Types overview

enum

Confidence level

enum

Filtered category

string

Input prompt

number (double format)

Score for category

object (CloudAiLargeModelsVisionMedia)

The generates samples.

string

Returns rai error message for filtered videos.

integer (int32 format)

Returns if any videos were filtered due to RAI policies.

string

Returns rai failure reasons if any.

object (CloudAiLargeModelsVisionFilteredText)

Returns filtered text rai info.

string

Image encoding, encoded as "image/png" or "image/jpg".

string (bytes format)

Raw bytes.

object (CloudAiLargeModelsVisionImageRAIScores)

RAI scores for generated image.

object (CloudAiLargeModelsVisionRaiInfo)

RAI info for image.

object (CloudAiLargeModelsVisionSemanticFilterResponse)

Semantic filter info for image.

string

Text/Expanded text input for imagen.

string

Path to another storage (typically Google Cloud Storage).

number (double format)

Agile watermark score for image.

object (CloudAiLargeModelsVisionImage)

Image.

object (CloudAiLargeModelsVisionVideo)

Video

string

(No description provided)

string

(No description provided)

number (float format)

(No description provided)

number (float format)

(No description provided)

number (float format)

(No description provided)

number (float format)

(No description provided)

number (float format)

(No description provided)

string

List of rai categories' information to return

number (float format)

List of rai scores mapping to the rai categories. Rounded to 1 decimal place.

object (CloudAiLargeModelsVisionNamedBoundingBox)

Class labels of the bounding boxes that failed the semantic filtering. Bounding box coordinates.

boolean

This response is added when semantic filter config is turned on in EditConfig. It reports if this image is passed semantic filter response. If passed_semantic_filter is false, the bounding box information will be populated for user to check what caused the semantic filter to fail.

string

Path to another storage (typically Google Cloud Storage).

string (bytes format)

Raw bytes.

string

The HTTP Content-Type header value specifying the content type of the body.

string (bytes format)

The HTTP request/response body as raw binary.

object

Application specific response metadata. Must be set in the first response for streaming APIs.

string (int64 format)

Max number of human labeled DataItems.

integer (int32 format)

Max percent of total DataItems for human labeling.

object (GoogleCloudAiplatformV1SampleConfig)

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

object (GoogleCloudAiplatformV1TrainingConfig)

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.

string

The resource names of the Artifacts to attribute to the Context. Format: projects/{project}/locations/{location}/metadataStores/{metadatastore}/artifacts/{artifact}

string

The resource names of the Executions to associate with the Context. Format: projects/{project}/locations/{location}/metadataStores/{metadatastore}/executions/{execution}

string

The resource names of the child Contexts.

object (GoogleCloudAiplatformV1Event)

The Events to create and add.

object (GoogleCloudAiplatformV1Measurement)

Required. The measurement to be added to a Trial.

object (GoogleCloudAiplatformV1UserActionReference)

Output only. The source of the Annotation.

string (Timestamp format)

Output only. Timestamp when this Annotation was created.

string

Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

Optional. The labels with user-defined metadata to organize your Annotations. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Annotation(System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. Following system labels exist for each Annotation: * "aiplatform.googleapis.com/annotation_set_name": optional, name of the UI's annotation set this Annotation belongs to. If not set, the Annotation is not visible in the UI. * "aiplatform.googleapis.com/payload_schema": output only, its value is the payload_schema's title.

string

Output only. Resource name of the Annotation.

any

Required. The schema of the payload can be found in payload_schema.

string

Required. Google Cloud Storage URI points to a YAML file describing payload. The schema is defined as an OpenAPI 3.0.2 Schema Object. The schema files that can be used here are found in gs://google-cloud-aiplatform/schema/dataset/annotation/, note that the chosen schema must be consistent with the parent Dataset's metadata.

string (Timestamp format)

Output only. Timestamp when this Annotation was last updated.

string (Timestamp format)

Output only. Timestamp when this AnnotationSpec was created.

string

Required. The user-defined name of the AnnotationSpec. The name can be up to 128 characters long and can consist of any UTF-8 characters.

string

Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

string

Output only. Resource name of the AnnotationSpec.

string (Timestamp format)

Output only. Timestamp when AnnotationSpec was last updated.

string (Timestamp format)

Output only. Timestamp when this Artifact was created.

string

Description of the Artifact

string

User provided display name of the Artifact. May be up to 128 Unicode characters.

string

An eTag used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

The labels with user-defined metadata to organize your Artifacts. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Artifact (System labels are excluded).

map (key: string, value: any)

Properties of the Artifact. Top level metadata keys' heading and trailing spaces will be trimmed. The size of this field should not exceed 200KB.

string

Output only. The resource name of the Artifact.

string

The title of the schema describing the metadata. Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store.

string

The version of the schema in schema_name to use. Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store.

enum

The state of this Artifact. This is a property of the Artifact, and does not imply or capture any ongoing process. This property is managed by clients (such as Vertex AI Pipelines), and the system does not prescribe or check the validity of state transitions.

string (Timestamp format)

Output only. Timestamp when this Artifact was last updated.

string

The uniform resource identifier of the artifact file. May be empty if there is no actual artifact file.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The operation generic information.

string

A human-readable message that shows the intermediate progress details of NotebookRuntime.

object (GoogleCloudAiplatformV1NotebookRuntime)

Required. Provide runtime specific information (e.g. runtime owner, notebook id) used for NotebookRuntime assignment.

string

Optional. User specified ID for the notebook runtime.

string

Required. The resource name of the NotebookRuntimeTemplate based on which a NotebookRuntime will be assigned (reuse or create a new one).

number (double format)

Output only. Error of feature_attributions caused by approximation used in the explanation method. Lower value means more precise attributions. * For Sampled Shapley attribution, increasing path_count might reduce the error. * For Integrated Gradients attribution, increasing step_count might reduce the error. * For XRAI attribution, increasing step_count might reduce the error. See this introduction for more information.

number (double format)

Output only. Model predicted output if the input instance is constructed from the baselines of all the features defined in ExplanationMetadata.inputs. The field name of the output is determined by the key in ExplanationMetadata.outputs. If the Model's predicted output has multiple dimensions (rank > 1), this is the value in the output located by output_index. If there are multiple baselines, their output values are averaged.

any

Output only. Attributions of each explained feature. Features are extracted from the prediction instances according to explanation metadata for inputs. The value is a struct, whose keys are the name of the feature. The values are how much the feature in the instance contributed to the predicted result. The format of the value is determined by the feature's input format: * If the feature is a scalar value, the attribution value is a floating number. * If the feature is an array of scalar values, the attribution value is an array. * If the feature is a struct, the attribution value is a struct. The keys in the attribution value struct are the same as the keys in the feature struct. The formats of the values in the attribution struct are determined by the formats of the values in the feature struct. The ExplanationMetadata.feature_attributions_schema_uri field, pointed to by the ExplanationSpec field of the Endpoint.deployed_models object, points to the schema file that describes the features and their attribution values (if it is populated).

number (double format)

Output only. Model predicted output on the corresponding explanation instance. The field name of the output is determined by the key in ExplanationMetadata.outputs. If the Model predicted output has multiple dimensions, this is the value in the output located by output_index.

string

Output only. The display name of the output identified by output_index. For example, the predicted class name by a multi-classification Model. This field is only populated iff the Model predicts display names as a separate field along with the explained output. The predicted display name must has the same shape of the explained output, and can be located using output_index.

integer (int32 format)

Output only. The index that locates the explained prediction output. If the prediction output is a scalar value, output_index is not populated. If the prediction output has multiple dimensions, the length of the output_index list is the same as the number of dimensions of the output. The i-th element in output_index is the element index of the i-th dimension of the output vector. Indices start from 0.

string

Output only. Name of the explain output. Specified as the key in ExplanationMetadata.outputs.

integer (int32 format)

Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.

integer (int32 format)

Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.

string

Required. The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization

integer (int32 format)

The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.

object (GoogleCloudAiplatformV1GcsSource)

Required. Google Cloud Storage location.

string

Required. The names of the PipelineJobs to cancel. A maximum of 32 PipelineJobs can be cancelled in a batch. Format: projects/{project}/locations/{location}/pipelineJobs/{pipelineJob}

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for Feature.

object (GoogleCloudAiplatformV1CreateFeatureRequest)

Required. The request message specifying the Features to create. All Features must be created under the same parent EntityType. The parent field in each child request message can be omitted. If parent is set in a child request, then the value must match the parent value in this request message.

object (GoogleCloudAiplatformV1Feature)

The Features created.

object (GoogleCloudAiplatformV1CreateTensorboardRunRequest)

Required. The request message specifying the TensorboardRuns to create. A maximum of 1000 TensorboardRuns can be created in a batch.

object (GoogleCloudAiplatformV1TensorboardRun)

The created TensorboardRuns.

object (GoogleCloudAiplatformV1CreateTensorboardTimeSeriesRequest)

Required. The request message specifying the TensorboardTimeSeries to create. A maximum of 1000 TensorboardTimeSeries can be created in a batch.

object (GoogleCloudAiplatformV1TensorboardTimeSeries)

The created TensorboardTimeSeries.

object (GoogleCloudAiplatformV1MachineSpec)

Required. Immutable. The specification of a single machine.

integer (int32 format)

Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.

integer (int32 format)

Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count

string

Required. The names of the PipelineJobs to delete. A maximum of 32 PipelineJobs can be deleted in a batch. Format: projects/{project}/locations/{location}/pipelineJobs/{pipelineJob}

object (GoogleCloudAiplatformV1EvaluatedAnnotation)

Required. Evaluated annotations resource to be imported.

integer (int32 format)

Output only. Number of EvaluatedAnnotations imported.

object (GoogleCloudAiplatformV1ModelEvaluationSlice)

Required. Model evaluation slice resource to be imported.

string

Output only. List of imported ModelEvaluationSlice.name.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The common part of the operation metadata.

object (GoogleCloudAiplatformV1BatchMigrateResourcesOperationMetadataPartialResult)

Partial results that reflect the latest migration operation progress.

string

Migrated dataset resource name.

object (GoogleRpcStatus)

The error result of the migration request in case of failure.

string

Migrated model resource name.

object (GoogleCloudAiplatformV1MigrateResourceRequest)

It's the same as the value in MigrateResourceRequest.migrate_resource_requests.

object (GoogleCloudAiplatformV1MigrateResourceRequest)

Required. The request messages specifying the resources to migrate. They must be in the same location as the destination. Up to 50 resources can be migrated in one batch.

object (GoogleCloudAiplatformV1MigrateResourceResponse)

Successfully migrated resources.

object (GoogleCloudAiplatformV1CompletionStats)

Output only. Statistics on completed and failed prediction instances.

string (Timestamp format)

Output only. Time when the BatchPredictionJob was created.

object (GoogleCloudAiplatformV1BatchDedicatedResources)

The config of resources used by the Model during the batch prediction. If the Model supports DEDICATED_RESOURCES this config may be provided (and the job will use these resources), if the Model doesn't support AUTOMATIC_RESOURCES, this config must be provided.

boolean

For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true.

string

Required. The user-defined name of this BatchPredictionJob.

object (GoogleCloudAiplatformV1EncryptionSpec)

Customer-managed encryption key options for a BatchPredictionJob. If this is set, then all resources created by the BatchPredictionJob will be encrypted with the provided encryption key.

string (Timestamp format)

Output only. Time when the BatchPredictionJob entered any of the following states: JOB_STATE_SUCCEEDED, JOB_STATE_FAILED, JOB_STATE_CANCELLED.

object (GoogleRpcStatus)

Output only. Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.

object (GoogleCloudAiplatformV1ExplanationSpec)

Explanation configuration for this BatchPredictionJob. Can be specified only if generate_explanation is set to true. This value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of the explanation_spec object is not populated, the corresponding field of the Model.explanation_spec object is inherited.

boolean

Generate explanation with the batch prediction results. When set to true, the batch prediction output changes based on the predictions_format field of the BatchPredictionJob.output_config object: * bigquery: output includes a column named explanation. The value is a struct that conforms to the Explanation object. * jsonl: The JSON objects on each line include an additional entry keyed explanation. The value of the entry is a JSON object that conforms to the Explanation object. * csv: Generating explanations for CSV format is not supported. If this field is set to true, either the Model.explanation_spec or explanation_spec must be populated.

object (GoogleCloudAiplatformV1BatchPredictionJobInputConfig)

Required. Input configuration of the instances on which predictions are performed. The schema of any single instance may be specified via the Model's PredictSchemata's instance_schema_uri.

object (GoogleCloudAiplatformV1BatchPredictionJobInstanceConfig)

Configuration for how to convert batch prediction input instances to the prediction instances that are sent to the Model.

map (key: string, value: string)

The labels with user-defined metadata to organize BatchPredictionJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.

object (GoogleCloudAiplatformV1ManualBatchTuningParameters)

Immutable. Parameters configuring the batch behavior. Currently only applicable when dedicated_resources are used (in other cases Vertex AI does the tuning itself).

string

The name of the Model resource that produces the predictions via this job, must share the same ancestor Location. Starting this job has no impact on any existing deployments of the Model and their resources. Exactly one of model and unmanaged_container_model must be set. The model resource name may contain version id or version alias to specify the version. Example: projects/{project}/locations/{location}/models/{model}@2 or projects/{project}/locations/{location}/models/{model}@golden if no version is specified, the default version will be deployed. The model resource could also be a publisher model. Example: publishers/{publisher}/models/{model} or projects/{project}/locations/{location}/publishers/{publisher}/models/{model}

any

The parameters that govern the predictions. The schema of the parameters may be specified via the Model's PredictSchemata's parameters_schema_uri.

string

Output only. The version ID of the Model that produces the predictions via this job.

string

Output only. Resource name of the BatchPredictionJob.

object (GoogleCloudAiplatformV1BatchPredictionJobOutputConfig)

Required. The Configuration specifying where output predictions should be written. The schema of any single prediction may be specified as a concatenation of Model's PredictSchemata's instance_schema_uri and prediction_schema_uri.

object (GoogleCloudAiplatformV1BatchPredictionJobOutputInfo)

Output only. Information further describing the output of this job.

object (GoogleRpcStatus)

Output only. Partial failures encountered. For example, single files that can't be read. This field never exceeds 20 entries. Status details fields contain standard Google Cloud error details.

object (GoogleCloudAiplatformV1ResourcesConsumed)

Output only. Information about resources that had been consumed by this job. Provided in real time at best effort basis, as well as a final value once the job completes. Note: This field currently may be not populated for batch predictions that use AutoML Models.

string

The service account that the DeployedModel's container runs as. If not specified, a system generated one will be used, which has minimal permissions and the custom container, if used, may not have enough permission to access other Google Cloud resources. Users deploying the Model must have the iam.serviceAccounts.actAs permission on this service account.

string (Timestamp format)

Output only. Time when the BatchPredictionJob for the first time entered the JOB_STATE_RUNNING state.

enum

Output only. The detailed state of the job.

object (GoogleCloudAiplatformV1UnmanagedContainerModel)

Contains model information necessary to perform batch prediction without requiring uploading to model registry. Exactly one of model and unmanaged_container_model must be set.

string (Timestamp format)

Output only. Time when the BatchPredictionJob was most recently updated.

object (GoogleCloudAiplatformV1BigQuerySource)

The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.

object (GoogleCloudAiplatformV1GcsSource)

The Cloud Storage location for the input instances.

string

Required. The format in which instances are given, must be one of the Model's supported_input_storage_formats.

string

Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, BigQuery or TfRecord.

string

Fields that will be included in the prediction instance that is sent to the Model. If instance_type is array, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, BigQuery or TfRecord.

string

The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: * object: Each input is converted to JSON object format. * For bigquery, each row is converted to an object. * For jsonl, each line of the JSONL input must be an object. * Does not apply to csv, file-list, tf-record, or tf-record-gzip. * array: Each input is converted to JSON array format. * For bigquery, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * For jsonl, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply to csv, file-list, tf-record, or tf-record-gzip. If not specified, Vertex AI converts the batch prediction input as follows: * For bigquery and csv, the behavior is the same as array. The order of columns is the same as defined in the file or table, unless included_fields is populated. * For jsonl, the prediction instance format is determined by each line of the input. * For tf-record/tf-record-gzip, each record will be converted to an object in the format of {"b64": }, where is the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where is the Base64-encoded string of the content of the file.

string

The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named key in the output: * For jsonl output format, the output will have a key field instead of the instance field. * For csv/bigquery output format, the output will have have a key column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.

object (GoogleCloudAiplatformV1BigQueryDestination)

The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name prediction__ where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created, predictions, and errors. If the Model has both instance and prediction schemata defined then the tables have columns as follows: The predictions table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. The errors table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing only code and message.

object (GoogleCloudAiplatformV1GcsDestination)

The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is prediction--, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it files predictions_0001., predictions_0002., ..., predictions_N. are created where ` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.,errors_0002.,...,errors_N.files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerrorfield which as value has google.rpc.Status containing onlycodeandmessage` fields.

string

Required. The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.

string

Output only. The path of the BigQuery dataset created, in bq://projectId.bqDatasetId format, into which the prediction output is written.

string

Output only. The name of the BigQuery table created, in predictions_ format, into which the prediction output is written. Can be used by UI to generate the BigQuery output path, for example.

string

Output only. The full path of the Cloud Storage directory created, into which the prediction output is written.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for Featurestore batch read Features values.

object (GoogleCloudAiplatformV1BigQuerySource)

Similar to csv_read_instances, but from BigQuery source.

object (GoogleCloudAiplatformV1CsvSource)

Each read instance consists of exactly one read timestamp and one or more entity IDs identifying entities of the corresponding EntityTypes whose Features are requested. Each output instance contains Feature values of requested entities concatenated together as of the read time. An example read instance may be foo_entity_id, bar_entity_id, 2020-01-01T10:00:00.123Z. An example output instance may be foo_entity_id, bar_entity_id, 2020-01-01T10:00:00.123Z, foo_entity_feature1_value, bar_entity_feature2_value. Timestamp in each read instance must be millisecond-aligned. csv_read_instances are read instances stored in a plain-text CSV file. The header should be: [ENTITY_TYPE_ID1], [ENTITY_TYPE_ID2], ..., timestamp The columns can be in any order. Values in the timestamp column must use the RFC 3339 format, e.g. 2012-07-30T10:43:17.123Z.

object (GoogleCloudAiplatformV1FeatureValueDestination)

Required. Specifies output location and format.

object (GoogleCloudAiplatformV1BatchReadFeatureValuesRequestEntityTypeSpec)

Required. Specifies EntityType grouping Features to read values of and settings.

object (GoogleCloudAiplatformV1BatchReadFeatureValuesRequestPassThroughField)

When not empty, the specified fields in the *_read_instances source will be joined as-is in the output, in addition to those fields from the Featurestore Entity. For BigQuery source, the type of the pass-through values will be automatically inferred. For CSV source, the pass-through values will be passed as opaque bytes.

string (Timestamp format)

Optional. Excludes Feature values with feature generation timestamp before this timestamp. If not set, retrieve oldest values kept in Feature Store. Timestamp, if present, must not have higher than millisecond precision.

string

Required. ID of the EntityType to select Features. The EntityType id is the entity_type_id specified during EntityType creation.

object (GoogleCloudAiplatformV1FeatureSelector)

Required. Selectors choosing which Feature values to read from the EntityType.

object (GoogleCloudAiplatformV1DestinationFeatureSetting)

Per-Feature settings for the batch read.

string

Required. The name of the field in the CSV header or the name of the column in BigQuery table. The naming restriction is the same as Feature.name.

object (GoogleCloudAiplatformV1TimeSeriesData)

The returned time series data.

string

Required. BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.

string

Required. BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example: bq://projectId.bqDatasetId.bqTableId.

string (bytes format)

Required. Raw bytes.

string

Required. The IANA standard MIME type of the source data.

number (float format)

The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.

boolean

A list of bool values.

object (GoogleCloudAiplatformV1CitationMetadata)

Output only. Source attribution of the generated content.

object (GoogleCloudAiplatformV1Content)

Output only. Content parts of the candidate.

string

Output only. Describes the reason the mode stopped generating tokens in more detail. This is only filled when finish_reason is set.

enum

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

object (GoogleCloudAiplatformV1GroundingMetadata)

Output only. Metadata specifies sources used to ground generated content.

integer (int32 format)

Output only. Index of the candidate.

object (GoogleCloudAiplatformV1SafetyRating)

Output only. List of ratings for the safety of a response candidate. There is at most one rating per category.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for suggesting Trials.

string

The name of the Study that the Trial belongs to.

string

The Trial name.

boolean

True if the Trial should stop.

integer (int32 format)

Output only. End index into the content.

string

Output only. License of the attribution.

object (GoogleTypeDate)

Output only. Publication date of the attribution.

integer (int32 format)

Output only. Start index into the content.

string

Output only. Title of the attribution.

string

Output only. Url reference of the attribution.

object (GoogleCloudAiplatformV1Citation)

Output only. List of citations.

object (GoogleCloudAiplatformV1Measurement)

Optional. If provided, it will be used as the completed Trial's final_measurement; Otherwise, the service will auto-select a previously reported measurement as the final-measurement

string

Optional. A human readable reason why the trial was infeasible. This should only be provided if trial_infeasible is true.

boolean

Optional. True if the Trial cannot be run with the given Parameter, and final_measurement will be ignored.

string (int64 format)

Output only. The number of entities for which any error was encountered.

string (int64 format)

Output only. In cases when enough errors are encountered a job, pipeline, or operation may be failed as a whole. Below is the number of entities for which the processing had not been finished (either in successful or failed state). Set to -1 if the number is unknown (for example, the operation failed before the total entity number could be collected).

string (int64 format)

Output only. The number of entities that had been processed successfully.

string (int64 format)

Output only. The number of the successful forecast points that are generated by the forecasting model. This is ONLY used by the forecasting batch prediction.

any

Required. The instances that are the input to token computing API call. Schema is identical to the prediction schema of the text model, even for the non-text models, like chat models, or Codey models.

object (GoogleCloudAiplatformV1TokensInfo)

Lists of tokens info from the input. A ComputeTokensRequest could have multiple instances with a prompt in each instance. We also need to return lists of tokens info for the request with multiple instances.

string

Required. Container Registry URI of a container image. Only Google Container Registry and Artifact Registry are supported now. Accepted forms: * Google Container Registry path. For example: gcr.io/projectId/imageName:tag. * Artifact Registry path. For example: us-central1-docker.pkg.dev/projectId/repoName/imageName:tag. If a tag is not specified, "latest" will be used as the default tag.

string

The arguments to be passed when starting the container.

string

The command to be invoked when the container is started. It overrides the entrypoint instruction in Dockerfile when provided.

object (GoogleCloudAiplatformV1EnvVar)

Environment variables to be passed to the container. Maximum limit is 100.

string

Required. The URI of a container image in the Container Registry that is to be run on each worker replica.

object (GoogleCloudAiplatformV1Part)

Required. Ordered Parts that constitute a single message. Parts may have different IANA MIME types.

string

Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.

string (Timestamp format)

Output only. Timestamp when this Context was created.

string

Description of the Context

string

User provided display name of the Context. May be up to 128 Unicode characters.

string

An eTag used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

The labels with user-defined metadata to organize your Contexts. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Context (System labels are excluded).

map (key: string, value: any)

Properties of the Context. Top level metadata keys' heading and trailing spaces will be trimmed. The size of this field should not exceed 200KB.

string

Immutable. The resource name of the Context.

string

Output only. A list of resource names of Contexts that are parents of this Context. A Context may have at most 10 parent_contexts.

string

The title of the schema describing the metadata. Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store.

string

The version of the schema in schema_name to use. Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store.

string (Timestamp format)

Output only. Timestamp when this Context was last updated.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The common part of the operation metadata.

object (GoogleCloudAiplatformV1EncryptionSpec)

Customer-managed encryption key options. If this is set, then the Model copy will be encrypted with the provided encryption key.

string

Optional. Copy source_model into a new Model with this ID. The ID will become the final component of the model resource name. This value may be up to 63 characters, and valid characters are [a-z0-9_-]. The first character cannot be a number or hyphen.

string

Optional. Specify this field to copy source_model into this existing Model as a new version. Format: projects/{project}/locations/{location}/models/{model}

string

Required. The resource name of the Model to copy. That Model must be in the same Project. Format: projects/{project}/locations/{location}/models/{model}

string

The name of the copied Model resource. Format: projects/{project}/locations/{location}/models/{model}

string

Output only. The version ID of the model that is copied.

object (GoogleCloudAiplatformV1Content)

Required. Input content.

any

Required. The instances that are the input to token counting call. Schema is identical to the prediction schema of the underlying model.

string

Required. The name of the publisher model requested to serve the prediction. Format: projects/{project}/locations/{location}/publishers/*/models/*

integer (int32 format)

The total number of billable characters counted across all instances from the request.

integer (int32 format)

The total number of tokens counted across all instances from the request.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The operation generic information.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The common part of the operation metadata.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The operation generic information.

object (GoogleCloudAiplatformV1DeploymentResourcePool)

Required. The DeploymentResourcePool to create.

string

Required. The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are /^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$/.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The operation generic information.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for EntityType.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for FeatureGroup.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for FeatureOnlineStore.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for Feature.

object (GoogleCloudAiplatformV1Feature)

Required. The Feature to create.

string

Required. The ID to use for the Feature, which will become the final component of the Feature's resource name. This value may be up to 128 characters, and valid characters are [a-z0-9_]. The first character cannot be a number. The value must be unique within an EntityType/FeatureGroup.

string

Required. The resource name of the EntityType or FeatureGroup to create a Feature. Format for entity_type as parent: projects/{project}/locations/{location}/featurestores/{featurestore}/entityTypes/{entity_type} Format for feature_group as parent: projects/{project}/locations/{location}/featureGroups/{feature_group}

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for FeatureView Create.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for Featurestore.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The operation generic information.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The operation generic information.

object (GoogleCloudAiplatformV1NearestNeighborSearchOperationMetadata)

The operation metadata with regard to Matching Engine Index operation.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for creating a MetadataStore.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The operation generic information.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for PersistentResource.

string

Progress Message for Create LRO

string

Required. The resource name of the Location to create the PipelineJob in. Format: projects/{project}/locations/{location}

object (GoogleCloudAiplatformV1PipelineJob)

Required. The PipelineJob to create.

string

The ID to use for the PipelineJob, which will become the final component of the PipelineJob name. If not provided, an ID will be automatically generated. This value should be less than 128 characters, and valid characters are /a-z-/.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for Feature.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The operation generic information.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for Tensorboard.

string

Required. The resource name of the TensorboardExperiment to create the TensorboardRun in. Format: projects/{project}/locations/{location}/tensorboards/{tensorboard}/experiments/{experiment}

object (GoogleCloudAiplatformV1TensorboardRun)

Required. The TensorboardRun to create.

string

Required. The ID to use for the Tensorboard run, which becomes the final component of the Tensorboard run's resource name. This value should be 1-128 characters, and valid characters are /a-z-/.

string

Required. The resource name of the TensorboardRun to create the TensorboardTimeSeries in. Format: projects/{project}/locations/{location}/tensorboards/{tensorboard}/experiments/{experiment}/runs/{run}

object (GoogleCloudAiplatformV1TensorboardTimeSeries)

Required. The TensorboardTimeSeries to create.

string

Optional. The user specified unique ID to use for the TensorboardTimeSeries, which becomes the final component of the TensorboardTimeSeries's resource name. This value should match "a-z0-9{0, 127}"

object (GoogleCloudAiplatformV1GcsDestination)

Required. Google Cloud Storage location.

object (GoogleCloudAiplatformV1GcsSource)

Required. Google Cloud Storage location.

string (Timestamp format)

Output only. Time when the CustomJob was created.

string

Required. The display name of the CustomJob. The name can be up to 128 characters long and can consist of any UTF-8 characters.

object (GoogleCloudAiplatformV1EncryptionSpec)

Customer-managed encryption key options for a CustomJob. If this is set, then all resources created by the CustomJob will be encrypted with the provided encryption key.

string (Timestamp format)

Output only. Time when the CustomJob entered any of the following states: JOB_STATE_SUCCEEDED, JOB_STATE_FAILED, JOB_STATE_CANCELLED.

object (GoogleRpcStatus)

Output only. Only populated when job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.

object (GoogleCloudAiplatformV1CustomJobSpec)

Required. Job spec.

map (key: string, value: string)

The labels with user-defined metadata to organize CustomJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.

string

Output only. Resource name of a CustomJob.

string (Timestamp format)

Output only. Time when the CustomJob for the first time entered the JOB_STATE_RUNNING state.

enum

Output only. The detailed state of the job.

string (Timestamp format)

Output only. Time when the CustomJob was most recently updated.

map (key: string, value: string)

Output only. URIs for accessing interactive shells (one URI for each training node). Only available if job_spec.enable_web_access is true. The keys are names of each node in the training job; for example, workerpool0-0 for the primary node, workerpool1-0 for the first node in the second worker pool, and workerpool1-1 for the second node in the second worker pool. The values are the URIs for each node's interactive shell.

object (GoogleCloudAiplatformV1GcsDestination)

The Cloud Storage location to store the output of this CustomJob or HyperparameterTuningJob. For HyperparameterTuningJob, the baseOutputDirectory of each child CustomJob backing a Trial is set to a subdirectory of name id under its parent HyperparameterTuningJob's baseOutputDirectory. The following Vertex AI environment variables will be passed to containers or python modules when this field is set: For CustomJob: * AIP_MODEL_DIR = /model/ * AIP_CHECKPOINT_DIR = /checkpoints/ * AIP_TENSORBOARD_LOG_DIR = /logs/ For CustomJob backing a Trial of HyperparameterTuningJob: * AIP_MODEL_DIR = //model/ * AIP_CHECKPOINT_DIR = //checkpoints/ * AIP_TENSORBOARD_LOG_DIR = //logs/

boolean

Optional. Whether you want Vertex AI to enable access to the customized dashboard in training chief container. If set to true, you can access the dashboard at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).

boolean

Optional. Whether you want Vertex AI to enable interactive shell access to training containers. If set to true, you can access interactive shells at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).

string

Optional. The Experiment associated with this job. Format: projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}

string

Optional. The Experiment Run associated with this job. Format: projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}-{experiment-run-name}

string

Optional. The name of the Model resources for which to generate a mapping to artifact URIs. Applicable only to some of the Google-provided custom jobs. Format: projects/{project}/locations/{location}/models/{model} In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: projects/{project}/locations/{location}/models/{model}@2 or projects/{project}/locations/{location}/models/{model}@golden If no version ID or alias is specified, the "default" version will be returned. The "default" version alias is created for the first version of the model, and can be moved to other versions later on. There will be exactly one default version.

string

Optional. The full name of the Compute Engine network to which the Job should be peered. For example, projects/12345/global/networks/myVPC. Format is of the form projects/{project}/global/networks/{network}. Where {project} is a project number, as in 12345, and {network} is a network name. To specify this field, you must have already configured VPC Network Peering for Vertex AI. If this field is left unspecified, the job is not peered with any network.

string

Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected.

string

The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations

string

Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range'].

object (GoogleCloudAiplatformV1Scheduling)

Scheduling options for a CustomJob.

string

Specifies the service account for workload run-as account. Users submitting jobs must have act-as permission on this run-as account. If unspecified, the Vertex AI Custom Code Service Agent for the CustomJob's project is used.

string

Optional. The name of a Vertex AI Tensorboard resource to which this CustomJob will upload Tensorboard logs. Format: projects/{project}/locations/{location}/tensorboards/{tensorboard}

object (GoogleCloudAiplatformV1WorkerPoolSpec)

Required. The spec of the worker pools including machine type and Docker image. All worker pools except the first one are optional and can be skipped by providing an empty value.

string (Timestamp format)

Output only. Timestamp when this DataItem was created.

string

Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

Optional. The labels with user-defined metadata to organize your DataItems. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one DataItem(System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable.

string

Output only. The resource name of the DataItem.

any

Required. The data that the DataItem represents (for example, an image or a text snippet). The schema of the payload is stored in the parent Dataset's metadata schema's dataItemSchemaUri field.

string (Timestamp format)

Output only. Timestamp when this DataItem was last updated.

object (GoogleCloudAiplatformV1Annotation)

The Annotations on the DataItem. If too many Annotations should be returned for the DataItem, this field will be truncated per annotations_limit in request. If it was, then the has_truncated_annotations will be set to true.

object (GoogleCloudAiplatformV1DataItem)

The DataItem.

boolean

True if and only if the Annotations field has been truncated. It happens if more Annotations for this DataItem met the request's annotation_filter than are allowed to be returned by annotations_limit. Note that if Annotations field is not being returned due to field mask, then this field will not be set to true no matter how many Annotations are there.

object (GoogleCloudAiplatformV1ActiveLearningConfig)

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

map (key: string, value: string)

Labels to assign to annotations generated by this DataLabelingJob. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable.

string (Timestamp format)

Output only. Timestamp when this DataLabelingJob was created.

object (GoogleTypeMoney)

Output only. Estimated cost(in US dollars) that the DataLabelingJob has incurred to date.

string

Required. Dataset resource names. Right now we only support labeling from a single Dataset. Format: projects/{project}/locations/{location}/datasets/{dataset}

string

Required. The user-defined name of the DataLabelingJob. The name can be up to 128 characters long and can consist of any UTF-8 characters. Display name of a DataLabelingJob.

object (GoogleCloudAiplatformV1EncryptionSpec)

Customer-managed encryption key spec for a DataLabelingJob. If set, this DataLabelingJob will be secured by this key. Note: Annotations created in the DataLabelingJob are associated with the EncryptionSpec of the Dataset they are exported to.

object (GoogleRpcStatus)

Output only. DataLabelingJob errors. It is only populated when job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.

any

Required. Input config parameters for the DataLabelingJob.

string

Required. Points to a YAML file stored on Google Cloud Storage describing the config for a specific type of DataLabelingJob. The schema files that can be used here are found in the https://storage.googleapis.com/google-cloud-aiplatform bucket in the /schema/datalabelingjob/inputs/ folder.

string

Required. The Google Cloud Storage location of the instruction pdf. This pdf is shared with labelers, and provides detailed description on how to label DataItems in Datasets.

integer (int32 format)

Required. Number of labelers to work on each DataItem.

integer (int32 format)

Output only. Current labeling job progress percentage scaled in interval [0, 100], indicating the percentage of DataItems that has been finished.

map (key: string, value: string)

The labels with user-defined metadata to organize your DataLabelingJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. Following system labels exist for each DataLabelingJob: * "aiplatform.googleapis.com/schema": output only, its value is the inputs_schema's title.

string

Output only. Resource name of the DataLabelingJob.

string

The SpecialistPools' resource names associated with this job.

enum

Output only. The detailed state of the job.

string (Timestamp format)

Output only. Timestamp when this DataLabelingJob was updated most recently.

string (Timestamp format)

Output only. Timestamp when this Dataset was created.

string (int64 format)

Output only. The number of DataItems in this Dataset. Only apply for non-structured Dataset.

string

The description of the Dataset.

string

Required. The user-defined name of the Dataset. The name can be up to 128 characters long and can consist of any UTF-8 characters.

object (GoogleCloudAiplatformV1EncryptionSpec)

Customer-managed encryption key spec for a Dataset. If set, this Dataset and all sub-resources of this Dataset will be secured by this key.

string

Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

The labels with user-defined metadata to organize your Datasets. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Dataset (System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable. Following system labels exist for each Dataset: * "aiplatform.googleapis.com/dataset_metadata_schema": output only, its value is the metadata_schema's title.

any

Required. Additional information about the Dataset.

string

Output only. The resource name of the Artifact that was created in MetadataStore when creating the Dataset. The Artifact resource name pattern is projects/{project}/locations/{location}/metadataStores/{metadata_store}/artifacts/{artifact}.

string

Required. Points to a YAML file stored on Google Cloud Storage describing additional information about the Dataset. The schema is defined as an OpenAPI 3.0.2 Schema Object. The schema files that can be used here are found in gs://google-cloud-aiplatform/schema/dataset/metadata/.

string

Optional. Reference to the public base model last used by the dataset. Only set for prompt datasets.

string

Output only. The resource name of the Dataset.

object (GoogleCloudAiplatformV1SavedQuery)

All SavedQueries belong to the Dataset will be returned in List/Get Dataset response. The annotation_specs field will not be populated except for UI cases which will only use annotation_spec_count. In CreateDataset request, a SavedQuery is created together if this field is set, up to one SavedQuery can be set in CreateDatasetRequest. The SavedQuery should not contain any AnnotationSpec.

string (Timestamp format)

Output only. Timestamp when this Dataset was last updated.

string

Output only. Name of the associated BigQuery dataset.

string (Timestamp format)

Output only. Timestamp when this DatasetVersion was created.

string

The user-defined name of the DatasetVersion. The name can be up to 128 characters long and can consist of any UTF-8 characters.

string

Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

any

Required. Output only. Additional information about the DatasetVersion.

string

Output only. Reference to the public base model last used by the dataset version. Only set for prompt dataset versions.

string

Output only. The resource name of the DatasetVersion.

string (Timestamp format)

Output only. Timestamp when this DatasetVersion was last updated.

object (GoogleCloudAiplatformV1AutoscalingMetricSpec)

Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.

object (GoogleCloudAiplatformV1MachineSpec)

Required. Immutable. The specification of a single machine used by the prediction.

integer (int32 format)

Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).

integer (int32 format)

Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for Featurestore delete Features values.

object (GoogleCloudAiplatformV1DeleteFeatureValuesRequestSelectEntity)

Select feature values to be deleted by specifying entities.

object (GoogleCloudAiplatformV1DeleteFeatureValuesRequestSelectTimeRangeAndFeature)

Select feature values to be deleted by specifying time range and features.

object (GoogleCloudAiplatformV1EntityIdSelector)

Required. Selectors choosing feature values of which entity id to be deleted from the EntityType.

object (GoogleCloudAiplatformV1FeatureSelector)

Required. Selectors choosing which feature values to be deleted from the EntityType.

boolean

If set, data will not be deleted from online storage. When time range is older than the data in online storage, setting this to be true will make the deletion have no impact on online serving.

object (GoogleTypeInterval)

Required. Select feature generated within a half-inclusive time range. The time range is lower inclusive and upper exclusive.

object (GoogleCloudAiplatformV1DeleteFeatureValuesResponseSelectEntity)

Response for request specifying the entities to delete

object (GoogleCloudAiplatformV1DeleteFeatureValuesResponseSelectTimeRangeAndFeature)

Response for request specifying time range and feature

string (int64 format)

The count of deleted entity rows in the offline storage. Each row corresponds to the combination of an entity ID and a timestamp. One entity ID can have multiple rows in the offline storage.

string (int64 format)

The count of deleted entities in the online storage. Each entity ID corresponds to one entity.

string (int64 format)

The count of the features or columns impacted. This is the same as the feature count in the request.

string (int64 format)

The count of modified entity rows in the offline storage. Each row corresponds to the combination of an entity ID and a timestamp. One entity ID can have multiple rows in the offline storage. Within each row, only the features specified in the request are deleted.

string (int64 format)

The count of modified entities in the online storage. Each entity ID corresponds to one entity. Within each entity, only the features specified in the request are deleted.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for deleting a MetadataStore.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The common part of the operation metadata.

string

The unique index id specified by user

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The operation generic information.

object (GoogleCloudAiplatformV1DeployedIndex)

Required. The DeployedIndex to be created within the IndexEndpoint.

object (GoogleCloudAiplatformV1DeployedIndex)

The DeployedIndex that had been deployed in the IndexEndpoint.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The operation generic information.

object (GoogleCloudAiplatformV1DeployedModel)

Required. The DeployedModel to be created within the Endpoint. Note that Endpoint.traffic_split must be updated for the DeployedModel to start receiving traffic, either as part of this call, or via EndpointService.UpdateEndpoint.

map (key: string, value: integer (int32 format))

A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If this field is non-empty, then the Endpoint's traffic_split will be overwritten with it. To refer to the ID of the just being deployed Model, a "0" should be used, and the actual ID of the new DeployedModel will be filled in its place by this method. The traffic percentage values must add up to 100. If this field is empty, then the Endpoint's traffic_split is not updated.

object (GoogleCloudAiplatformV1DeployedModel)

The DeployedModel that had been deployed in the Endpoint.

object (GoogleCloudAiplatformV1AutomaticResources)

Optional. A description of resources that the DeployedIndex uses, which to large degree are decided by Vertex AI, and optionally allows only a modest additional configuration. If min_replica_count is not set, the default value is 2 (we don't provide SLA when min_replica_count=1). If max_replica_count is not set, the default value is min_replica_count. The max allowed replica count is 1000.

string (Timestamp format)

Output only. Timestamp when the DeployedIndex was created.

object (GoogleCloudAiplatformV1DedicatedResources)

Optional. A description of resources that are dedicated to the DeployedIndex, and that need a higher degree of manual configuration. The field min_replica_count must be set to a value strictly greater than 0, or else validation will fail. We don't provide SLA when min_replica_count=1. If max_replica_count is not set, the default value is min_replica_count. The max allowed replica count is 1000. Available machine types for SMALL shard: e2-standard-2 and all machine types available for MEDIUM and LARGE shard. Available machine types for MEDIUM shard: e2-standard-16 and all machine types available for LARGE shard. Available machine types for LARGE shard: e2-highmem-16, n2d-standard-32. n1-standard-16 and n1-standard-32 are still available, but we recommend e2-standard-16 and e2-highmem-16 for cost efficiency.

object (GoogleCloudAiplatformV1DeployedIndexAuthConfig)

Optional. If set, the authentication is enabled for the private endpoint.

string

Optional. The deployment group can be no longer than 64 characters (eg: 'test', 'prod'). If not set, we will use the 'default' deployment group. Creating deployment_groups with reserved_ip_ranges is a recommended practice when the peered network has multiple peering ranges. This creates your deployments from predictable IP spaces for easier traffic administration. Also, one deployment_group (except 'default') can only be used with the same reserved_ip_ranges which means if the deployment_group has been used with reserved_ip_ranges: [a, b, c], using it with [a, b] or [d, e] is disallowed. Note: we only support up to 5 deployment groups(not including 'default').

string

The display name of the DeployedIndex. If not provided upon creation, the Index's display_name is used.

boolean

Optional. If true, private endpoint's access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each MatchRequest. Note that logs may incur a cost, especially if the deployed index receives a high queries per second rate (QPS). Estimate your costs before enabling this option.

string

Required. The user specified ID of the DeployedIndex. The ID can be up to 128 characters long and must start with a letter and only contain letters, numbers, and underscores. The ID must be unique within the project it is created in.

string

Required. The name of the Index this is the deployment of. We may refer to this Index as the DeployedIndex's "original" Index.

string (Timestamp format)

Output only. The DeployedIndex may depend on various data on its original Index. Additionally when certain changes to the original Index are being done (e.g. when what the Index contains is being changed) the DeployedIndex may be asynchronously updated in the background to reflect these changes. If this timestamp's value is at least the Index.update_time of the original Index, it means that this DeployedIndex and the original Index are in sync. If this timestamp is older, then to see which updates this DeployedIndex already contains (and which it does not), one must list the operations that are running on the original Index. Only the successfully completed Operations with update_time equal or before this sync time are contained in this DeployedIndex.

object (GoogleCloudAiplatformV1IndexPrivateEndpoints)

Output only. Provides paths for users to send requests directly to the deployed index services running on Cloud via private services access. This field is populated if network is configured.

string

Optional. A list of reserved ip ranges under the VPC network that can be used for this DeployedIndex. If set, we will deploy the index within the provided ip ranges. Otherwise, the index might be deployed to any ip ranges under the provided VPC network. The value should be the name of the address (https://cloud.google.com/compute/docs/reference/rest/v1/addresses) Example: ['vertex-ai-ip-range']. For more information about subnets and network IP ranges, please see https://cloud.google.com/vpc/docs/subnets#manually_created_subnet_ip_ranges.

object (GoogleCloudAiplatformV1DeployedIndexAuthConfigAuthProvider)

Defines the authentication provider that the DeployedIndex uses.

string

A list of allowed JWT issuers. Each entry must be a valid Google service account, in the following format: service-account-name@project-id.iam.gserviceaccount.com

string

The list of JWT audiences. that are allowed to access. A JWT containing any of these audiences will be accepted.

string

Immutable. The ID of the DeployedIndex in the above IndexEndpoint.

string

Output only. The display name of the DeployedIndex.

string

Immutable. A resource name of the IndexEndpoint.

object (GoogleCloudAiplatformV1AutomaticResources)

A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.

string (Timestamp format)

Output only. Timestamp when the DeployedModel was created.

object (GoogleCloudAiplatformV1DedicatedResources)

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

boolean

For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true.

boolean

If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.

string

The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.

boolean

If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.

object (GoogleCloudAiplatformV1ExplanationSpec)

Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.

string

Immutable. The ID of the DeployedModel. If not provided upon deployment, Vertex AI will generate a value for this ID. This value should be 1-10 characters, and valid characters are /[0-9]/.

string

Required. The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: projects/{project}/locations/{location}/models/{model}@2 or projects/{project}/locations/{location}/models/{model}@golden if no version is specified, the default version will be deployed.

string

Output only. The version ID of the model that is deployed.

object (GoogleCloudAiplatformV1PrivateEndpoints)

Output only. Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.

string

The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the iam.serviceAccounts.actAs permission on this service account.

string

The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}

string

Immutable. An ID of a DeployedModel in the above Endpoint.

string

Immutable. A resource name of an Endpoint.

string (Timestamp format)

Output only. Timestamp when this DeploymentResourcePool was created.

object (GoogleCloudAiplatformV1DedicatedResources)

Required. The underlying DedicatedResources that the DeploymentResourcePool uses.

string

Immutable. The resource name of the DeploymentResourcePool. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}

string

Specify the field name in the export destination. If not specified, Feature ID is used.

string

Required. The ID of the Feature to apply the setting to.

object (GoogleCloudAiplatformV1Tensor)

The prediction input.

object (GoogleCloudAiplatformV1Tensor)

The parameters that govern the prediction.

object (GoogleCloudAiplatformV1Tensor)

The prediction output.

object (GoogleCloudAiplatformV1Tensor)

The parameters that govern the prediction.

string (bytes format)

The prediction input.

string

Fully qualified name of the API method being invoked to perform predictions. Format: /namespace.Service/Method/ Example: /tensorflow.serving.PredictionService/Predict

string (bytes format)

The prediction output.

integer (int32 format)

Size in GB of the boot disk (default is 100GB).

string

Type of the boot disk (default is "pd-ssd"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).

number (double format)

A list of double values.

string

Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.

string (Timestamp format)

Output only. Timestamp when this Endpoint was created.

object (GoogleCloudAiplatformV1DeployedModel)

Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.

string

The description of the Endpoint.

string

Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.

boolean

Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

object (GoogleCloudAiplatformV1EncryptionSpec)

Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.

string

Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.

string

Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}

string

Output only. The resource name of the Endpoint.

string

Optional. The full name of the Google Compute Engine network to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. Format: projects/{project}/global/networks/{network}. Where {project} is a project number, as in 12345, and {network} is network name.

object (GoogleCloudAiplatformV1PredictRequestResponseLoggingConfig)

Configures the request-response logging for online prediction.

object (GoogleCloudAiplatformV1PrivateServiceConnectConfig)

Optional. Configuration for private service connect. network and private_service_connect_config are mutually exclusive.

map (key: string, value: integer (int32 format))

A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.

string (Timestamp format)

Output only. Timestamp when this Endpoint was last updated.

object (GoogleCloudAiplatformV1CsvSource)

Source of Csv

string

Source column that holds entity IDs. If not provided, entity IDs are extracted from the column named entity_id.

string (Timestamp format)

Output only. Timestamp when this EntityType was created.

string

Optional. Description of the EntityType.

string

Optional. Used to perform a consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

Optional. The labels with user-defined metadata to organize your EntityTypes. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one EntityType (System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable.

object (GoogleCloudAiplatformV1FeaturestoreMonitoringConfig)

Optional. The default monitoring configuration for all Features with value type (Feature.ValueType) BOOL, STRING, DOUBLE or INT64 under this EntityType. If this is populated with [FeaturestoreMonitoringConfig.monitoring_interval] specified, snapshot analysis monitoring is enabled. Otherwise, snapshot analysis monitoring is disabled.

string

Immutable. Name of the EntityType. Format: projects/{project}/locations/{location}/featurestores/{featurestore}/entityTypes/{entity_type} The last part entity_type is assigned by the client. The entity_type can be up to 64 characters long and can consist only of ASCII Latin letters A-Z and a-z and underscore(_), and ASCII digits 0-9 starting with a letter. The value will be unique given a featurestore.

integer (int32 format)

Optional. Config for data retention policy in offline storage. TTL in days for feature values that will be stored in offline storage. The Feature Store offline storage periodically removes obsolete feature values older than offline_storage_ttl_days since the feature generation time. If unset (or explicitly set to 0), default to 4000 days TTL.

string (Timestamp format)

Output only. Timestamp when this EntityType was most recently updated.

string

Required. Name of the environment variable. Must be a valid C identifier.

string

Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.

object (GoogleCloudAiplatformV1ErrorAnalysisAnnotationAttributedItem)

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

number (double format)

The outlier score of this annotated item. Usually defined as the min of all distances from attributed items.

number (double format)

The threshold used to determine if this annotation is an outlier or not.

enum

The query type used for finding the attributed items.

string

The unique ID for each annotation. Used by FE to allocate the annotation in DB.

number (double format)

The distance of this item to the annotation.

any

Output only. The data item payload that the Model predicted this EvaluatedAnnotation on.

object (GoogleCloudAiplatformV1ErrorAnalysisAnnotation)

Annotations of model error analysis results.

string

Output only. ID of the EvaluatedDataItemView under the same ancestor ModelEvaluation. The EvaluatedDataItemView consists of all ground truths and predictions on data_item_payload.

object (GoogleCloudAiplatformV1EvaluatedAnnotationExplanation)

Explanations of predictions. Each element of the explanations indicates the explanation for one explanation Method. The attributions list in the EvaluatedAnnotationExplanation.explanation object corresponds to the predictions list. For example, the second element in the attributions list explains the second element in the predictions list.

any

Output only. The ground truth Annotations, i.e. the Annotations that exist in the test data the Model is evaluated on. For true positive, there is one and only one ground truth annotation, which matches the only prediction in predictions. For false positive, there are zero or more ground truth annotations that are similar to the only prediction in predictions, but not enough for a match. For false negative, there is one and only one ground truth annotation, which doesn't match any predictions created by the model. The schema of the ground truth is stored in ModelEvaluation.annotation_schema_uri

any

Output only. The model predicted annotations. For true positive, there is one and only one prediction, which matches the only one ground truth annotation in ground_truths. For false positive, there is one and only one prediction, which doesn't match any ground truth annotation of the corresponding data_item_view_id. For false negative, there are zero or more predictions which are similar to the only ground truth annotation in ground_truths but not enough for a match. The schema of the prediction is stored in ModelEvaluation.annotation_schema_uri

enum

Output only. Type of the EvaluatedAnnotation.

object (GoogleCloudAiplatformV1Explanation)

Explanation attribution response details.

string

Explanation type. For AutoML Image Classification models, possible values are: * image-integrated-gradients * image-xrai

string

Required. The relative resource name of the Artifact in the Event.

string (Timestamp format)

Output only. Time the Event occurred.

string

Output only. The relative resource name of the Execution in the Event.

map (key: string, value: string)

The labels with user-defined metadata to annotate Events. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Event (System labels are excluded). See https://goo.gl/xmQnxf for more information and examples of labels. System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable.

enum

Required. The type of the Event.

object (GoogleCloudAiplatformV1ExamplesExampleGcsSource)

The Cloud Storage input instances.

any

The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.

integer (int32 format)

The number of neighbors to return when querying for examples.

object (GoogleCloudAiplatformV1Presets)

Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.

enum

The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.

object (GoogleCloudAiplatformV1GcsSource)

The Cloud Storage location for the input instances.

integer (int32 format)

The number of neighbors to return that have the same crowding tag.

enum

The format of the data being provided with each call.

integer (int32 format)

The number of neighbors to return.

object (GoogleCloudAiplatformV1ExamplesRestrictionsNamespace)

Restrict the resulting nearest neighbors to respect these constraints.

boolean

If true, return the embeddings instead of neighbors.

string

The list of allowed tags.

string

The list of deny tags.

string

The namespace name.

string (Timestamp format)

Output only. Timestamp when this Execution was created.

string

Description of the Execution

string

User provided display name of the Execution. May be up to 128 Unicode characters.

string

An eTag used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

The labels with user-defined metadata to organize your Executions. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. No more than 64 user labels can be associated with one Execution (System labels are excluded).

map (key: string, value: any)

Properties of the Execution. Top level metadata keys' heading and trailing spaces will be trimmed. The size of this field should not exceed 200KB.

string

Output only. The resource name of the Execution.

string

The title of the schema describing the metadata. Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store.

string

The version of the schema in schema_title to use. Schema title and version is expected to be registered in earlier Create Schema calls. And both are used together as unique identifiers to identify schemas within the local metadata store.

enum

The state of this Execution. This is a property of the Execution, and does not imply or capture any ongoing process. This property is managed by clients (such as Vertex AI Pipelines) and the system does not prescribe or check the validity of state transitions.

string (Timestamp format)

Output only. Timestamp when this Execution was last updated.

string

If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.

object (GoogleCloudAiplatformV1ExplanationSpecOverride)

If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as: - Explaining top-5 predictions results as opposed to top-1; - Increasing path count or step count of the attribution methods to reduce approximate errors; - Using different baselines for explaining the prediction results.

any

Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

any

The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.

string

ID of the Endpoint's DeployedModel that served this explanation.

object (GoogleCloudAiplatformV1Explanation)

The explanations of the Model's PredictResponse.predictions. It has the same number of elements as instances to be explained.

any

The predictions that are the output of the predictions call. Same as PredictResponse.predictions.

object (GoogleCloudAiplatformV1Attribution)

Output only. Feature attributions grouped by predicted outputs. For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining. By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class. If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

object (GoogleCloudAiplatformV1Neighbor)

Output only. List of the nearest neighbors for example-based explanations. For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

string

Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.

map (key: string, value: object (GoogleCloudAiplatformV1ExplanationMetadataInputMetadata))

Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.

string

Name of the source to generate embeddings for example based explanations.

map (key: string, value: object (GoogleCloudAiplatformV1ExplanationMetadataOutputMetadata))

Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.

string

Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.

any

A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.

string

Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.

enum

Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.

object (GoogleCloudAiplatformV1ExplanationMetadataInputMetadataFeatureValueDomain)

The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.

string

Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.

string

A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.

string

Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.

any

Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

string

Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.

string

Modality of the feature. Valid values are: numeric, image. Defaults to numeric.

object (GoogleCloudAiplatformV1ExplanationMetadataInputMetadataVisualization)

Visualization configurations for image explanation.

number (float format)

The maximum permissible value for this feature.

number (float format)

The minimum permissible value for this feature.

number (float format)

If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.

number (float format)

If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.

number (float format)

Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.

number (float format)

Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.

enum

The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.

enum

How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.

enum

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

enum

Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.

string

Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.

any

Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.

string

Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.

map (key: string, value: object (GoogleCloudAiplatformV1ExplanationMetadataOverrideInputMetadataOverride))

Required. Overrides the input metadata of the features. The key is the name of the feature to be overridden. The keys specified here must exist in the input metadata to be overridden. If a feature is not specified here, the corresponding feature's input metadata is not overridden.

any

Baseline inputs for this feature. This overrides the input_baseline field of the ExplanationMetadata.InputMetadata object of the corresponding feature's input metadata. If it's not specified, the original baselines are not overridden.

object (GoogleCloudAiplatformV1Examples)

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

object (GoogleCloudAiplatformV1IntegratedGradientsAttribution)

An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365

any

If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).

object (GoogleCloudAiplatformV1SampledShapleyAttribution)

An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.

integer (int32 format)

If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.

object (GoogleCloudAiplatformV1XraiAttribution)

An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.

object (GoogleCloudAiplatformV1ExplanationMetadata)

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

object (GoogleCloudAiplatformV1ExplanationParameters)

Required. Parameters that configure explaining of the Model's predictions.

object (GoogleCloudAiplatformV1ExamplesOverride)

The example-based explanations parameter overrides.

object (GoogleCloudAiplatformV1ExplanationMetadataOverride)

The metadata to be overridden. If not specified, no metadata is overridden.

object (GoogleCloudAiplatformV1ExplanationParameters)

The parameters to be overridden. Note that the attribution method cannot be changed. If not specified, no parameter is overridden.

string

The Cloud Storage URI that points to a YAML file describing the annotation schema. The schema is defined as an OpenAPI 3.0.2 Schema Object. The schema files that can be used here are found in gs://google-cloud-aiplatform/schema/dataset/annotation/, note that the chosen schema must be consistent with metadata of the Dataset specified by dataset_id. Only used for custom training data export use cases. Only applicable to Datasets that have DataItems and Annotations. Only Annotations that both match this schema and belong to DataItems not ignored by the split method are used in respectively training, validation or test role, depending on the role of the DataItem they are on. When used in conjunction with annotations_filter, the Annotations used for training are filtered by both annotations_filter and annotation_schema_uri.

string

An expression for filtering what part of the Dataset is to be exported. Only Annotations that match this filter will be exported. The filter syntax is the same as in ListAnnotations.

enum

Indicates the usage of the exported files.

object (GoogleCloudAiplatformV1ExportFilterSplit)

Split based on the provided filters for each set.

object (GoogleCloudAiplatformV1ExportFractionSplit)

Split based on fractions defining the size of each set.

object (GoogleCloudAiplatformV1GcsDestination)

The Google Cloud Storage location where the output is to be written to. In the given directory a new directory will be created with name: export-data-- where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. All export output will be written into that directory. Inside that directory, annotations with the same schema will be grouped into sub directories which are named with the corresponding annotations' schema title. Inside these sub directories, a schema.yaml will be created to describe the output format.

string

The ID of a SavedQuery (annotation set) under the Dataset specified by dataset_id used for filtering Annotations for training. Only used for custom training data export use cases. Only applicable to Datasets that have SavedQueries. Only Annotations that are associated with this SavedQuery are used in respectively training. When used in conjunction with annotations_filter, the Annotations used for training are filtered by both saved_query_id and annotations_filter. Only one of saved_query_id and annotation_schema_uri should be specified as both of them represent the same thing: problem type.

string

A Google Cloud Storage directory which path ends with '/'. The exported data is stored in the directory.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The common part of the operation metadata.

object (GoogleCloudAiplatformV1ExportDataConfig)

Required. The desired output location.

object (GoogleCloudAiplatformV1ModelDataStats)

Only present for custom code training export use case. Records data stats, i.e., train/validation/test item/annotation counts calculated during the export operation.

string

All of the files that are exported in this export operation. For custom code training export, only three (training, validation and test) Cloud Storage paths in wildcard format are populated (for example, gs://.../training-*).

object (GoogleCloudAiplatformV1GenericOperationMetadata)

Operation metadata for Featurestore export Feature values.

object (GoogleCloudAiplatformV1FeatureValueDestination)

Required. Specifies destination location and format.

object (GoogleCloudAiplatformV1FeatureSelector)

Required. Selects Features to export values of.

object (GoogleCloudAiplatformV1ExportFeatureValuesRequestFullExport)

Exports all historical values of all entities of the EntityType within a time range

object (GoogleCloudAiplatformV1DestinationFeatureSetting)

Per-Feature export settings.

object (GoogleCloudAiplatformV1ExportFeatureValuesRequestSnapshotExport)

Exports the latest Feature values of all entities of the EntityType within a time range.

string (Timestamp format)

Exports Feature values as of this timestamp. If not set, retrieve values as of now. Timestamp, if present, must not have higher than millisecond precision.

string (Timestamp format)

Excludes Feature values with feature generation timestamp before this timestamp. If not set, retrieve oldest values kept in Feature Store. Timestamp, if present, must not have higher than millisecond precision.

string (Timestamp format)

Exports Feature values as of this timestamp. If not set, retrieve values as of now. Timestamp, if present, must not have higher than millisecond precision.

string (Timestamp format)

Excludes Feature values with feature generation timestamp before this timestamp. If not set, retrieve oldest values kept in Feature Store. Timestamp, if present, must not have higher than millisecond precision.

string

Required. A filter on DataItems of the Dataset. DataItems that match this filter are used to test the Model. A filter with same syntax as the one used in DatasetService.ListDataItems may be used. If a single DataItem is matched by more than one of the FilterSplit filters, then it is assigned to the first set that applies to it in the training, validation, test order.

string

Required. A filter on DataItems of the Dataset. DataItems that match this filter are used to train the Model. A filter with same syntax as the one used in DatasetService.ListDataItems may be used. If a single DataItem is matched by more than one of the FilterSplit filters, then it is assigned to the first set that applies to it in the training, validation, test order.

string

Required. A filter on DataItems of the Dataset. DataItems that match this filter are used to validate the Model. A filter with same syntax as the one used in DatasetService.ListDataItems may be used. If a single DataItem is matched by more than one of the FilterSplit filters, then it is assigned to the first set that applies to it in the training, validation, test order.

number (double format)

The fraction of the input data that is to be used to evaluate the Model.

number (double format)

The fraction of the input data that is to be used to train the Model.

number (double format)

The fraction of the input data that is to be used to validate the Model.

object (GoogleCloudAiplatformV1GenericOperationMetadata)

The common part of the operation metadata.

object (GoogleCloudAiplatformV1ExportModelOperationMetadataOutputInfo)

Output only. Information further describing the output of this Model export.

string

Output only. If the Model artifact is being exported to Google Cloud Storage this is the full path of the directory created, into which the Model files are being written to.

string

Output only. If the Model image is being exported to Google Container Registry or Artifact Registry this is the full path of the image created.

object (GoogleCloudAiplatformV1ExportModelRequestOutputConfig)

Required. The desired output location and configuration.

object (GoogleCloudAiplatformV1GcsDestination)

The Cloud Storage location where the Model artifact is to be written to. Under the directory given as the destination a new one with name "model-export--", where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format, will be created. Inside, the Model and any of its supporting files will be written. This field should only be set when the exportableContent field of the [Model.supported_export_formats] object contains ARTIFACT.

string

The ID of the format in which the Model must be exported. Each Model lists the export formats it supports. If no value is provided here, then the first from the list of the Model's supported formats is used by default.

object (GoogleCloudAiplatformV1ContainerRegistryDestination)

The Google Container Registry or Artifact Registry uri where the Model container image will be copied to. This field should only be set when the exportableContent field of the [Model.supported_export_formats] object contains IMAGE.

string

Exports the TensorboardTimeSeries' data that match the filter expression.

string

Field to use to sort the TensorboardTimeSeries' data. By default, TensorboardTimeSeries' data is returned in a pseudo random order.

integer (int32 format)

The maximum number of data points to return per page. The default page_size is 1000. Values must be between 1 and 10000. Values above 10000 are coerced to 10000.

string

A page token, received from a previous ExportTensorboardTimeSeriesData call. Provide this to retrieve the subsequent page. When paginating, all other parameters provided to ExportTensorboardTimeSeriesData must match the call that provided the page token.

string

A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

object (GoogleCloudAiplatformV1TimeSeriesDataPoint)

The returned time series data points.

string (Timestamp format)

Output only. Only applicable for Vertex AI Feature Store (Legacy). Timestamp when this EntityType was created.

string

Description of the Feature.

boolean

Optional. Only applicable for Vertex AI Feature Store (Legacy). If not set, use the monitoring_config defined for the EntityType this Feature belongs to. Only Features with type (Feature.ValueType) BOOL, STRING, DOUBLE or INT64 can enable monitoring. If set to true, all types of data monitoring are disabled despite the config on EntityType.

string

Used to perform a consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

Optional. The labels with user-defined metadata to organize your Features. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one Feature (System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable.

object (GoogleCloudAiplatformV1FeatureMonitoringStatsAnomaly)

Output only. Only applicable for Vertex AI Feature Store (Legacy). The list of historical stats and anomalies with specified objectives.

string

Immutable. Name of the Feature. Format: projects/{project}/locations/{location}/featurestores/{featurestore}/entityTypes/{entity_type}/features/{feature} projects/{project}/locations/{location}/featureGroups/{feature_group}/features/{feature} The last part feature is assigned by the client. The feature can be up to 64 characters long and can consist only of ASCII Latin letters A-Z and a-z, underscore(_), and ASCII digits 0-9 starting with a letter. The value will be unique given an entity type.

string

Entity responsible for maintaining this feature. Can be comma separated list of email addresses or URIs.

string (Timestamp format)

Output only. Only applicable for Vertex AI Feature Store (Legacy). Timestamp when this EntityType was most recently updated.

enum

Immutable. Only applicable for Vertex AI Feature Store (Legacy). Type of Feature value.

string

Only applicable for Vertex AI Feature Store. The name of the BigQuery Table/View column hosting data for this version. If no value is provided, will use feature_id.

object (GoogleCloudAiplatformV1FeatureGroupBigQuery)

Indicates that features for this group come from BigQuery Table/View. By default treats the source as a sparse time series source. The BigQuery source table or view must have at least one entity ID column and a column named feature_timestamp.

string (Timestamp format)

Output only. Timestamp when this FeatureGroup was created.

string

Optional. Description of the FeatureGroup.

string

Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

Optional. The labels with user-defined metadata to organize your FeatureGroup. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one FeatureGroup(System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable.

string

Identifier. Name of the FeatureGroup. Format: projects/{project}/locations/{location}/featureGroups/{featureGroup}

string (Timestamp format)

Output only. Timestamp when this FeatureGroup was last updated.

object (GoogleCloudAiplatformV1BigQuerySource)

Required. Immutable. The BigQuery source URI that points to either a BigQuery Table or View.

string

Optional. Columns to construct entity_id / row keys. If not provided defaults to entity_id.

object (GoogleCloudAiplatformV1FeatureStatsAnomaly)

Output only. The stats and anomalies generated at specific timestamp.

enum

Output only. The objective for each stats.

object (GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeature)

Noise sigma per feature. No noise is added to features that are not set.

string

The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.

number (float format)

This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.

object (GoogleCloudAiplatformV1FeatureOnlineStoreBigtable)

Contains settings for the Cloud Bigtable instance that will be created to serve featureValues for all FeatureViews under this FeatureOnlineStore.

string (Timestamp format)

Output only. Timestamp when this FeatureOnlineStore was created.

object (GoogleCloudAiplatformV1FeatureOnlineStoreDedicatedServingEndpoint)

Optional. The dedicated serving endpoint for this FeatureOnlineStore, which is different from common Vertex service endpoint.

string

Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

Optional. The labels with user-defined metadata to organize your FeatureOnlineStore. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one FeatureOnlineStore(System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable.

string

Identifier. Name of the FeatureOnlineStore. Format: projects/{project}/locations/{location}/featureOnlineStores/{featureOnlineStore}

object (GoogleCloudAiplatformV1FeatureOnlineStoreOptimized)

Contains settings for the Optimized store that will be created to serve featureValues for all FeatureViews under this FeatureOnlineStore. When choose Optimized storage type, need to set PrivateServiceConnectConfig.enable_private_service_connect to use private endpoint. Otherwise will use public endpoint by default.

enum

Output only. State of the featureOnlineStore.

string (Timestamp format)

Output only. Timestamp when this FeatureOnlineStore was last updated.

object (GoogleCloudAiplatformV1FeatureOnlineStoreBigtableAutoScaling)

Required. Autoscaling config applied to Bigtable Instance.

integer (int32 format)

Optional. A percentage of the cluster's CPU capacity. Can be from 10% to 80%. When a cluster's CPU utilization exceeds the target that you have set, Bigtable immediately adds nodes to the cluster. When CPU utilization is substantially lower than the target, Bigtable removes nodes. If not set will default to 50%.

integer (int32 format)

Required. The maximum number of nodes to scale up to. Must be greater than or equal to min_node_count, and less than or equal to 10 times of 'min_node_count'.

integer (int32 format)

Required. The minimum number of nodes to scale down to. Must be greater than or equal to 1.

string

Output only. This field will be populated with the domain name to use for this FeatureOnlineStore

object (GoogleCloudAiplatformV1IdMatcher)

Required. Matches Features based on ID.

number (double format)

This is the threshold used when detecting anomalies. The threshold can be changed by user, so this one might be different from ThresholdConfig.value.

string

Path of the anomaly file for current feature values in Cloud Storage bucket. Format: gs:////anomalies. Example: gs://monitoring_bucket/feature_name/anomalies. Stats are stored as binary format with Protobuf message Anoamlies are stored as binary format with Protobuf message tensorflow.metadata.v0.AnomalyInfo.

number (double format)

Deviation from the current stats to baseline stats. 1. For categorical feature, the distribution distance is calculated by L-inifinity norm. 2. For numerical feature, the distribution distance is calculated by Jensen–Shannon divergence.

string (Timestamp format)

The end timestamp of window where stats were generated. For objectives where time window doesn't make sense (e.g. Featurestore Snapshot Monitoring), end_time indicates the timestamp of the data used to generate stats (e.g. timestamp we take snapshots for feature values).

number (double format)

Feature importance score, only populated when cross-feature monitoring is enabled. For now only used to represent feature attribution score within range [0, 1] for ModelDeploymentMonitoringObjectiveType.FEATURE_ATTRIBUTION_SKEW and ModelDeploymentMonitoringObjectiveType.FEATURE_ATTRIBUTION_DRIFT.

string (Timestamp format)

The start timestamp of window where stats were generated. For objectives where time window doesn't make sense (e.g. Featurestore Snapshot Monitoring), start_time is only used to indicate the monitoring intervals, so it always equals to (end_time - monitoring_interval).

string

Path of the stats file for current feature values in Cloud Storage bucket. Format: gs:////stats. Example: gs://monitoring_bucket/feature_name/stats. Stats are stored as binary format with Protobuf message tensorflow.metadata.v0.FeatureNameStatistics.

object (GoogleCloudAiplatformV1BoolArray)

A list of bool type feature value.

boolean

Bool type feature value.

string (bytes format)

Bytes feature value.

object (GoogleCloudAiplatformV1DoubleArray)

A list of double type feature value.

number (double format)

Double type feature value.

object (GoogleCloudAiplatformV1Int64Array)

A list of int64 type feature value.

string (int64 format)

Int64 feature value.

object (GoogleCloudAiplatformV1FeatureValueMetadata)

Metadata of feature value.

object (GoogleCloudAiplatformV1StringArray)

A list of string type feature value.

string

String feature value.

object (GoogleCloudAiplatformV1BigQueryDestination)

Output in BigQuery format. BigQueryDestination.output_uri in FeatureValueDestination.bigquery_destination must refer to a table.

object (GoogleCloudAiplatformV1CsvDestination)

Output in CSV format. Array Feature value types are not allowed in CSV format.

object (GoogleCloudAiplatformV1TFRecordDestination)

Output in TFRecord format. Below are the mapping from Feature value type in Featurestore to Feature value type in TFRecord: Value type in Featurestore | Value type in TFRecord DOUBLE, DOUBLE_ARRAY | FLOAT_LIST INT64, INT64_ARRAY | INT64_LIST STRING, STRING_ARRAY, BYTES | BYTES_LIST true -> byte_string("true"), false -> byte_string("false") BOOL, BOOL_ARRAY (true, false) | BYTES_LIST

object (GoogleCloudAiplatformV1FeatureValue)

A list of feature values. All of them should be the same data type.

string (Timestamp format)

Feature generation timestamp. Typically, it is provided by user at feature ingestion time. If not, feature store will use the system timestamp when the data is ingested into feature store. For streaming ingestion, the time, aligned by days, must be no older than five years (1825 days) and no later than one year (366 days) in the future.

object (GoogleCloudAiplatformV1FeatureViewBigQuerySource)

Optional. Configures how data is supposed to be extracted from a BigQuery source to be loaded onto the FeatureOnlineStore.

string (Timestamp format)

Output only. Timestamp when this FeatureView was created.

string

Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

object (GoogleCloudAiplatformV1FeatureViewFeatureRegistrySource)

Optional. Configures the features from a Feature Registry source that need to be loaded onto the FeatureOnlineStore.

object (GoogleCloudAiplatformV1FeatureViewIndexConfig)

Optional. Configuration for index preparation for vector search. It contains the required configurations to create an index from source data, so that approximate nearest neighbor (a.k.a ANN) algorithms search can be performed during online serving.

map (key: string, value: string)

Optional. The labels with user-defined metadata to organize your FeatureViews. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one FeatureOnlineStore(System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable.

string

Identifier. Name of the FeatureView. Format: projects/{project}/locations/{location}/featureOnlineStores/{feature_online_store}/featureViews/{feature_view}

object (GoogleCloudAiplatformV1FeatureViewSyncConfig)

Configures when data is to be synced/updated for this FeatureView. At the end of the sync the latest featureValues for each entityId of this FeatureView are made ready for online serving.

string (Timestamp format)

Output only. Timestamp when this FeatureView was last updated.

string

Required. Columns to construct entity_id / row keys.

string

Required. The BigQuery view URI that will be materialized on each sync trigger based on FeatureView.SyncConfig.

object (GoogleCloudAiplatformV1FeatureViewDataKeyCompositeKey)

The actual Entity ID will be composed from this struct. This should match with the way ID is defined in the FeatureView spec.

string

String key to use for lookup.

string

Parts to construct Entity ID. Should match with the same ID columns as defined in FeatureView in the same order.

object (GoogleCloudAiplatformV1FeatureViewFeatureRegistrySourceFeatureGroup)

Required. List of features that need to be synced to Online Store.

string (int64 format)

Optional. The project number of the parent project of the Feature Groups.

string

Required. Identifier of the feature group.

string

Required. Identifiers of features under the feature group.

object (GoogleCloudAiplatformV1FeatureViewIndexConfigBruteForceConfig)

Optional. Configuration options for using brute force search, which simply implements the standard linear search in the database for each query. It is primarily meant for benchmarking and to generate the ground truth for approximate search.

string

Optional. Column of crowding. This column contains crowding attribute which is a constraint on a neighbor list produced by FeatureOnlineStoreService.SearchNearestEntities to diversify search results. If NearestNeighborQuery.per_crowding_attribute_neighbor_count is set to K in SearchNearestEntitiesRequest, it's guaranteed that no more than K entities of the same crowding attribute are returned in the response.

enum

Optional. The distance measure used in nearest neighbor search.

string

Optional. Column of embedding. This column contains the source data to create index for vector search. embedding_column must be set when using vector search.

integer (int32 format)

Optional. The number of dimensions of the input embedding.

string

Optional. Columns of features that're used to filter vector search results.

object (GoogleCloudAiplatformV1FeatureViewIndexConfigTreeAHConfig)

Optional. Configuration options for the tree-AH algorithm (Shallow tree + Asymmetric Hashing). Please refer to this paper for more details: https://arxiv.org/abs/1908.10396

string (int64 format)

Optional. Number of embeddings on each leaf node. The default value is 1000 if not set.

string (Timestamp format)

Output only. Time when this FeatureViewSync is created. Creation of a FeatureViewSync means that the job is pending / waiting for sufficient resources but may not have started the actual data transfer yet.

object (GoogleRpcStatus)

Output only. Final status of the FeatureViewSync.

string

Identifier. Name of the FeatureViewSync. Format: projects/{project}/locations/{location}/featureOnlineStores/{feature_online_store}/featureViews/{feature_view}/featureViewSyncs/{feature_view_sync}

object (GoogleTypeInterval)

Output only. Time when this FeatureViewSync is finished.

object (GoogleCloudAiplatformV1FeatureViewSyncSyncSummary)

Output only. Summary of the sync job.

string

Cron schedule (https://en.wikipedia.org/wiki/Cron) to launch scheduled runs. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: "CRON_TZ=${IANA_TIME_ZONE}" or "TZ=${IANA_TIME_ZONE}". The ${IANA_TIME_ZONE} may only be a valid string from IANA time zone database. For example, "CRON_TZ=America/New_York 1 * * * ", or "TZ=America/New_York 1 * * * ".

string (int64 format)

Output only. Total number of rows synced.

string (int64 format)

Output only. BigQuery slot milliseconds consumed for the sync job.

string (Timestamp format)

Output only. Timestamp when this Featurestore was created.

object (GoogleCloudAiplatformV1EncryptionSpec)

Optional. Customer-managed encryption key spec for data storage. If set, both of the online and offline data storage will be secured by this key.

string

Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

map (key: string, value: string)

Optional. The labels with user-defined metadata to organize your Featurestore. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information on and examples of labels. No more than 64 user labels can be associated with one Featurestore(System labels are excluded)." System reserved label keys are prefixed with "aiplatform.googleapis.com/" and are immutable.

string

Output only. Name of the Featurestore. Format: projects/{project}/locations/{location}/featurestores/{featurestore}

object (GoogleCloudAiplatformV1FeaturestoreOnlineServingConfig)

Optional. Config for online storage resources. The field should not co-exist with the field of OnlineStoreReplicationConfig. If both of it and OnlineStoreReplicationConfig are unset, the feature store will not have an online store and cannot be used for online serving.

integer (int32 format)

Optional. TTL in days for feature values that will be stored in online serving storage. The Feature Store online storage periodically removes obsolete feature values older than online_storage_ttl_days since the feature generation time. Note that online_storage_ttl_days should be less than or equal to offline_storage_ttl_days for each EntityType under a featurestore. If not set, default to 4000 days

enum

Output only. State of the featurestore.

string (Timestamp format)

Output only. Timestamp when this Featurestore was last updated.

object (GoogleCloudAiplatformV1FeaturestoreMonitoringConfigThresholdConfig)

Threshold for categorical features of anomaly detection. This is shared by all types of Featurestore Monitoring for categorical features (i.e. Features with type (Feature.ValueType) BOOL or STRING).

object (GoogleCloudAiplatformV1FeaturestoreMonitoringConfigImportFeaturesAnalysis)

The config for ImportFeatures Analysis Based Feature Monitoring.

object (GoogleCloudAiplatformV1FeaturestoreMonitoringConfigThresholdConfig)

Threshold for numerical features of anomaly detection. This is shared by all objectives of Featurestore Monitoring for numerical features (i.e. Features with type (Feature.ValueType) DOUBLE or INT64).

object (GoogleCloudAiplatformV1FeaturestoreMonitoringConfigSnapshotAnalysis)

The config for Snapshot Analysis Based Feature Monitoring.

enum

The baseline used to do anomaly detection for the statistics generated by import features analysis.

enum

Whether to enable / disable / inherite default hebavior for import features analysis.

boolean

The monitoring schedule for snapshot analysis. For EntityType-level config: unset / disabled = true indicates disabled by default for Features under it; otherwise by default enable snapshot analysis monitoring with monitoring_interval for Features under it. Feature-level config: disabled = true indicates disabled regardless of the EntityType-level config; unset monitoring_interval indicates going with EntityType-level config; otherwise run snapshot analysis monitoring with monitoring_interval regardless of the EntityType-level config. Explicitly Disable the snapshot analysis based monitoring.

integer (int32 format)

Configuration of the snapshot analysis based monitoring pipeline running interval. The value indicates number of days.

integer (int32 format)

Customized export features time window for snapshot analysis. Unit is one day. Default value is 3 weeks. Minimum value is 1 day. Maximum value is 4000 days.

number (double format)

Specify a threshold value that can trigger the alert. 1. For categorical feature, the distribution distance is calculated by L-inifinity norm. 2. For numerical feature, the distribution distance is calculated by Jensen–Shannon divergence. Each feature must have a non-zero threshold if they need to be monitored. Otherwise no alert will be triggered for that feature.

integer (int32 format)

The number of nodes for the online store. The number of nodes doesn't scale automatically, but you can manually update the number of nodes. If set to 0, the featurestore will not have an online store and cannot be used for online serving.

object (GoogleCloudAiplatformV1FeaturestoreOnlineServingConfigScaling)

Online serving scaling configuration. Only one of fixed_node_count and scaling can be set. Setting one will reset the other.

integer (int32 format)

Optional. The cpu utilization that the Autoscaler should be trying to achieve. This number is on a scale from 0 (no utilization) to 100 (total utilization), and is limited between 10 and 80. When a cluster's CPU utilization exceeds the target that you have set, Bigtable immediately adds nodes to the cluster. When CPU utilization is substantially lower than the target, Bigtable removes nodes. If not set or set to 0, default to 50.

integer (int32 format)

The maximum number of nodes to scale up to. Must be greater than min_node_count, and less than or equal to 10 times of 'min_node_count'.

integer (int32 format)

Required. The minimum number of nodes to scale down to. Must be greater than or equal to 1.

enum

Optional. Response data format. If not set, FeatureViewDataFormat.KEY_VALUE will be used.

object (GoogleCloudAiplatformV1FeatureViewDataKey)

Optional. The request key to fetch feature values for.

object (GoogleCloudAiplatformV1FeatureViewDataKey)

The data key associated with this response. Will only be populated for FeatureOnlineStoreService.StreamingFetchFeatureValues RPCs.

object (GoogleCloudAiplatformV1FetchFeatureValuesResponseFeatureNameValuePairList)

Feature values in KeyValue format.

map (key: string, value: any)

Feature values in proto Struct format.

object (GoogleCloudAiplatformV1FetchFeatureValuesResponseFeatureNameValuePairListFeatureNameValuePair)

List of feature names and values.

string

Feature short name.

object (GoogleCloudAiplatformV1FeatureValue)

Feature value.

string

Required. URI.

string

Required. The IANA standard MIME type of the source data.

string

Required. A filter on DataItems of the Dataset. DataItems that match this filter are used to test the Model. A filter with same syntax as the one used in DatasetService.ListDataItems may be used. If a single DataItem is matched by more than one of the FilterSplit filters, then it is assigned to the first set that applies to it in the training, validation, test order.

string

Required. A filter on DataItems of the Dataset. DataItems that match this filter are used to train the Model. A filter with same syntax as the one used in DatasetService.ListDataItems may be used. If a single DataItem is matched by more than one of the FilterSplit filters, then it is assigned to the first set that applies to it in the training, validation, test order.

string

Required. A filter on DataItems of the Dataset. DataItems that match this filter are used to validate the Model. A filter with same syntax as the one used in DatasetService.ListDataItems may be used. If a single DataItem is matched by more than one of the FilterSplit filters, then it is assigned to the first set that applies to it in the training, validation, test order.

string

The ID of the DeployedIndex that will serve the request. This request is sent to a specific IndexEndpoint, as per the IndexEndpoint.network. That IndexEndpoint also has IndexEndpoint.deployed_indexes, and each such index has a DeployedIndex.id field. The value of the field below must equal one of the DeployedIndex.id fields of the IndexEndpoint that is being called for this request.

object (GoogleCloudAiplatformV1FindNeighborsRequestQuery)

The list of queries.

boolean

If set to true, the full datapoints (including all vector values and restricts) of the nearest neighbors are returned. Note that returning full datapoint will significantly increase the latency and cost of the query.

integer (int32 format)

The number of neighbors to find via approximate search before exact reordering is performed. If not set, the default value from scam config is used; if set, this value must be > 0.

object (GoogleCloudAiplatformV1IndexDatapoint)

Required. The datapoint/vector whose nearest neighbors should be searched for.

number (double format)

The fraction of the number of leaves to search, set at query time allows user to tune search performance. This value increase result in both search accuracy and latency increase. The value should be between 0.0 and 1.0. If not set or set to 0.0, query uses the default value specified in NearestNeighborSearchConfig.TreeAHConfig.fraction_leaf_nodes_to_search.

integer (int32 format)

The number of nearest neighbors to be retrieved from database for each query. If not set, will use the default from the service configuration (https://cloud.google.com/vertex-ai/docs/matching-engine/configuring-indexes#nearest-neighbor-search-config).

integer (int32 format)

Crowding 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. It's used for improving result diversity. This field is the maximum number of matches with the same crowding tag.

object (GoogleCloudAiplatformV1FindNeighborsRequestQueryRRF)

Optional. Represents RRF algorithm that combines search results.

number (float format)

Required. Users can provide an alpha value to give more weight to dense vs sparse results. For example, if the alpha is 0, we only return sparse and if the alpha is 1, we only return dense.

object (GoogleCloudAiplatformV1FindNeighborsResponseNearestNeighbors)

The nearest neighbors of the query datapoints.

string

The ID of the query datapoint.

object (GoogleCloudAiplatformV1FindNeighborsResponseNeighbor)

All its neighbors.

object (GoogleCloudAiplatformV1IndexDatapoint)

The datapoint of the neighbor. Note that full datapoints are returned only when "return_full_datapoint" is set to true. Otherwise, only the "datapoint_id" and "crowding_tag" fields are populated.

number (double format)

The distance between the neighbor and the dense embedding query.

number (double format)

The distance between the neighbor and the query sparse_embedding.

number (double format)

The fraction of the input data that is to be used to evaluate the Model.

number (double format)

The fraction of the input data that is to be used to train the Model.

number (double format)

The fraction of the input data that is to be used to validate the Model.

map (key: string, value: any)

Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.

string

Required. The name of the function to call. Matches [FunctionDeclaration.name].

string

Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function.

string

Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64.

object (GoogleCloudAiplatformV1Schema)

Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1

string

Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].

map (key: string, value: any)

Required. The function response in JSON object format.