.cloud.aiplatform.v1beta1.EndpointService.UndeployModel].

Request message for [EndpointService.UndeployModel][google.cloud.aiplatform.v1beta1.EndpointService.UndeployModel].

Response message for [EndpointService.UndeployModel][google.cloud.aiplatform.v1beta1.EndpointService.UndeployModel].

Contains model information necessary to perform batch prediction without requiring a full model import.

Request message for [MetadataService.UpdateArtifact][google.cloud.aiplatform.v1beta1.MetadataService.UpdateArtifact].

Request message for [GenAiCacheService.UpdateCachedContent][google.cloud.aiplatform.v1beta1.GenAiCacheService.UpdateCachedContent]. Only expire_time or ttl can be updated.

Request message for [MetadataService.UpdateContext][google.cloud.aiplatform.v1beta1.MetadataService.UpdateContext].

Request message for [DatasetService.UpdateDataset][google.cloud.aiplatform.v1beta1.DatasetService.UpdateDataset].

Request message for [DatasetService.UpdateDatasetVersion][google.cloud.aiplatform.v1beta1.DatasetService.UpdateDatasetVersion].

Runtime operation information for UpdateDeploymentResourcePool method.

Request message for UpdateDeploymentResourcePool method.

Request message for [EndpointService.UpdateEndpoint][google.cloud.aiplatform.v1beta1.EndpointService.UpdateEndpoint].

Request message for [FeaturestoreService.UpdateEntityType][google.cloud.aiplatform.v1beta1.FeaturestoreService.UpdateEntityType].

Request message for [MetadataService.UpdateExecution][google.cloud.aiplatform.v1beta1.MetadataService.UpdateExecution].

Runtime operation information for [ModelService.UpdateExplanationDataset][google.cloud.aiplatform.v1beta1.ModelService.UpdateExplanationDataset].

Request message for [ModelService.UpdateExplanationDataset][google.cloud.aiplatform.v1beta1.ModelService.UpdateExplanationDataset].

Response message of [ModelService.UpdateExplanationDataset][google.cloud.aiplatform.v1beta1.ModelService.UpdateExplanationDataset] operation.

Request message for [ExtensionRegistryService.UpdateExtension][google.cloud.aiplatform.v1beta1.ExtensionRegistryService.UpdateExtension].

Details of operations that perform update FeatureGroup.

Request message for [FeatureRegistryService.UpdateFeatureGroup][google.cloud.aiplatform.v1beta1.FeatureRegistryService.UpdateFeatureGroup].

Details of operations that perform update FeatureOnlineStore.

Request message for [FeatureOnlineStoreAdminService.UpdateFeatureOnlineStore][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.UpdateFeatureOnlineStore].

Details of operations that perform update Feature.

Request message for [FeaturestoreService.UpdateFeature][google.cloud.aiplatform.v1beta1.FeaturestoreService.UpdateFeature]. Request message for [FeatureRegistryService.UpdateFeature][google.cloud.aiplatform.v1beta1.FeatureRegistryService.UpdateFeature].

Details of operations that perform update FeatureView.

Request message for [FeatureOnlineStoreAdminService.UpdateFeatureView][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreAdminService.UpdateFeatureView].

Details of operations that perform update Featurestore.

Request message for [FeaturestoreService.UpdateFeaturestore][google.cloud.aiplatform.v1beta1.FeaturestoreService.UpdateFeaturestore].

Request message for [IndexEndpointService.UpdateIndexEndpoint][google.cloud.aiplatform.v1beta1.IndexEndpointService.UpdateIndexEndpoint].

Runtime operation information for [IndexService.UpdateIndex][google.cloud.aiplatform.v1beta1.IndexService.UpdateIndex].

Request message for [IndexService.UpdateIndex][google.cloud.aiplatform.v1beta1.IndexService.UpdateIndex].

Runtime operation information for [JobService.UpdateModelDeploymentMonitoringJob][google.cloud.aiplatform.v1beta1.JobService.UpdateModelDeploymentMonitoringJob].

Request message for [JobService.UpdateModelDeploymentMonitoringJob][google.cloud.aiplatform.v1beta1.JobService.UpdateModelDeploymentMonitoringJob].

Runtime operation information for [ModelMonitoringService.UpdateModelMonitor][google.cloud.aiplatform.v1beta1.ModelMonitoringService.UpdateModelMonitor].

Request message for [ModelMonitoringService.UpdateModelMonitor][google.cloud.aiplatform.v1beta1.ModelMonitoringService.UpdateModelMonitor].

Request message for [ModelService.UpdateModel][google.cloud.aiplatform.v1beta1.ModelService.UpdateModel].

Request message for [NotebookService.UpdateNotebookRuntimeTemplate][google.cloud.aiplatform.v1beta1.NotebookService.UpdateNotebookRuntimeTemplate].

Details of operations that perform update PersistentResource.

Request message for UpdatePersistentResource method.

Runtime operation information for [VertexRagDataService.UpdateRagCorpus][google.cloud.aiplatform.v1beta1.VertexRagDataService.UpdateRagCorpus].

Request message for [VertexRagDataService.UpdateRagCorpus][google.cloud.aiplatform.v1beta1.VertexRagDataService.UpdateRagCorpus].

Details of [ReasoningEngineService.UpdateReasoningEngine][google.cloud.aiplatform.v1beta1.ReasoningEngineService.UpdateReasoningEngine] operation.

Request message for [ReasoningEngineService.UpdateReasoningEngine][google.cloud.aiplatform.v1beta1.ReasoningEngineService.UpdateReasoningEngine].

Request message for [ScheduleService.UpdateSchedule][google.cloud.aiplatform.v1beta1.ScheduleService.UpdateSchedule].

Runtime operation metadata for [SpecialistPoolService.UpdateSpecialistPool][google.cloud.aiplatform.v1beta1.SpecialistPoolService.UpdateSpecialistPool].

Request message for [SpecialistPoolService.UpdateSpecialistPool][google.cloud.aiplatform.v1beta1.SpecialistPoolService.UpdateSpecialistPool].

Request message for [TensorboardService.UpdateTensorboardExperiment][google.cloud.aiplatform.v1beta1.TensorboardService.UpdateTensorboardExperiment].

Details of operations that perform update Tensorboard.

Request message for [TensorboardService.UpdateTensorboard][google.cloud.aiplatform.v1beta1.TensorboardService.UpdateTensorboard].

Request message for [TensorboardService.UpdateTensorboardRun][google.cloud.aiplatform.v1beta1.TensorboardService.UpdateTensorboardRun].

Request message for [TensorboardService.UpdateTensorboardTimeSeries][google.cloud.aiplatform.v1beta1.TensorboardService.UpdateTensorboardTimeSeries].

Metadata information for [NotebookService.UpgradeNotebookRuntime][google.cloud.aiplatform.v1beta1.NotebookService.UpgradeNotebookRuntime].

Request message for [NotebookService.UpgradeNotebookRuntime][google.cloud.aiplatform.v1beta1.NotebookService.UpgradeNotebookRuntime].

Response message for [NotebookService.UpgradeNotebookRuntime][google.cloud.aiplatform.v1beta1.NotebookService.UpgradeNotebookRuntime].

Details of [ModelService.UploadModel][google.cloud.aiplatform.v1beta1.ModelService.UploadModel] operation.

Request message for [ModelService.UploadModel][google.cloud.aiplatform.v1beta1.ModelService.UploadModel].

Response message of [ModelService.UploadModel][google.cloud.aiplatform.v1beta1.ModelService.UploadModel] operation.

Config for uploading RagFile.

Request message for [VertexRagDataService.UploadRagFile][google.cloud.aiplatform.v1beta1.VertexRagDataService.UploadRagFile].

Response message for [VertexRagDataService.UploadRagFile][google.cloud.aiplatform.v1beta1.VertexRagDataService.UploadRagFile].

Request message for [IndexService.UpsertDatapoints][google.cloud.aiplatform.v1beta1.IndexService.UpsertDatapoints]

Response message for [IndexService.UpsertDatapoints][google.cloud.aiplatform.v1beta1.IndexService.UpsertDatapoints]

References an API call. It contains more information about long running operation and Jobs that are triggered by the API call.

Value is the value of the field.

Resource name for the Version resource.

Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/products/agent-builder

A service for managing user data for RAG.

Base class for server-side implementations of VertexRagDataService

Client for VertexRagDataService

VertexRagDataService client wrapper, for convenient use.

Builder class for VertexRagDataServiceClient to provide simple configuration of credentials, endpoint etc.

VertexRagDataService client wrapper implementation, for convenient use.

Settings for VertexRagDataServiceClient instances.

A service for retrieving relevant contexts.

Base class for server-side implementations of VertexRagService

Client for VertexRagService

VertexRagService client wrapper, for convenient use.

Builder class for VertexRagServiceClient to provide simple configuration of credentials, endpoint etc.

VertexRagService client wrapper implementation, for convenient use.

Settings for VertexRagServiceClient instances.

Retrieve from Vertex RAG Store for grounding.

Container for nested types declared in the VertexRagStore message type.

The definition of the Rag resource.

Metadata describes the input video content.

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.

Base class for server-side implementations of VizierService

Client for VizierService

VizierService client wrapper, for convenient use.

Builder class for VizierServiceClient to provide simple configuration of credentials, endpoint etc.

VizierService client wrapper implementation, for convenient use.

Settings for VizierServiceClient instances.

Represents the spec of a worker pool in a job.

Contains Feature values to be written for a specific entity.

Request message for [FeaturestoreOnlineServingService.WriteFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreOnlineServingService.WriteFeatureValues].

Response message for [FeaturestoreOnlineServingService.WriteFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreOnlineServingService.WriteFeatureValues].

Request message for [TensorboardService.WriteTensorboardExperimentData][google.cloud.aiplatform.v1beta1.TensorboardService.WriteTensorboardExperimentData].

Response message for [TensorboardService.WriteTensorboardExperimentData][google.cloud.aiplatform.v1beta1.TensorboardService.WriteTensorboardExperimentData].

Request message for [TensorboardService.WriteTensorboardRunData][google.cloud.aiplatform.v1beta1.TensorboardService.WriteTensorboardRunData].

Response message for [TensorboardService.WriteTensorboardRunData][google.cloud.aiplatform.v1beta1.TensorboardService.WriteTensorboardRunData].

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.

Represents a hardware accelerator type.

Enum of possible cases for the "human_labeling_budget" oneof.

The possible contents of AnnotatedDatasetName.

The possible contents of AnnotationName.

The possible contents of AnnotationSpecName.

Enum of possible cases for the "auth_config" oneof.

Describes the state of the Artifact.

The possible contents of ArtifactName.

Enum of possible cases for the "kind" oneof.

Enum of possible cases for the "auth_config" oneof.

Enum of possible cases for the "oauth_config" oneof.

Enum of possible cases for the "oidc_config" oneof.

Type of Auth.

The possible contents of AutoMLDatasetName.

The possible contents of AutoMLModelName.

Enum of possible cases for the "result" oneof.

Enum of possible cases for the "source" oneof.

Enum of possible cases for the "destination" oneof.

Enum of possible cases for the "output_location" oneof.

The possible contents of BatchPredictionJobName.

Enum of possible cases for the "read_option" oneof.

Enum of possible cases for the "expiration" oneof.

The possible contents of CachedContentName.

The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.

The possible contents of ContextName.

Enum of possible cases for the "destination_model" oneof.

RagCorpus life state.

The possible contents of CustomJobName.

The possible contents of DataItemName.

The possible contents of DataLabelingDatasetName.

The possible contents of DataLabelingJobName.

The possible contents of DatasetName.

The possible contents of DatasetVersionName.

Enum of possible cases for the "DeleteOption" oneof.

Enum of possible cases for the "response" oneof.

Enum of possible cases for the "prediction_resources" oneof.

The possible contents of DeploymentResourcePoolName.

Enum of possible cases for the "teacher_model" oneof.

The mode of the predictor to be used in dynamic retrieval.

The possible contents of EndpointName.

Enum of possible cases for the "EntityIdsSource" oneof.

The possible contents of EntityTypeName.

The query type used for finding the attributed items.

Enum of possible cases for the "metric_inputs" oneof.

Enum of possible cases for the "evaluation_results" oneof.

Describes the type of the EvaluatedAnnotation. The type is determined

Describes whether an Event's Artifact is the Execution's input or output.

Enum of possible cases for the "config" oneof.

Enum of possible cases for the "source" oneof.

The format of the input example instances.

Data format enum.

Describes the state of the Execution.

The possible contents of ExecutionName.

Defines how a feature is encoded. Defaults to IDENTITY.

The color scheme used for highlighting areas.

How the original image is displayed in the visualization.

Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.

Type of the image visualization. Only applicable to [Integrated Gradients attribution][google.cloud.aiplatform.v1beta1.ExplanationParameters.integrated_gradients_attribution].

Enum of possible cases for the "display_name_mapping" oneof.

Enum of possible cases for the "method" oneof.

Enum of possible cases for the "destination" oneof.

Enum of possible cases for the "split" oneof.

Enum of possible cases for the "mode" oneof.

Enum of possible cases for the "api_spec" oneof.

The possible contents of ExtensionName.

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.

Only applicable for Vertex AI Legacy Feature Store. An enum representing the value type of a feature.

Enum of possible cases for the "source" oneof.

The possible contents of FeatureGroupName.

The possible contents of FeatureName.

Enum of possible cases for the "storage_type" oneof.

Possible states a featureOnlineStore can have.

The possible contents of FeatureOnlineStoreName.

Enum of possible cases for the "value" oneof.

Enum of possible cases for the "destination" oneof.

Enum of possible cases for the "source" oneof.

Enum of possible cases for the "algorithm_config" oneof.

The distance measure used in nearest neighbor search.

Service agent type used during data sync.

Enum of possible cases for the "algorithm_config" oneof.

Format of the data in the Feature View.

Enum of possible cases for the "key_oneof" oneof.

The possible contents of FeatureViewName.

The possible contents of FeatureViewSyncName.

Possible states a featurestore can have.

Defines the baseline to do anomaly detection for feature values imported by each [ImportFeatureValues][google.cloud.aiplatform.v1beta1.FeaturestoreService.ImportFeatureValues] operation.

The state defines whether to enable ImportFeature analysis.

Enum of possible cases for the "threshold" oneof.

The possible contents of FeaturestoreName.

Enum of possible cases for the "entity_id" oneof.

Format of the response data.

Enum of possible cases for the "format" oneof.

Enum of possible cases for the "data" oneof.

RagFile state.

Enum of possible cases for the "ranking" oneof.

Function calling mode.

Blocked reason enumeration.

Enum of possible cases for the "routing_config" oneof.

The model routing preference.

The type of the Google Drive resource.

Enum of possible cases for the "chunk_type" oneof.

Harm categories that will block the content.

Enum of location an HTTP element can be.

The possible contents of HyperparameterTuningJobName.

Enum of possible cases for the "source" oneof.

Enum of possible cases for the "feature_time_source" oneof.

Enum of possible cases for the "source" oneof.

Enum of possible cases for the "import_source" oneof.

Enum of possible cases for the "partial_failure_sink" oneof.

Enum of possible cases for the "partial_failure_sink" oneof.

The update method of an Index.

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.

Enum of possible cases for the "Value" oneof.

The possible contents of IndexEndpointName.

The possible contents of IndexName.

Enum of possible cases for the "destination" oneof.

Enum of possible cases for the "split" oneof.

Describes the state of a job.

Describes the type of the MetadataSchema.

The possible contents of MetadataSchemaName.

The possible contents of MetadataStoreName.

Enum of possible cases for the "resource" oneof.

Enum of possible cases for the "request" oneof.

Enum of possible cases for the "migrated_resource" oneof.

Enum of possible cases for the "source" oneof.

Identifies a type of Model's prediction resources.

The Model content that can be exported.

Indicates where does the log come from.

Indicates what type of traffic does the log belong to.

The state to Specify the monitoring pipeline.

The possible contents of ModelDeploymentMonitoringJobName.

The Model Monitoring Objective types.

The possible contents of ModelEvaluationName.

Enum of possible cases for the "kind" oneof.

Enum of possible cases for the "kind" oneof.

The possible contents of ModelEvaluationSliceName.

Enum of possible cases for the "default_objective" oneof.

Enum of possible cases for the "source" oneof.

The possible contents of ModelMonitorName.

Enum of possible cases for the "condition" oneof.

Enum of possible cases for the "alert" oneof.

Enum of possible cases for the "anomaly" oneof.

Enum of possible cases for the "dataset" oneof.

Enum of possible cases for the "time_spec" oneof.

Enum of possible cases for the "data_location" oneof.

Enum of possible cases for the "connection" oneof.

Supported data format.

The possible contents of ModelMonitoringJobName.

Enum of possible cases for the "destination" oneof.

The storage format of the predictions generated BatchPrediction job.

Enum of possible cases for the "data_source" oneof.

Enum of possible cases for the "objective" oneof.

Enum of possible cases for the "stats" oneof.

Enum of possible cases for the "value" oneof.

The possible contents of ModelName.

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.

The possible contents of NasJobName.

Enum of possible cases for the "output" oneof.

Enum of possible cases for the "nas_algorithm_spec" oneof.

The available types of optimization goals.

The available types of multi-trial algorithms.

Describes a NasTrial state.

The possible contents of NasTrialDetailName.

Enum of possible cases for the "instance" oneof.

Datapoints for which Operator is true relative to the query’s Value field will be allowlisted.

Enum of possible cases for the "Value" oneof.

The possible contents of NetworkAttachmentName.

The possible contents of NetworkName.

Enum of possible cases for the "environment_spec" oneof.

Enum of possible cases for the "execution_identity" oneof.

Enum of possible cases for the "execution_sink" oneof.

Enum of possible cases for the "notebook_source" oneof.

The possible contents of NotebookExecutionJobName.

Views for Get/List NotebookExecutionJob

The substate of the NotebookRuntime to display health information.

The substate of the NotebookRuntime to display state of runtime. The resource of NotebookRuntime is in ACTIVE state for these sub state.

The possible contents of NotebookRuntimeName.

The possible contents of NotebookRuntimeTemplateName.

Represents a notebook runtime type.

The possible contents of NotificationChannelName.

Pairwise prediction autorater preference.

Enum of possible cases for the "instance" oneof.

Enum of possible cases for the "data" oneof.

Enum of possible cases for the "metadata" oneof.

Describes the PersistentResource state.

The possible contents of PersistentResourceName.

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.

Enum of possible cases for the "runtime_detail" oneof.

Enum of possible cases for the "kind" oneof.

An enum that specifies the behavior to take if the timeout is reached.

The possible contents of PipelineJobName.

Describes the state of a pipeline.

Specifies state of TaskExecution

Enum of possible cases for the "details" oneof.

Enum of possible cases for the "instance" oneof.

Enum of possible cases for the "response" oneof.

Preset option controlling parameters for different modalities

Preset option controlling parameters for query speed-precision trade-off

Enum of possible cases for the "probe_type" oneof.

Enum of possible cases for the "prediction_resources" oneof.

An enum representing the launch stage of a PublisherModel.

An enum representing the open source category of a PublisherModel.

Enum of possible cases for the "reference" oneof.

An enum representing the state of the PublicModelVersion.

The possible contents of PublisherModelName.

View enumeration of PublisherModel.

The possible contents of RagCorpusName.

Enum of possible cases for the "model_config" oneof.

Enum of possible cases for the "model" oneof.

Enum of possible cases for the "rag_file_source" oneof.

The type of the RagFile.

The possible contents of RagFileName.

Enum of possible cases for the "query" oneof.

Enum of possible cases for the "vector_db" oneof.

Enum of possible cases for the "data" oneof.

The possible contents of ReasoningEngineName.

Identifies a type of reservation affinity.

The possible contents of ReservationName.

Enum of possible cases for the "source" oneof.

Enum of possible cases for the "data_source" oneof.

Enum of possible cases for the "GoogleFirstPartyExtensionConfig" oneof.

Harm probability levels in the content.

Harm severity levels.

Probability vs severity.

Probability based thresholds levels for blocking.

Enum of possible cases for the "following_batch_sample_size" oneof.

Enum of possible cases for the "initial_batch_sample_size" oneof.

Sample strategy decides which subset of DataItems should be selected for human labeling in every batch.

The possible contents of SavedQueryName.

Enum of possible cases for the "request" oneof.

Enum of possible cases for the "time_specification" oneof.

Possible state of the schedule.

The possible contents of ScheduleName.

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.

Enum of possible cases for the "order" oneof.

Enum of possible cases for the "filter" oneof.

The possible contents of SecretVersionName.

The possible contents of ServiceName.

Enum of possible cases for the "drive_source" oneof.

Enum of possible cases for the "folder_source" oneof.

Enum of possible cases for the "GradientNoiseSigma" oneof.

The possible contents of SpecialistPoolName.

Describes the Study state.

The possible contents of StudyName.

Enum of possible cases for the "automated_stopping_spec" oneof.

The available search algorithms for the Study.

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.

The available types of optimization goals.

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.

Enum of possible cases for the "parameter_value_spec" oneof.

Enum of possible cases for the "parent_value_condition" oneof.

The type of scaling that should be applied to this parameter.

Enum of possible cases for the "constraint" oneof.

The possible contents of SubnetworkName.

Supported adapter sizes for tuning.

Data type of the tensor.

The possible contents of TensorboardExperimentName.

The possible contents of TensorboardName.

The possible contents of TensorboardRunName.

An enum representing the value type of a TensorboardTimeSeries.

The possible contents of TensorboardTimeSeriesName.

Enum of possible cases for the "threshold" oneof.

Enum of possible cases for the "value" oneof.

Enum of possible cases for the "Target" oneof.

The possible contents of TrainingPipelineName.

Describes a Trial state.

The possible contents of TrialName.

Enum of possible cases for the "tuned_model_ref" oneof.

Enum of possible cases for the "tuning_data_stats" oneof.