aiplatform library

The Google Cloud client for the Vertex AI API.

Train high-quality custom machine learning models with minimal machine learning expertise and effort.

Classes

AcceleratorType: Represents a hardware accelerator type.
AcceptPublisherModelEulaRequest: Request message for ModelGardenService.AcceptPublisherModelEula.
ActiveLearningConfig: Parameters that configure the active learning pipeline. Active learning will label the data incrementally by several iterations. For every iteration, it will select a batch of data based on the sampling strategy.
AddContextArtifactsAndExecutionsRequest: Request message for MetadataService.AddContextArtifactsAndExecutions.
AddContextArtifactsAndExecutionsResponse: Response message for MetadataService.AddContextArtifactsAndExecutions.
AddContextChildrenRequest: Request message for MetadataService.AddContextChildren.
AddContextChildrenResponse: Response message for MetadataService.AddContextChildren.
AddExecutionEventsRequest: Request message for MetadataService.AddExecutionEvents.
AddExecutionEventsResponse: Response message for MetadataService.AddExecutionEvents.
AddTrialMeasurementRequest: Request message for VizierService.AddTrialMeasurement.
AggregationOutput: The aggregation result for the entire dataset and all metrics.
AggregationResult: The aggregation result for a single metric.
Annotation: Used to assign specific AnnotationSpec to a particular area of a DataItem or the whole part of the DataItem.
AnnotationSpec: Identifies a concept with which DataItems may be annotated with.
ApiAuth: The generic reusable api auth config.
ApiAuth_ApiKeyConfig: The API secret.
AppendEventRequest: Request message for SessionService.AppendEvent.
AppendEventResponse: Response message for SessionService.AppendEvent.
Artifact: Instance of a general artifact.
Artifact_State: Describes the state of the Artifact.
ArtifactTypeSchema: The definition of a artifact type in MLMD.
AssembleDataOperationMetadata: Runtime operation information for DatasetService.AssembleData.
AssembleDataRequest: Request message for DatasetService.AssembleData. Used only for MULTIMODAL datasets.
AssembleDataResponse: Response message for DatasetService.AssembleData.
AssessDataOperationMetadata: Runtime operation information for DatasetService.AssessData.
AssessDataRequest: Request message for DatasetService.AssessData. Used only for MULTIMODAL datasets.
AssessDataRequest_BatchPredictionResourceUsageAssessmentConfig: Configuration for the batch prediction resource usage assessment.
AssessDataRequest_BatchPredictionValidationAssessmentConfig: Configuration for the batch prediction validation assessment.
AssessDataRequest_TuningResourceUsageAssessmentConfig: Configuration for the tuning resource usage assessment.
AssessDataRequest_TuningValidationAssessmentConfig: Configuration for the tuning validation assessment.
AssessDataRequest_TuningValidationAssessmentConfig_DatasetUsage: The dataset usage (e.g. training/validation).
AssessDataResponse: Response message for DatasetService.AssessData.
AssessDataResponse_BatchPredictionResourceUsageAssessmentResult: The result of the batch prediction resource usage assessment.
AssessDataResponse_BatchPredictionValidationAssessmentResult: The result of the batch prediction validation assessment.
AssessDataResponse_TuningResourceUsageAssessmentResult: The result of the tuning resource usage assessment.
AssessDataResponse_TuningValidationAssessmentResult: The result of the tuning validation assessment.
AssignNotebookRuntimeOperationMetadata: Metadata information for NotebookService.AssignNotebookRuntime.
AssignNotebookRuntimeRequest: Request message for NotebookService.AssignNotebookRuntime.
Attribution: Attribution that explains a particular prediction output.
AugmentPromptRequest: Request message for AugmentPrompt.
AugmentPromptRequest_Model: Metadata of the backend deployed model.
AugmentPromptResponse: Response message for AugmentPrompt.
AuthConfig: Auth configuration to run the extension.
AuthConfig_ApiKeyConfig: Config for authentication with API key.
AuthConfig_GoogleServiceAccountConfig: Config for Google Service Account Authentication.
AuthConfig_HttpBasicAuthConfig: Config for HTTP Basic Authentication.
AuthConfig_OauthConfig: Config for user oauth.
AuthConfig_OidcConfig: Config for user OIDC auth.
AuthType: Type of Auth.
AutomaticResources: A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines.
AutoraterConfig: The configs for autorater. This is applicable to both EvaluateInstances and EvaluateDataset.
AutoscalingMetricSpec: The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
AvroSource: The storage details for Avro input content.
BatchCancelPipelineJobsOperationMetadata: Runtime operation information for PipelineService.BatchCancelPipelineJobs.
BatchCancelPipelineJobsRequest: Request message for PipelineService.BatchCancelPipelineJobs.
BatchCancelPipelineJobsResponse: Response message for PipelineService.BatchCancelPipelineJobs.
BatchCreateFeaturesOperationMetadata: Details of operations that perform batch create Features.
BatchCreateFeaturesRequest: Request message for FeaturestoreService.BatchCreateFeatures. Request message for FeatureRegistryService.BatchCreateFeatures.
BatchCreateFeaturesResponse: Response message for FeaturestoreService.BatchCreateFeatures.
BatchCreateTensorboardRunsRequest: Request message for TensorboardService.BatchCreateTensorboardRuns.
BatchCreateTensorboardRunsResponse: Response message for TensorboardService.BatchCreateTensorboardRuns.
BatchCreateTensorboardTimeSeriesRequest: Request message for TensorboardService.BatchCreateTensorboardTimeSeries.
BatchCreateTensorboardTimeSeriesResponse: Response message for TensorboardService.BatchCreateTensorboardTimeSeries.
BatchDedicatedResources: A description of resources that are used for performing batch operations, are dedicated to a Model, and need manual configuration.
BatchDeletePipelineJobsRequest: Request message for PipelineService.BatchDeletePipelineJobs.
BatchDeletePipelineJobsResponse: Response message for PipelineService.BatchDeletePipelineJobs.
BatchImportEvaluatedAnnotationsRequest: Request message for ModelService.BatchImportEvaluatedAnnotations
BatchImportEvaluatedAnnotationsResponse: Response message for ModelService.BatchImportEvaluatedAnnotations
BatchImportModelEvaluationSlicesRequest: Request message for ModelService.BatchImportModelEvaluationSlices
BatchImportModelEvaluationSlicesResponse: Response message for ModelService.BatchImportModelEvaluationSlices
BatchMigrateResourcesOperationMetadata: Runtime operation information for MigrationService.BatchMigrateResources.
BatchMigrateResourcesOperationMetadata_PartialResult: Represents a partial result in batch migration operation for one MigrateResourceRequest.
BatchMigrateResourcesRequest: Request message for MigrationService.BatchMigrateResources.
BatchMigrateResourcesResponse: Response message for MigrationService.BatchMigrateResources.
BatchPredictionJob: A job that uses a Model to produce predictions on multiple google.cloud.aiplatform.v1beta1.BatchPredictionJob.input_config. If predictions for significant portion of the instances fail, the job may finish without attempting predictions for all remaining instances.
BatchPredictionJob_InputConfig: Configures the input to BatchPredictionJob. See Model.supported_input_storage_formats for Model's supported input formats, and how instances should be expressed via any of them.
BatchPredictionJob_InstanceConfig: Configuration defining how to transform batch prediction input instances to the instances that the Model accepts.
BatchPredictionJob_OutputConfig: Configures the output of BatchPredictionJob. See Model.supported_output_storage_formats for supported output formats, and how predictions are expressed via any of them.
BatchPredictionJob_OutputInfo: Further describes this job's output. Supplements output_config.
BatchReadFeatureValuesOperationMetadata: Details of operations that batch reads Feature values.
BatchReadFeatureValuesRequest: Request message for FeaturestoreService.BatchReadFeatureValues.
BatchReadFeatureValuesRequest_EntityTypeSpec: Selects Features of an EntityType to read values of and specifies read settings.
BatchReadFeatureValuesRequest_PassThroughField: Describe pass-through fields in read_instance source.
BatchReadFeatureValuesResponse: Response message for FeaturestoreService.BatchReadFeatureValues.
BatchReadTensorboardTimeSeriesDataRequest: Request message for TensorboardService.BatchReadTensorboardTimeSeriesData.
BatchReadTensorboardTimeSeriesDataResponse: Response message for TensorboardService.BatchReadTensorboardTimeSeriesData.
BigQueryDestination: The BigQuery location for the output content.
BigQuerySource: The BigQuery location for the input content.
BleuInput: Input for bleu metric.
BleuInstance: Spec for bleu instance.
BleuMetricValue: Bleu metric value for an instance.
BleuResults: Results for bleu metric.
BleuSpec: Spec for bleu score metric - calculates the precision of n-grams in the prediction as compared to reference - returns a score ranging between 0 to 1.
Blob: Content blob.
BlurBaselineConfig: Config for blur baseline.
BoolArray: A list of boolean values.
CachedContent: A resource used in LLM queries for users to explicitly specify what to cache and how to cache.
CachedContent_UsageMetadata: Metadata on the usage of the cached content.
CancelBatchPredictionJobRequest: Request message for JobService.CancelBatchPredictionJob.
CancelCustomJobRequest: Request message for JobService.CancelCustomJob.
CancelDataLabelingJobRequest: Request message for JobService.CancelDataLabelingJob.
CancelHyperparameterTuningJobRequest: Request message for JobService.CancelHyperparameterTuningJob.
CancelNasJobRequest: Request message for JobService.CancelNasJob.
CancelPipelineJobRequest: Request message for PipelineService.CancelPipelineJob.
CancelTrainingPipelineRequest: Request message for PipelineService.CancelTrainingPipeline.
CancelTuningJobRequest: Request message for GenAiTuningService.CancelTuningJob.
Candidate: A response candidate generated from the model.
Candidate_FinishReason: The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
ChatCompletionsRequest: Request message for PredictionService.ChatCompletions
Checkpoint: Describes the machine learning model version checkpoint.
CheckPublisherModelEulaAcceptanceRequest: Request message for ModelGardenService.CheckPublisherModelEula.
CheckTrialEarlyStoppingStateMetatdata: This message will be placed in the metadata field of a google.longrunning.Operation associated with a CheckTrialEarlyStoppingState request.
CheckTrialEarlyStoppingStateRequest: Request message for VizierService.CheckTrialEarlyStoppingState.
CheckTrialEarlyStoppingStateResponse: Response message for VizierService.CheckTrialEarlyStoppingState.
Citation: Source attributions for content.
CitationMetadata: A collection of source attributions for a piece of content.
Claim: Claim that is extracted from the input text and facts that support it.
ClientConnectionConfig: Configurations (e.g. inference timeout) that are applied on your endpoints.
CodeExecutionResult: Result of executing the ExecutableCode.
CodeExecutionResult_Outcome: Enumeration of possible outcomes of the code execution.
CoherenceInput: Input for coherence metric.
CoherenceInstance: Spec for coherence instance.
CoherenceResult: Spec for coherence result.
CoherenceSpec: Spec for coherence score metric.
ColabImage: Colab image of the runtime.
CometInput: Input for Comet metric.
CometInstance: Spec for Comet instance - The fields used for evaluation are dependent on the comet version.
CometResult: Spec for Comet result - calculates the comet score for the given instance using the version specified in the spec.
CometSpec: Spec for Comet metric.
CometSpec_CometVersion: Comet version options.
CompleteTrialRequest: Request message for VizierService.CompleteTrial.
CompletionStats: Success and error statistics of processing multiple entities (for example, DataItems or structured data rows) in batch.
ComputeTokensRequest: Request message for ComputeTokens RPC call.
ComputeTokensResponse: Response message for ComputeTokens RPC call.
ContainerRegistryDestination: The Container Registry location for the container image.
ContainerSpec: The spec of a Container.
Content: The base structured datatype containing multi-part content of a message.
ContentMap: Map of placeholder in metric prompt template to contents of model input.
ContentMap_Contents: Repeated Content type.
ContentsExample: A single example of a conversation with the model.
ContentsExample_ExpectedContent: A single step of the expected output.
Context: Instance of a general context.
CopyModelOperationMetadata: Details of ModelService.CopyModel operation.
CopyModelRequest: Request message for ModelService.CopyModel.
CopyModelResponse: Response message of ModelService.CopyModel operation.
CorpusStatus: RagCorpus status.
CorpusStatus_State: RagCorpus life state.
CorroborateContentRequest: Request message for CorroborateContent.
CorroborateContentRequest_Parameters: Parameters that can be overrided per request.
CorroborateContentResponse: Response message for CorroborateContent.
CountTokensRequest: Request message for PredictionService.CountTokens.
CountTokensResponse: Response message for PredictionService.CountTokens.
CreateArtifactRequest: Request message for MetadataService.CreateArtifact.
CreateBatchPredictionJobRequest: Request message for JobService.CreateBatchPredictionJob.
CreateCachedContentRequest: Request message for GenAiCacheService.CreateCachedContent.
CreateContextRequest: Request message for MetadataService.CreateContext.
CreateCustomJobRequest: Request message for JobService.CreateCustomJob.
CreateDataLabelingJobRequest: Request message for JobService.CreateDataLabelingJob.
CreateDatasetOperationMetadata: Runtime operation information for DatasetService.CreateDataset.
CreateDatasetRequest: Request message for DatasetService.CreateDataset.
CreateDatasetVersionOperationMetadata: Runtime operation information for DatasetService.CreateDatasetVersion.
CreateDatasetVersionRequest: Request message for DatasetService.CreateDatasetVersion.
CreateDeploymentResourcePoolOperationMetadata: Runtime operation information for CreateDeploymentResourcePool method.
CreateDeploymentResourcePoolRequest: Request message for CreateDeploymentResourcePool method.
CreateEndpointOperationMetadata: Runtime operation information for EndpointService.CreateEndpoint.
CreateEndpointRequest: Request message for EndpointService.CreateEndpoint.
CreateEntityTypeOperationMetadata: Details of operations that perform create EntityType.
CreateEntityTypeRequest: Request message for FeaturestoreService.CreateEntityType.
CreateExampleStoreOperationMetadata: Details of ExampleStoreService.CreateExampleStore operation.
CreateExampleStoreRequest: Request message for ExampleStoreService.CreateExampleStore.
CreateExecutionRequest: Request message for MetadataService.CreateExecution.
CreateFeatureGroupOperationMetadata: Details of operations that perform create FeatureGroup.
CreateFeatureGroupRequest: Request message for FeatureRegistryService.CreateFeatureGroup.
CreateFeatureMonitorJobRequest: Request message for FeatureRegistryService.CreateFeatureMonitorJobRequest.
CreateFeatureMonitorOperationMetadata: Details of operations that perform create FeatureMonitor.
CreateFeatureMonitorRequest: Request message for FeatureRegistryService.CreateFeatureMonitorRequest.
CreateFeatureOnlineStoreOperationMetadata: Details of operations that perform create FeatureOnlineStore.
CreateFeatureOnlineStoreRequest: Request message for FeatureOnlineStoreAdminService.CreateFeatureOnlineStore.
CreateFeatureOperationMetadata: Details of operations that perform create Feature.
CreateFeatureRequest: Request message for FeaturestoreService.CreateFeature. Request message for FeatureRegistryService.CreateFeature.
CreateFeaturestoreOperationMetadata: Details of operations that perform create Featurestore.
CreateFeaturestoreRequest: Request message for FeaturestoreService.CreateFeaturestore.
CreateFeatureViewOperationMetadata: Details of operations that perform create FeatureView.
CreateFeatureViewRequest: Request message for FeatureOnlineStoreAdminService.CreateFeatureView.
CreateHyperparameterTuningJobRequest: Request message for JobService.CreateHyperparameterTuningJob.
CreateIndexEndpointOperationMetadata: Runtime operation information for IndexEndpointService.CreateIndexEndpoint.
CreateIndexEndpointRequest: Request message for IndexEndpointService.CreateIndexEndpoint.
CreateIndexOperationMetadata: Runtime operation information for IndexService.CreateIndex.
CreateIndexRequest: Request message for IndexService.CreateIndex.
CreateMemoryOperationMetadata: Details of MemoryBankService.CreateMemory operation.
CreateMemoryRequest: Request message for MemoryBankService.CreateMemory.
CreateMetadataSchemaRequest: Request message for MetadataService.CreateMetadataSchema.
CreateMetadataStoreOperationMetadata: Details of operations that perform MetadataService.CreateMetadataStore.
CreateMetadataStoreRequest: Request message for MetadataService.CreateMetadataStore.
CreateModelDeploymentMonitoringJobRequest: Request message for JobService.CreateModelDeploymentMonitoringJob.
CreateModelMonitoringJobRequest: Request message for ModelMonitoringService.CreateModelMonitoringJob.
CreateModelMonitorOperationMetadata: Runtime operation information for ModelMonitoringService.CreateModelMonitor.
CreateModelMonitorRequest: Request message for ModelMonitoringService.CreateModelMonitor.
CreateNasJobRequest: Request message for JobService.CreateNasJob.
CreateNotebookExecutionJobOperationMetadata: Metadata information for NotebookService.CreateNotebookExecutionJob.
CreateNotebookExecutionJobRequest: Request message for NotebookService.CreateNotebookExecutionJob
CreateNotebookRuntimeTemplateOperationMetadata: Metadata information for NotebookService.CreateNotebookRuntimeTemplate.
CreateNotebookRuntimeTemplateRequest: Request message for NotebookService.CreateNotebookRuntimeTemplate.
CreatePersistentResourceOperationMetadata: Details of operations that perform create PersistentResource.
CreatePersistentResourceRequest: Request message for PersistentResourceService.CreatePersistentResource.
CreatePipelineJobRequest: Request message for PipelineService.CreatePipelineJob.
CreateRagCorpusOperationMetadata: Runtime operation information for VertexRagDataService.CreateRagCorpus.
CreateRagCorpusRequest: Request message for VertexRagDataService.CreateRagCorpus.
CreateReasoningEngineOperationMetadata: Details of ReasoningEngineService.CreateReasoningEngine operation.
CreateReasoningEngineRequest: Request message for ReasoningEngineService.CreateReasoningEngine.
CreateRegistryFeatureOperationMetadata: Details of operations that perform create FeatureGroup.
CreateScheduleRequest: Request message for ScheduleService.CreateSchedule.
CreateSessionOperationMetadata: Metadata associated with the SessionService.CreateSession operation.
CreateSessionRequest: Request message for SessionService.CreateSession.
CreateSpecialistPoolOperationMetadata: Runtime operation information for SpecialistPoolService.CreateSpecialistPool.
CreateSpecialistPoolRequest: Request message for SpecialistPoolService.CreateSpecialistPool.
CreateStudyRequest: Request message for VizierService.CreateStudy.
CreateTensorboardExperimentRequest: Request message for TensorboardService.CreateTensorboardExperiment.
CreateTensorboardOperationMetadata: Details of operations that perform create Tensorboard.
CreateTensorboardRequest: Request message for TensorboardService.CreateTensorboard.
CreateTensorboardRunRequest: Request message for TensorboardService.CreateTensorboardRun.
CreateTensorboardTimeSeriesRequest: Request message for TensorboardService.CreateTensorboardTimeSeries.
CreateTrainingPipelineRequest: Request message for PipelineService.CreateTrainingPipeline.
CreateTrialRequest: Request message for VizierService.CreateTrial.
CreateTuningJobRequest: Request message for GenAiTuningService.CreateTuningJob.
CsvDestination: The storage details for CSV output content.
CsvSource: The storage details for CSV input content.
CustomJob: Represents a job that runs custom workloads such as a Docker container or a Python package. A CustomJob can have multiple worker pools and each worker pool can have its own machine and input spec. A CustomJob will be cleaned up once the job enters terminal state (failed or succeeded).
CustomJobSpec: Represents the spec of a CustomJob.
CustomOutput: Spec for custom output.
CustomOutputFormatConfig: Spec for custom output format configuration.
DataItem: A piece of data in a Dataset. Could be an image, a video, a document or plain text.
DataItemView: A container for a single DataItem and Annotations on it.
DataLabelingJob: DataLabelingJob is used to trigger a human labeling job on unlabeled data from the following Dataset:
Dataset: A collection of DataItems and Annotations on them.
DatasetDistribution: Distribution computed over a tuning dataset.
DatasetDistribution_DistributionBucket: Dataset bucket used to create a histogram for the distribution given a population of values.
DatasetService: The service that manages Vertex AI Dataset and its child resources.
DatasetStats: Statistics computed over a tuning dataset.
DatasetVersion: Describes the dataset version.
DedicatedResources: A description of resources that are dedicated to a DeployedModel or DeployedIndex, and that need a higher degree of manual configuration.
DedicatedResources_ScaleToZeroSpec: Specification for scale-to-zero feature.
DeleteArtifactRequest: Request message for MetadataService.DeleteArtifact.
DeleteBatchPredictionJobRequest: Request message for JobService.DeleteBatchPredictionJob.
DeleteCachedContentRequest: Request message for GenAiCacheService.DeleteCachedContent.
DeleteContextRequest: Request message for MetadataService.DeleteContext.
DeleteCustomJobRequest: Request message for JobService.DeleteCustomJob.
DeleteDataLabelingJobRequest: Request message for JobService.DeleteDataLabelingJob.
DeleteDatasetRequest: Request message for DatasetService.DeleteDataset.
DeleteDatasetVersionRequest: Request message for DatasetService.DeleteDatasetVersion.
DeleteDeploymentResourcePoolRequest: Request message for DeleteDeploymentResourcePool method.
DeleteEndpointRequest: Request message for EndpointService.DeleteEndpoint.
DeleteEntityTypeRequest: Request message for FeaturestoreService.DeleteEntityTypes.
DeleteExampleStoreOperationMetadata: Details of ExampleStoreService.DeleteExampleStore operation.
DeleteExampleStoreRequest: Request message for ExampleStoreService.DeleteExampleStore.
DeleteExecutionRequest: Request message for MetadataService.DeleteExecution.
DeleteExtensionRequest: Request message for ExtensionRegistryService.DeleteExtension.
DeleteFeatureGroupRequest: Request message for FeatureRegistryService.DeleteFeatureGroup.
DeleteFeatureMonitorRequest: Request message for FeatureRegistryService.DeleteFeatureMonitor.
DeleteFeatureOnlineStoreRequest: Request message for FeatureOnlineStoreAdminService.DeleteFeatureOnlineStore.
DeleteFeatureRequest: Request message for FeaturestoreService.DeleteFeature. Request message for FeatureRegistryService.DeleteFeature.
DeleteFeaturestoreRequest: Request message for FeaturestoreService.DeleteFeaturestore.
DeleteFeatureValuesOperationMetadata: Details of operations that delete Feature values.
DeleteFeatureValuesRequest: Request message for FeaturestoreService.DeleteFeatureValues.
DeleteFeatureValuesRequest_SelectEntity: Message to select entity. If an entity id is selected, all the feature values corresponding to the entity id will be deleted, including the entityId.
DeleteFeatureValuesRequest_SelectTimeRangeAndFeature: Message to select time range and feature. Values of the selected feature generated within an inclusive time range will be deleted. Using this option permanently deletes the feature values from the specified feature IDs within the specified time range. This might include data from the online storage. If you want to retain any deleted historical data in the online storage, you must re-ingest it.
DeleteFeatureValuesResponse: Response message for FeaturestoreService.DeleteFeatureValues.
DeleteFeatureValuesResponse_SelectEntity: Response message if the request uses the SelectEntity option.
DeleteFeatureValuesResponse_SelectTimeRangeAndFeature: Response message if the request uses the SelectTimeRangeAndFeature option.
DeleteFeatureViewRequest: Request message for FeatureOnlineStoreAdminService.DeleteFeatureViews.
DeleteHyperparameterTuningJobRequest: Request message for JobService.DeleteHyperparameterTuningJob.
DeleteIndexEndpointRequest: Request message for IndexEndpointService.DeleteIndexEndpoint.
DeleteIndexRequest: Request message for IndexService.DeleteIndex.
DeleteMemoryOperationMetadata: Details of MemoryBankService.DeleteMemory operation.
DeleteMemoryRequest: Request message for MemoryBankService.DeleteMemory.
DeleteMetadataStoreOperationMetadata: Details of operations that perform MetadataService.DeleteMetadataStore.
DeleteMetadataStoreRequest: Request message for MetadataService.DeleteMetadataStore.
DeleteModelDeploymentMonitoringJobRequest: Request message for JobService.DeleteModelDeploymentMonitoringJob.
DeleteModelMonitoringJobRequest: Request message for ModelMonitoringService.DeleteModelMonitoringJob.
DeleteModelMonitorRequest: Request message for ModelMonitoringService.DeleteModelMonitor.
DeleteModelRequest: Request message for ModelService.DeleteModel.
DeleteModelVersionRequest: Request message for ModelService.DeleteModelVersion.
DeleteNasJobRequest: Request message for JobService.DeleteNasJob.
DeleteNotebookExecutionJobRequest: Request message for NotebookService.DeleteNotebookExecutionJob
DeleteNotebookRuntimeRequest: Request message for NotebookService.DeleteNotebookRuntime.
DeleteNotebookRuntimeTemplateRequest: Request message for NotebookService.DeleteNotebookRuntimeTemplate.
DeleteOperationMetadata: Details of operations that perform deletes of any entities.
DeletePersistentResourceRequest: Request message for PersistentResourceService.DeletePersistentResource.
DeletePipelineJobRequest: Request message for PipelineService.DeletePipelineJob.
DeleteRagCorpusRequest: Request message for VertexRagDataService.DeleteRagCorpus.
DeleteRagFileRequest: Request message for VertexRagDataService.DeleteRagFile.
DeleteReasoningEngineRequest: Request message for ReasoningEngineService.DeleteReasoningEngine.
DeleteSavedQueryRequest: Request message for DatasetService.DeleteSavedQuery.
DeleteScheduleRequest: Request message for ScheduleService.DeleteSchedule.
DeleteSessionRequest: Request message for SessionService.DeleteSession.
DeleteSpecialistPoolRequest: Request message for SpecialistPoolService.DeleteSpecialistPool.
DeleteStudyRequest: Request message for VizierService.DeleteStudy.
DeleteTensorboardExperimentRequest: Request message for TensorboardService.DeleteTensorboardExperiment.
DeleteTensorboardRequest: Request message for TensorboardService.DeleteTensorboard.
DeleteTensorboardRunRequest: Request message for TensorboardService.DeleteTensorboardRun.
DeleteTensorboardTimeSeriesRequest: Request message for TensorboardService.DeleteTensorboardTimeSeries.
DeleteTrainingPipelineRequest: Request message for PipelineService.DeleteTrainingPipeline.
DeleteTrialRequest: Request message for VizierService.DeleteTrial.
DeployedIndex: A deployment of an Index. IndexEndpoints contain one or more DeployedIndexes.
DeployedIndexAuthConfig: Used to set up the auth on the DeployedIndex's private endpoint.
DeployedIndexAuthConfig_AuthProvider: Configuration for an authentication provider, including support for JSON Web Token (JWT).
DeployedIndexRef: Points to a DeployedIndex.
DeployedModel: A deployment of a Model. Endpoints contain one or more DeployedModels.
DeployedModel_Status: Runtime status of the deployed model.
DeployedModelRef: Points to a DeployedModel.
DeployIndexOperationMetadata: Runtime operation information for IndexEndpointService.DeployIndex.
DeployIndexRequest: Request message for IndexEndpointService.DeployIndex.
DeployIndexResponse: Response message for IndexEndpointService.DeployIndex.
DeploymentResourcePool: A description of resources that can be shared by multiple DeployedModels, whose underlying specification consists of a DedicatedResources.
DeploymentResourcePoolService: A service that manages the DeploymentResourcePool resource.
DeploymentStage: Stage field indicating the current progress of a deployment.
DeployModelOperationMetadata: Runtime operation information for EndpointService.DeployModel.
DeployModelRequest: Request message for EndpointService.DeployModel.
DeployModelResponse: Response message for EndpointService.DeployModel.
DeployOperationMetadata: Runtime operation information for ModelGardenService.Deploy.
DeployPublisherModelOperationMetadata: Runtime operation information for ModelGardenService.DeployPublisherModel.
DeployPublisherModelRequest: Request message for ModelGardenService.DeployPublisherModel.
DeployPublisherModelResponse: Response message for ModelGardenService.DeployPublisherModel.
DeployRequest: Request message for ModelGardenService.Deploy.
DeployRequest_CustomModel: The custom model to deploy from model weights in a Google Cloud Storage URI or Model Registry model.
DeployRequest_DeployConfig: The deploy config to use for the deployment.
DeployRequest_EndpointConfig: The endpoint config to use for the deployment.
DeployRequest_ModelConfig: The model config to use for the deployment.
DeployResponse: Response message for ModelGardenService.Deploy.
DestinationFeatureSetting
DirectPredictRequest: Request message for PredictionService.DirectPredict.
DirectPredictResponse: Response message for PredictionService.DirectPredict.
DirectRawPredictRequest: Request message for PredictionService.DirectRawPredict.
DirectRawPredictResponse: Response message for PredictionService.DirectRawPredict.
DirectUploadSource: The input content is encapsulated and uploaded in the request.
DiskSpec: Represents the spec of disk options.
DistillationDataStats: Statistics computed for datasets used for distillation.
DistillationHyperParameters: Hyperparameters for Distillation.
DistillationSpec: Tuning Spec for Distillation.
DnsPeeringConfig: DNS peering configuration. These configurations are used to create DNS peering zones in the Vertex tenant project VPC, enabling resolution of records within the specified domain hosted in the target network's Cloud DNS.
DoubleArray: A list of double values.
DynamicRetrievalConfig: Describes the options to customize dynamic retrieval.
DynamicRetrievalConfig_Mode: The mode of the predictor to be used in dynamic retrieval.
EncryptionSpec: Represents a customer-managed encryption key spec that can be applied to a top-level resource.
Endpoint: Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.
EndpointService: A service for managing Vertex AI's Endpoints.
EnterpriseWebSearch: Tool to search public web data, powered by Vertex AI Search and Sec4 compliance.
EntityIdSelector: Selector for entityId. Getting ids from the given source.
EntityType: An entity type is a type of object in a system that needs to be modeled and have stored information about. For example, driver is an entity type, and driver0 is an instance of an entity type driver.
EnvVar: Represents an environment variable present in a Container or Python Module.
ErrorAnalysisAnnotation: Model error analysis for each annotation.
ErrorAnalysisAnnotation_AttributedItem: Attributed items for a given annotation, typically representing neighbors from the training sets constrained by the query type.
ErrorAnalysisAnnotation_QueryType: The query type used for finding the attributed items.
EvaluatedAnnotation: True positive, false positive, or false negative.
EvaluatedAnnotation_EvaluatedAnnotationType: Describes the type of the EvaluatedAnnotation. The type is determined
EvaluatedAnnotationExplanation: Explanation result of the prediction produced by the Model.
EvaluateDatasetOperationMetadata: Operation metadata for Dataset Evaluation.
EvaluateDatasetRequest: Request message for EvaluationService.EvaluateDataset.
EvaluateDatasetResponse: Response in LRO for EvaluationService.EvaluateDataset.
EvaluateDatasetRun: Evaluate Dataset Run Result for Tuning Job.
EvaluateInstancesRequest: Request message for EvaluationService.EvaluateInstances.
EvaluateInstancesResponse: Response message for EvaluationService.EvaluateInstances.
EvaluationConfig: Evaluation Config for Tuning Job.
EvaluationDataset: The dataset used for evaluation.
EvaluationService: Vertex AI Online Evaluation Service.
Event: An edge describing the relationship between an Artifact and an Execution in a lineage graph.
Event_Type: Describes whether an Event's Artifact is the Execution's input or output.
EventActions: Actions are parts of events that are executed by the agent.
EventMetadata: Metadata relating to a LLM response event.
ExactMatchInput: Input for exact match metric.
ExactMatchInstance: Spec for exact match instance.
ExactMatchMetricValue: Exact match metric value for an instance.
ExactMatchResults: Results for exact match metric.
ExactMatchSpec: Spec for exact match metric - returns 1 if prediction and reference exactly matches, otherwise 0.
Example: A single example to upload or read from the Example Store.
Examples: Example-based explainability that returns the nearest neighbors from the provided dataset.
Examples_ExampleGcsSource: The Cloud Storage input instances.
Examples_ExampleGcsSource_DataFormat: The format of the input example instances.
ExamplesArrayFilter: Filters for examples' array metadata fields. An array field is example metadata where multiple values are attributed to a single example.
ExamplesArrayFilter_ArrayOperator: The logic to use for filtering.
ExamplesOverride: Overrides for example-based explanations.
ExamplesOverride_DataFormat: Data format enum.
ExamplesRestrictionsNamespace: Restrictions namespace for example-based explanations overrides.
ExampleStore: Represents an executable service to manage and retrieve examples.
ExampleStoreConfig: Configuration for the Example Store.
ExampleStoreService: A service for managing and retrieving few-shot examples.
ExecutableCode: Code generated by the model that is meant to be executed, and the result returned to the model.
ExecutableCode_Language: Supported programming languages for the generated code.
ExecuteExtensionRequest: Request message for ExtensionExecutionService.ExecuteExtension.
ExecuteExtensionResponse: Response message for ExtensionExecutionService.ExecuteExtension.
Execution: Instance of a general execution.
Execution_State: Describes the state of the Execution.
ExplainRequest: Request message for PredictionService.Explain.
ExplainResponse: Response message for PredictionService.Explain.
ExplainResponse_ConcurrentExplanation: This message is a wrapper grouping Concurrent Explanations.
Explanation: Explanation of a prediction (provided in PredictResponse.predictions) produced by the Model on a given instance.
ExplanationMetadata: Metadata describing the Model's input and output for explanation.
ExplanationMetadata_InputMetadata: Metadata of the input of a feature.
ExplanationMetadata_InputMetadata_Encoding: Defines how a feature is encoded. Defaults to IDENTITY.
ExplanationMetadata_InputMetadata_FeatureValueDomain: Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained.
ExplanationMetadata_InputMetadata_Visualization: Visualization configurations for image explanation.
ExplanationMetadata_InputMetadata_Visualization_ColorMap: The color scheme used for highlighting areas.
ExplanationMetadata_InputMetadata_Visualization_OverlayType: How the original image is displayed in the visualization.
ExplanationMetadata_InputMetadata_Visualization_Polarity: Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
ExplanationMetadata_InputMetadata_Visualization_Type: Type of the image visualization. Only applicable to google.cloud.aiplatform.v1beta1.ExplanationParameters.integrated_gradients_attribution.
ExplanationMetadata_OutputMetadata: Metadata of the prediction output to be explained.
ExplanationMetadataOverride: The ExplanationMetadata entries that can be overridden at google.cloud.aiplatform.v1beta1.PredictionService.Explain time.
ExplanationMetadataOverride_InputMetadataOverride: The google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata entries to be overridden.
ExplanationParameters: Parameters to configure explaining for Model's predictions.
ExplanationSpec: Specification of Model explanation.
ExplanationSpecOverride: The ExplanationSpec entries that can be overridden at google.cloud.aiplatform.v1beta1.PredictionService.Explain time.
ExportDataConfig: Describes what part of the Dataset is to be exported, the destination of the export and how to export.
ExportDataOperationMetadata: Runtime operation information for DatasetService.ExportData.
ExportDataRequest: Request message for DatasetService.ExportData.
ExportDataResponse: Response message for DatasetService.ExportData.
ExportFeatureValuesOperationMetadata: Details of operations that exports Features values.
ExportFeatureValuesRequest: Request message for FeaturestoreService.ExportFeatureValues.
ExportFeatureValuesRequest_FullExport: Describes exporting all historical Feature values of all entities of the EntityType between start_time, end_time.
ExportFeatureValuesRequest_SnapshotExport: Describes exporting the latest Feature values of all entities of the EntityType between start_time, snapshot_time.
ExportFeatureValuesResponse: Response message for FeaturestoreService.ExportFeatureValues.
ExportFractionSplit: Assigns the input data to training, validation, and test sets as per the given fractions. Any of training_fraction, validation_fraction and test_fraction may optionally be provided, they must sum to up to 1. If the provided ones sum to less than 1, the remainder is assigned to sets as decided by Vertex AI. If none of the fractions are set, by default roughly 80% of data is used for training, 10% for validation, and 10% for test.
ExportModelOperationMetadata: Details of ModelService.ExportModel operation.
ExportModelOperationMetadata_OutputInfo: Further describes the output of the ExportModel. Supplements ExportModelRequest.OutputConfig.
ExportModelRequest: Request message for ModelService.ExportModel.
ExportModelRequest_OutputConfig: Output configuration for the Model export.
ExportModelResponse: Response message of ModelService.ExportModel operation.
ExportPublisherModelOperationMetadata: Runtime operation information for ModelGardenService.ExportPublisherModel.
ExportPublisherModelRequest: Request message for ModelGardenService.ExportPublisherModel.
ExportPublisherModelResponse: Response message for ModelGardenService.ExportPublisherModel.
ExportTensorboardTimeSeriesDataRequest: Request message for TensorboardService.ExportTensorboardTimeSeriesData.
ExportTensorboardTimeSeriesDataResponse: Response message for TensorboardService.ExportTensorboardTimeSeriesData.
Extension: Extensions are tools for large language models to access external data, run computations, etc.
ExtensionExecutionService: A service for Extension execution.
ExtensionManifest: Manifest spec of an Extension needed for runtime execution.
ExtensionManifest_ApiSpec: The API specification shown to the LLM.
ExtensionOperation: Operation of an extension.
ExtensionPrivateServiceConnectConfig: PrivateExtensionConfig configuration for the extension.
ExtensionRegistryService: A service for managing Vertex AI's Extension registry.
Fact: The fact used in grounding.
FasterDeploymentConfig: Configuration for faster model deployment.
Feature: Feature Metadata information. For example, color is a feature that describes an apple.
Feature_MonitoringStatsAnomaly: A list of historical SnapshotAnalysis or ImportFeaturesAnalysis stats requested by user, sorted by FeatureStatsAnomaly.start_time descending.
Feature_MonitoringStatsAnomaly_Objective: If the objective in the request is both Import Feature Analysis and Snapshot Analysis, this objective could be one of them. Otherwise, this objective should be the same as the objective in the request.
Feature_ValueType: Only applicable for Vertex AI Legacy Feature Store. An enum representing the value type of a feature.
FeatureGroup: Vertex AI Feature Group.
FeatureGroup_BigQuery: Input source type for BigQuery Tables and Views.
FeatureGroup_BigQuery_TimeSeries
FeatureGroup_ServiceAgentType: Service agent type used during jobs under a FeatureGroup.
FeatureMonitor: Vertex AI Feature Monitor.
FeatureMonitorJob: Vertex AI Feature Monitor Job.
FeatureMonitorJob_FeatureMonitorJobTrigger: Choices of the trigger type.
FeatureMonitorJob_JobSummary: Summary from the FeatureMonitorJob.
FeatureNoiseSigma: Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients.
FeatureNoiseSigma_NoiseSigmaForFeature: Noise sigma for a single feature.
FeatureOnlineStore: Vertex AI Feature Online Store provides a centralized repository for serving ML features and embedding indexes at low latency. The Feature Online Store is a top-level container.
FeatureOnlineStore_Bigtable
FeatureOnlineStore_Bigtable_AutoScaling
FeatureOnlineStore_Bigtable_BigtableMetadata: Metadata of the Bigtable instance. This is used by direct read access to the Bigtable in tenant project.
FeatureOnlineStore_DedicatedServingEndpoint: The dedicated serving endpoint for this FeatureOnlineStore. Only need to set when you choose Optimized storage type. Public endpoint is provisioned by default.
FeatureOnlineStore_EmbeddingManagement: Deprecated: This sub message is no longer needed anymore and embedding management is automatically enabled when specifying Optimized storage type. Contains settings for embedding management.
FeatureOnlineStore_Optimized: Optimized storage type
FeatureOnlineStore_State: Possible states a featureOnlineStore can have.
FeatureOnlineStoreAdminService: The service that handles CRUD and List for resources for FeatureOnlineStore.
FeatureOnlineStoreService: A service for fetching feature values from the online store.
FeatureRegistryService: The service that handles CRUD and List for resources for FeatureRegistry.
FeatureSelectionConfig: Feature selection configuration for the FeatureMonitor.
FeatureSelectionConfig_FeatureConfig: Feature configuration.
FeatureSelector: Selector for Features of an EntityType.
FeatureStatsAndAnomaly: Stats and Anomaly generated by FeatureMonitorJobs. Anomaly only includes Drift.
FeatureStatsAndAnomalySpec: Defines how to select FeatureStatsAndAnomaly to be populated in response. If set, retrieves FeatureStatsAndAnomaly generated by FeatureMonitors based on this spec.
FeatureStatsAnomaly: Stats and Anomaly generated at specific timestamp for specific Feature. The start_time and end_time are used to define the time range of the dataset that current stats belongs to, e.g. prediction traffic is bucketed into prediction datasets by time window. If the Dataset is not defined by time window, start_time = end_time. Timestamp of the stats and anomalies always refers to end_time. Raw stats and anomalies are stored in stats_uri or anomaly_uri in the tensorflow defined protos. Field data_stats contains almost identical information with the raw stats in Vertex AI defined proto, for UI to display.
Featurestore: Vertex AI Feature Store provides a centralized repository for organizing, storing, and serving ML features. The Featurestore is a top-level container for your features and their values.
Featurestore_OnlineServingConfig: OnlineServingConfig specifies the details for provisioning online serving resources.
Featurestore_OnlineServingConfig_Scaling: Online serving scaling configuration. If min_node_count and max_node_count are set to the same value, the cluster will be configured with the fixed number of node (no auto-scaling).
Featurestore_State: Possible states a featurestore can have.
FeaturestoreMonitoringConfig: Configuration of how features in Featurestore are monitored.
FeaturestoreMonitoringConfig_ImportFeaturesAnalysis: Configuration of the Featurestore's ImportFeature Analysis Based Monitoring. This type of analysis generates statistics for values of each Feature imported by every ImportFeatureValues operation.
FeaturestoreMonitoringConfig_ImportFeaturesAnalysis_Baseline: Defines the baseline to do anomaly detection for feature values imported by each ImportFeatureValues operation.
FeaturestoreMonitoringConfig_ImportFeaturesAnalysis_State: The state defines whether to enable ImportFeature analysis.
FeaturestoreMonitoringConfig_SnapshotAnalysis: Configuration of the Featurestore's Snapshot Analysis Based Monitoring. This type of analysis generates statistics for each Feature based on a snapshot of the latest feature value of each entities every monitoring_interval.
FeaturestoreMonitoringConfig_ThresholdConfig: The config for Featurestore Monitoring threshold.
FeaturestoreOnlineServingService: A service for serving online feature values.
FeaturestoreService: The service that handles CRUD and List for resources for Featurestore.
FeatureValue: Value for a feature.
FeatureValue_Metadata: Metadata of feature value.
FeatureValueDestination: A destination location for Feature values and format.
FeatureValueList: Container for list of values.
FeatureView: FeatureView is representation of values that the FeatureOnlineStore will serve based on its syncConfig.
FeatureView_BigQuerySource
FeatureView_BigtableMetadata: Metadata for the Cloud Bigtable that supports directly interacting Bigtable instances.
FeatureView_FeatureRegistrySource: A Feature Registry source for features that need to be synced to Online Store.
FeatureView_FeatureRegistrySource_FeatureGroup: Features belonging to a single feature group that will be synced to Online Store.
FeatureView_IndexConfig: Configuration for vector indexing.
FeatureView_IndexConfig_BruteForceConfig: Configuration options for using brute force search.
FeatureView_IndexConfig_DistanceMeasureType: The distance measure used in nearest neighbor search.
FeatureView_IndexConfig_TreeAhconfig: Configuration options for the tree-AH algorithm.
FeatureView_OptimizedConfig: Configuration for FeatureViews created in Optimized FeatureOnlineStore.
FeatureView_ServiceAgentType: Service agent type used during data sync.
FeatureView_SyncConfig: Configuration for Sync. Only one option is set.
FeatureView_VectorSearchConfig: Deprecated. Use IndexConfig instead.
FeatureView_VectorSearchConfig_BruteForceConfig
FeatureView_VectorSearchConfig_DistanceMeasureType
FeatureView_VectorSearchConfig_TreeAhconfig
FeatureView_VertexRagSource: A Vertex Rag source for features that need to be synced to Online Store.
FeatureViewDataFormat: Format of the data in the Feature View.
FeatureViewDataKey: Lookup key for a feature view.
FeatureViewDataKey_CompositeKey: ID that is comprised from several parts (columns).
FeatureViewDirectWriteRequest: Request message for FeatureOnlineStoreService.FeatureViewDirectWrite.
FeatureViewDirectWriteRequest_DataKeyAndFeatureValues: A data key and associated feature values to write to the feature view.
FeatureViewDirectWriteRequest_DataKeyAndFeatureValues_Feature: Feature name & value pair.
FeatureViewDirectWriteRequest_DataKeyAndFeatureValues_Feature_FeatureValueAndTimestamp: Feature value and timestamp.
FeatureViewDirectWriteResponse: Response message for FeatureOnlineStoreService.FeatureViewDirectWrite.
FeatureViewDirectWriteResponse_WriteResponse: Details about the write for each key.
FeatureViewSync: FeatureViewSync is a representation of sync operation which copies data from data source to Feature View in Online Store.
FeatureViewSync_SyncSummary: Summary from the Sync job. For continuous syncs, the summary is updated periodically. For batch syncs, it gets updated on completion of the sync.
FetchExamplesRequest: Request message for ExampleStoreService.FetchExamples.
FetchExamplesResponse: Response message for ExampleStoreService.FetchExamples.
FetchFeatureValuesRequest: Request message for FeatureOnlineStoreService.FetchFeatureValues. All the features under the requested feature view will be returned.
FetchFeatureValuesRequest_Format: Format of the response data.
FetchFeatureValuesResponse: Response message for FeatureOnlineStoreService.FetchFeatureValues
FetchFeatureValuesResponse_FeatureNameValuePairList: Response structure in the format of key (feature name) and (feature) value pair.
FetchFeatureValuesResponse_FeatureNameValuePairList_FeatureNameValuePair: Feature name & value pair.
FetchPublisherModelConfigRequest: Request message for EndpointService.FetchPublisherModelConfig.
FileData: URI based data.
FileStatus: RagFile status.
FileStatus_State: RagFile state.
FilterSplit: Assigns input data to training, validation, and test sets based on the given filters, data pieces not matched by any filter are ignored. Currently only supported for Datasets containing DataItems. If any of the filters in this message are to match nothing, then they can be set as '-' (the minus sign).
FindNeighborsRequest: The request message for MatchService.FindNeighbors.
FindNeighborsRequest_Query: A query to find a number of the nearest neighbors (most similar vectors) of a vector.
FindNeighborsRequest_Query_Rrf: Parameters for RRF algorithm that combines search results.
FindNeighborsResponse: The response message for MatchService.FindNeighbors.
FindNeighborsResponse_NearestNeighbors: Nearest neighbors for one query.
FindNeighborsResponse_Neighbor: A neighbor of the query vector.
FlexStart: FlexStart is used to schedule the deployment workload on DWS resource. It contains the max duration of the deployment.
FluencyInput: Input for fluency metric.
FluencyInstance: Spec for fluency instance.
FluencyResult: Spec for fluency result.
FluencySpec: Spec for fluency score metric.
FractionSplit: Assigns the input data to training, validation, and test sets as per the given fractions. Any of training_fraction, validation_fraction and test_fraction may optionally be provided, they must sum to up to 1. If the provided ones sum to less than 1, the remainder is assigned to sets as decided by Vertex AI. If none of the fractions are set, by default roughly 80% of data is used for training, 10% for validation, and 10% for test.
FulfillmentInput: Input for fulfillment metric.
FulfillmentInstance: Spec for fulfillment instance.
FulfillmentResult: Spec for fulfillment result.
FulfillmentSpec: Spec for fulfillment metric.
FunctionCall: A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values.
FunctionCallingConfig: Function calling config.
FunctionCallingConfig_Mode: Function calling mode.
FunctionDeclaration: Structured representation of a function declaration as defined by the OpenAPI 3.0 specification. Included in this declaration are the function name, description, parameters and response type. This FunctionDeclaration is a representation of a block of code that can be used as a Tool by the model and executed by the client.
FunctionResponse: The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a FunctionCall made based on model prediction.
GcsDestination: The Google Cloud Storage location where the output is to be written to.
GcsSource: The Google Cloud Storage location for the input content.
GeminiExample: Format for Gemini examples used for Vertex Multimodal datasets.
GeminiRequestReadConfig: Configuration for how to read Gemini requests from a multimodal dataset.
GeminiTemplateConfig: Template configuration to create Gemini examples from a multimodal dataset.
GenAiAdvancedFeaturesConfig: Configuration for GenAiAdvancedFeatures.
GenAiAdvancedFeaturesConfig_RagConfig: Configuration for Retrieval Augmented Generation feature.
GenAiCacheService: Service for managing Vertex AI's CachedContent resource.
GenAiTuningService: A service for creating and managing GenAI Tuning Jobs.
GenerateContentRequest: Request message for PredictionService.GenerateContent.
GenerateContentResponse: Response message for PredictionService.GenerateContent.
GenerateContentResponse_PromptFeedback: Content filter results for a prompt sent in the request.
GenerateContentResponse_PromptFeedback_BlockedReason: Blocked reason enumeration.
GenerateContentResponse_UsageMetadata: Usage metadata about response(s).
GenerateFetchAccessTokenRequest: Request message for FeatureOnlineStoreService.GenerateFetchAccessToken.
GenerateFetchAccessTokenResponse: Response message for FeatureOnlineStoreService.GenerateFetchAccessToken.
GenerateMemoriesOperationMetadata: Details of MemoryBankService.GenerateMemories operation.
GenerateMemoriesRequest: Request message for MemoryBankService.GenerateMemories.
GenerateMemoriesRequest_DirectContentsSource: Defines a direct source of content from which to generate the memories.
GenerateMemoriesRequest_DirectContentsSource_Event: A single piece of conversation from which to generate memories.
GenerateMemoriesRequest_DirectMemoriesSource: Defines a direct source of memories that should be uploaded to Memory Bank with consolidation.
GenerateMemoriesRequest_DirectMemoriesSource_DirectMemory: A direct memory to upload to Memory Bank.
GenerateMemoriesRequest_VertexSessionSource: Defines an Agent Engine Session from which to generate the memories. If scope is not provided, the scope will be extracted from the Session (i.e. {"user_id": sesison.user_id}).
GenerateMemoriesResponse: Response message for MemoryBankService.GenerateMemories.
GenerateMemoriesResponse_GeneratedMemory: A memory generated by the operation.
GenerateMemoriesResponse_GeneratedMemory_Action: Actions that can be performed on a Memory.
GenerateVideoResponse: Generate video response.
GenerationConfig: Generation config.
GenerationConfig_MediaResolution: Media resolution for the input media.
GenerationConfig_Modality: The modalities of the response.
GenerationConfig_ModelConfig: Config for model selection.
GenerationConfig_ModelConfig_FeatureSelectionPreference: Options for feature selection preference.
GenerationConfig_RoutingConfig: The configuration for routing the request to a specific model.
GenerationConfig_RoutingConfig_AutoRoutingMode: When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference.
GenerationConfig_RoutingConfig_AutoRoutingMode_ModelRoutingPreference: The model routing preference.
GenerationConfig_RoutingConfig_ManualRoutingMode: When manual routing is set, the specified model will be used directly.
GenerationConfig_ThinkingConfig: Config for thinking features.
GenericOperationMetadata: Generic Metadata shared by all operations.
GenieSource: Contains information about the source of the models generated from Generative AI Studio.
GetAnnotationSpecRequest: Request message for DatasetService.GetAnnotationSpec.
GetArtifactRequest: Request message for MetadataService.GetArtifact.
GetBatchPredictionJobRequest: Request message for JobService.GetBatchPredictionJob.
GetCachedContentRequest: Request message for GenAiCacheService.GetCachedContent.
GetContextRequest: Request message for MetadataService.GetContext.
GetCustomJobRequest: Request message for JobService.GetCustomJob.
GetDataLabelingJobRequest: Request message for JobService.GetDataLabelingJob.
GetDatasetRequest: Request message for DatasetService.GetDataset.
GetDatasetVersionRequest: Request message for DatasetService.GetDatasetVersion.
GetDeploymentResourcePoolRequest: Request message for GetDeploymentResourcePool method.
GetEndpointRequest: Request message for EndpointService.GetEndpoint
GetEntityTypeRequest: Request message for FeaturestoreService.GetEntityType.
GetExampleStoreRequest: Request message for ExampleStoreService.GetExampleStore.
GetExecutionRequest: Request message for MetadataService.GetExecution.
GetExtensionRequest: Request message for ExtensionRegistryService.GetExtension.
GetFeatureGroupRequest: Request message for FeatureRegistryService.GetFeatureGroup.
GetFeatureMonitorJobRequest: Request message for FeatureRegistryService.GetFeatureMonitorJob.
GetFeatureMonitorRequest: Request message for FeatureRegistryService.GetFeatureMonitor.
GetFeatureOnlineStoreRequest: Request message for FeatureOnlineStoreAdminService.GetFeatureOnlineStore.
GetFeatureRequest: Request message for FeaturestoreService.GetFeature. Request message for FeatureRegistryService.GetFeature.
GetFeaturestoreRequest: Request message for FeaturestoreService.GetFeaturestore.
GetFeatureViewRequest: Request message for FeatureOnlineStoreAdminService.GetFeatureView.
GetFeatureViewSyncRequest: Request message for FeatureOnlineStoreAdminService.GetFeatureViewSync.
GetHyperparameterTuningJobRequest: Request message for JobService.GetHyperparameterTuningJob.
GetIndexEndpointRequest: Request message for IndexEndpointService.GetIndexEndpoint
GetIndexRequest: Request message for IndexService.GetIndex
GetMemoryRequest: Request message for MemoryBankService.GetMemory.
GetMetadataSchemaRequest: Request message for MetadataService.GetMetadataSchema.
GetMetadataStoreRequest: Request message for MetadataService.GetMetadataStore.
GetModelDeploymentMonitoringJobRequest: Request message for JobService.GetModelDeploymentMonitoringJob.
GetModelEvaluationRequest: Request message for ModelService.GetModelEvaluation.
GetModelEvaluationSliceRequest: Request message for ModelService.GetModelEvaluationSlice.
GetModelMonitoringJobRequest: Request message for ModelMonitoringService.GetModelMonitoringJob.
GetModelMonitorRequest: Request message for ModelMonitoringService.GetModelMonitor.
GetModelRequest: Request message for ModelService.GetModel.
GetNasJobRequest: Request message for JobService.GetNasJob.
GetNasTrialDetailRequest: Request message for JobService.GetNasTrialDetail.
GetNotebookExecutionJobRequest: Request message for NotebookService.GetNotebookExecutionJob
GetNotebookRuntimeRequest: Request message for NotebookService.GetNotebookRuntime
GetNotebookRuntimeTemplateRequest: Request message for NotebookService.GetNotebookRuntimeTemplate
GetPersistentResourceRequest: Request message for PersistentResourceService.GetPersistentResource.
GetPipelineJobRequest: Request message for PipelineService.GetPipelineJob.
GetPublisherModelRequest: Request message for ModelGardenService.GetPublisherModel
GetRagCorpusRequest: Request message for VertexRagDataService.GetRagCorpus
GetRagEngineConfigRequest: Request message for VertexRagDataService.GetRagEngineConfig
GetRagFileRequest: Request message for VertexRagDataService.GetRagFile
GetReasoningEngineRequest: Request message for ReasoningEngineService.GetReasoningEngine.
GetScheduleRequest: Request message for ScheduleService.GetSchedule.
GetSessionRequest: Request message for SessionService.GetSession.
GetSpecialistPoolRequest: Request message for SpecialistPoolService.GetSpecialistPool.
GetStudyRequest: Request message for VizierService.GetStudy.
GetTensorboardExperimentRequest: Request message for TensorboardService.GetTensorboardExperiment.
GetTensorboardRequest: Request message for TensorboardService.GetTensorboard.
GetTensorboardRunRequest: Request message for TensorboardService.GetTensorboardRun.
GetTensorboardTimeSeriesRequest: Request message for TensorboardService.GetTensorboardTimeSeries.
GetTrainingPipelineRequest: Request message for PipelineService.GetTrainingPipeline.
GetTrialRequest: Request message for VizierService.GetTrial.
GetTuningJobRequest: Request message for GenAiTuningService.GetTuningJob.
GoogleDriveSource: The Google Drive location for the input content.
GoogleDriveSource_ResourceId: The type and ID of the Google Drive resource.
GoogleDriveSource_ResourceId_ResourceType: The type of the Google Drive resource.
GoogleMaps: Tool to retrieve public maps data for grounding, powered by Google.
GoogleSearchRetrieval: Tool to retrieve public web data for grounding, powered by Google.
GroundednessInput: Input for groundedness metric.
GroundednessInstance: Spec for groundedness instance.
GroundednessResult: Spec for groundedness result.
GroundednessSpec: Spec for groundedness metric.
GroundingChunk: Grounding chunk.
GroundingChunk_Maps: Chunk from Google Maps.
GroundingChunk_Maps_PlaceAnswerSources
GroundingChunk_Maps_PlaceAnswerSources_ReviewSnippet: Encapsulates a review snippet.
GroundingChunk_RetrievedContext: Chunk from context retrieved by the retrieval tools.
GroundingChunk_Web: Chunk from the web.
GroundingMetadata: Metadata returned to client when grounding is enabled.
GroundingMetadata_SourceFlaggingUri: Source content flagging uri for a place or review. This is currently populated only for Google Maps grounding.
GroundingSupport: Grounding support.
HarmCategory: Harm categories that will block the content.
HttpElementLocation: Enum of location an HTTP element can be.
HyperparameterTuningJob: Represents a HyperparameterTuningJob. A HyperparameterTuningJob has a Study specification and multiple CustomJobs with identical CustomJob specification.
IdMatcher: Matcher for Features of an EntityType by Feature ID.
ImageConfig: Config for image generation features.
ImportDataConfig: Describes the location from where we import data into a Dataset, together with the labels that will be applied to the DataItems and the Annotations.
ImportDataOperationMetadata: Runtime operation information for DatasetService.ImportData.
ImportDataRequest: Request message for DatasetService.ImportData.
ImportDataResponse: Response message for DatasetService.ImportData.
ImportExtensionOperationMetadata: Details of ExtensionRegistryService.ImportExtension operation.
ImportExtensionRequest: Request message for ExtensionRegistryService.ImportExtension.
ImportFeatureValuesOperationMetadata: Details of operations that perform import Feature values.
ImportFeatureValuesRequest: Request message for FeaturestoreService.ImportFeatureValues.
ImportFeatureValuesRequest_FeatureSpec: Defines the Feature value(s) to import.
ImportFeatureValuesResponse: Response message for FeaturestoreService.ImportFeatureValues.
ImportIndexOperationMetadata: Runtime operation information for IndexService.ImportIndex.
ImportIndexRequest: Request message for IndexService.ImportIndex.
ImportIndexRequest_ConnectorConfig: Configuration for importing data from an external source.
ImportIndexRequest_ConnectorConfig_BigQuerySourceConfig: Configuration for importing data from a BigQuery table.
ImportIndexRequest_ConnectorConfig_DatapointFieldMapping: Mapping of datapoint fields to column names for columnar data sources.
ImportIndexRequest_ConnectorConfig_DatapointFieldMapping_NumericRestrict: Restrictions on numeric values.
ImportIndexRequest_ConnectorConfig_DatapointFieldMapping_NumericRestrict_ValueType: The type of numeric value for the restrict.
ImportIndexRequest_ConnectorConfig_DatapointFieldMapping_Restrict: Restrictions on string values.
ImportModelEvaluationRequest: Request message for ModelService.ImportModelEvaluation
ImportRagFilesConfig: Config for importing RagFiles.
ImportRagFilesOperationMetadata: Runtime operation information for VertexRagDataService.ImportRagFiles.
ImportRagFilesRequest: Request message for VertexRagDataService.ImportRagFiles.
ImportRagFilesResponse: Response message for VertexRagDataService.ImportRagFiles.
Index: A representation of a collection of database items organized in a way that allows for approximate nearest neighbor (a.k.a ANN) algorithms search.
Index_IndexUpdateMethod: The update method of an Index.
IndexDatapoint: A datapoint of Index.
IndexDatapoint_CrowdingTag: Crowding tag is a constraint on a neighbor list produced by nearest neighbor search requiring that no more than some value k' of the k neighbors returned have the same value of crowding_attribute.
IndexDatapoint_NumericRestriction: This field allows restricts to be based on numeric comparisons rather than categorical tokens.
IndexDatapoint_NumericRestriction_Operator: Which comparison operator to use. Should be specified for queries only; specifying this for a datapoint is an error.
IndexDatapoint_Restriction: Restriction of a datapoint which describe its attributes(tokens) from each of several attribute categories(namespaces).
IndexDatapoint_SparseEmbedding: Feature embedding vector for sparse index. An array of numbers whose values are located in the specified dimensions.
IndexEndpoint: Indexes are deployed into it. An IndexEndpoint can have multiple DeployedIndexes.
IndexEndpointService: A service for managing Vertex AI's IndexEndpoints.
IndexPrivateEndpoints: IndexPrivateEndpoints proto is used to provide paths for users to send requests via private endpoints (e.g. private service access, private service connect). To send request via private service access, use match_grpc_address. To send request via private service connect, use service_attachment.
IndexService: A service for creating and managing Vertex AI's Index resources.
IndexStats: Stats of the Index.
InputDataConfig: Specifies Vertex AI owned input data to be used for training, and possibly evaluating, the Model.
Int64Array: A list of int64 values.
IntegratedGradientsAttribution: An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
JiraSource: The Jira source for the ImportRagFilesRequest.
JiraSource_JiraQueries: JiraQueries contains the Jira queries and corresponding authentication.
JobService: A service for creating and managing Vertex AI's jobs.
JobState: Describes the state of a job.
LargeModelReference: Contains information about the Large Model.
LineageSubgraph: A subgraph of the overall lineage graph. Event edges connect Artifact and Execution nodes.
ListAnnotationsRequest: Request message for DatasetService.ListAnnotations.
ListAnnotationsResponse: Response message for DatasetService.ListAnnotations.
ListArtifactsRequest: Request message for MetadataService.ListArtifacts.
ListArtifactsResponse: Response message for MetadataService.ListArtifacts.
ListBatchPredictionJobsRequest: Request message for JobService.ListBatchPredictionJobs.
ListBatchPredictionJobsResponse: Response message for JobService.ListBatchPredictionJobs
ListCachedContentsRequest: Request to list CachedContents.
ListCachedContentsResponse: Response with a list of CachedContents.
ListContextsRequest: Request message for MetadataService.ListContexts
ListContextsResponse: Response message for MetadataService.ListContexts.
ListCustomJobsRequest: Request message for JobService.ListCustomJobs.
ListCustomJobsResponse: Response message for JobService.ListCustomJobs
ListDataItemsRequest: Request message for DatasetService.ListDataItems.
ListDataItemsResponse: Response message for DatasetService.ListDataItems.
ListDataLabelingJobsRequest: Request message for JobService.ListDataLabelingJobs.
ListDataLabelingJobsResponse: Response message for JobService.ListDataLabelingJobs.
ListDatasetsRequest: Request message for DatasetService.ListDatasets.
ListDatasetsResponse: Response message for DatasetService.ListDatasets.
ListDatasetVersionsRequest: Request message for DatasetService.ListDatasetVersions.
ListDatasetVersionsResponse: Response message for DatasetService.ListDatasetVersions.
ListDeploymentResourcePoolsRequest: Request message for ListDeploymentResourcePools method.
ListDeploymentResourcePoolsResponse: Response message for ListDeploymentResourcePools method.
ListEndpointsRequest: Request message for EndpointService.ListEndpoints.
ListEndpointsResponse: Response message for EndpointService.ListEndpoints.
ListEntityTypesRequest: Request message for FeaturestoreService.ListEntityTypes.
ListEntityTypesResponse: Response message for FeaturestoreService.ListEntityTypes.
ListEventsRequest: Request message for SessionService.ListEvents.
ListEventsResponse: Response message for SessionService.ListEvents.
ListExampleStoresRequest: Request message for ExampleStoreService.ListExampleStores.
ListExampleStoresResponse: Response message for ExampleStoreService.ListExampleStores.
ListExecutionsRequest: Request message for MetadataService.ListExecutions.
ListExecutionsResponse: Response message for MetadataService.ListExecutions.
ListExtensionsRequest: Request message for ExtensionRegistryService.ListExtensions.
ListExtensionsResponse: Response message for ExtensionRegistryService.ListExtensions
ListFeatureGroupsRequest: Request message for FeatureRegistryService.ListFeatureGroups.
ListFeatureGroupsResponse: Response message for FeatureRegistryService.ListFeatureGroups.
ListFeatureMonitorJobsRequest: Request message for FeatureRegistryService.ListFeatureMonitorJobs.
ListFeatureMonitorJobsResponse: Response message for FeatureRegistryService.ListFeatureMonitorJobs.
ListFeatureMonitorsRequest: Request message for FeatureRegistryService.ListFeatureMonitors.
ListFeatureMonitorsResponse: Response message for FeatureRegistryService.ListFeatureMonitors.
ListFeatureOnlineStoresRequest: Request message for FeatureOnlineStoreAdminService.ListFeatureOnlineStores.
ListFeatureOnlineStoresResponse: Response message for FeatureOnlineStoreAdminService.ListFeatureOnlineStores.
ListFeaturesRequest: Request message for FeaturestoreService.ListFeatures. Request message for FeatureRegistryService.ListFeatures.
ListFeaturesResponse: Response message for FeaturestoreService.ListFeatures. Response message for FeatureRegistryService.ListFeatures.
ListFeaturestoresRequest: Request message for FeaturestoreService.ListFeaturestores.
ListFeaturestoresResponse: Response message for FeaturestoreService.ListFeaturestores.
ListFeatureViewsRequest: Request message for FeatureOnlineStoreAdminService.ListFeatureViews.
ListFeatureViewsResponse: Response message for FeatureOnlineStoreAdminService.ListFeatureViews.
ListFeatureViewSyncsRequest: Request message for FeatureOnlineStoreAdminService.ListFeatureViewSyncs.
ListFeatureViewSyncsResponse: Response message for FeatureOnlineStoreAdminService.ListFeatureViewSyncs.
ListHyperparameterTuningJobsRequest: Request message for JobService.ListHyperparameterTuningJobs.
ListHyperparameterTuningJobsResponse: Response message for JobService.ListHyperparameterTuningJobs
ListIndexEndpointsRequest: Request message for IndexEndpointService.ListIndexEndpoints.
ListIndexEndpointsResponse: Response message for IndexEndpointService.ListIndexEndpoints.
ListIndexesRequest: Request message for IndexService.ListIndexes.
ListIndexesResponse: Response message for IndexService.ListIndexes.
ListMemoriesRequest: Request message for MemoryBankService.ListMemories.
ListMemoriesResponse: Response message for MemoryBankService.ListMemories.
ListMetadataSchemasRequest: Request message for MetadataService.ListMetadataSchemas.
ListMetadataSchemasResponse: Response message for MetadataService.ListMetadataSchemas.
ListMetadataStoresRequest: Request message for MetadataService.ListMetadataStores.
ListMetadataStoresResponse: Response message for MetadataService.ListMetadataStores.
ListModelDeploymentMonitoringJobsRequest: Request message for JobService.ListModelDeploymentMonitoringJobs.
ListModelDeploymentMonitoringJobsResponse: Response message for JobService.ListModelDeploymentMonitoringJobs.
ListModelEvaluationSlicesRequest: Request message for ModelService.ListModelEvaluationSlices.
ListModelEvaluationSlicesResponse: Response message for ModelService.ListModelEvaluationSlices.
ListModelEvaluationsRequest: Request message for ModelService.ListModelEvaluations.
ListModelEvaluationsResponse: Response message for ModelService.ListModelEvaluations.
ListModelMonitoringJobsRequest: Request message for ModelMonitoringService.ListModelMonitoringJobs.
ListModelMonitoringJobsResponse: Response message for ModelMonitoringService.ListModelMonitoringJobs.
ListModelMonitorsRequest: Request message for ModelMonitoringService.ListModelMonitors.
ListModelMonitorsResponse: Response message for ModelMonitoringService.ListModelMonitors
ListModelsRequest: Request message for ModelService.ListModels.
ListModelsResponse: Response message for ModelService.ListModels
ListModelVersionCheckpointsRequest: Request message for ModelService.ListModelVersionCheckpoints.
ListModelVersionCheckpointsResponse: Response message for ModelService.ListModelVersionCheckpoints
ListModelVersionsRequest: Request message for ModelService.ListModelVersions.
ListModelVersionsResponse: Response message for ModelService.ListModelVersions
ListNasJobsRequest: Request message for JobService.ListNasJobs.
ListNasJobsResponse: Response message for JobService.ListNasJobs
ListNasTrialDetailsRequest: Request message for JobService.ListNasTrialDetails.
ListNasTrialDetailsResponse: Response message for JobService.ListNasTrialDetails
ListNotebookExecutionJobsRequest: Request message for NotebookService.ListNotebookExecutionJobs
ListNotebookExecutionJobsResponse: Response message for NotebookService.CreateNotebookExecutionJob
ListNotebookRuntimesRequest: Request message for NotebookService.ListNotebookRuntimes.
ListNotebookRuntimesResponse: Response message for NotebookService.ListNotebookRuntimes.
ListNotebookRuntimeTemplatesRequest: Request message for NotebookService.ListNotebookRuntimeTemplates.
ListNotebookRuntimeTemplatesResponse: Response message for NotebookService.ListNotebookRuntimeTemplates.
ListOptimalTrialsRequest: Request message for VizierService.ListOptimalTrials.
ListOptimalTrialsResponse: Response message for VizierService.ListOptimalTrials.
ListPersistentResourcesRequest: Request message for PersistentResourceService.ListPersistentResource.
ListPersistentResourcesResponse: Response message for PersistentResourceService.ListPersistentResources
ListPipelineJobsRequest: Request message for PipelineService.ListPipelineJobs.
ListPipelineJobsResponse: Response message for PipelineService.ListPipelineJobs
ListPublisherModelsRequest: Request message for ModelGardenService.ListPublisherModels.
ListPublisherModelsResponse: Response message for ModelGardenService.ListPublisherModels.
ListRagCorporaRequest: Request message for VertexRagDataService.ListRagCorpora.
ListRagCorporaResponse: Response message for VertexRagDataService.ListRagCorpora.
ListRagFilesRequest: Request message for VertexRagDataService.ListRagFiles.
ListRagFilesResponse: Response message for VertexRagDataService.ListRagFiles.
ListReasoningEnginesRequest: Request message for ReasoningEngineService.ListReasoningEngines.
ListReasoningEnginesResponse: Response message for ReasoningEngineService.ListReasoningEngines
ListSavedQueriesRequest: Request message for DatasetService.ListSavedQueries.
ListSavedQueriesResponse: Response message for DatasetService.ListSavedQueries.
ListSchedulesRequest: Request message for ScheduleService.ListSchedules.
ListSchedulesResponse: Response message for ScheduleService.ListSchedules
ListSessionsRequest: Request message for SessionService.ListSessions.
ListSessionsResponse: Response message for SessionService.ListSessions.
ListSpecialistPoolsRequest: Request message for SpecialistPoolService.ListSpecialistPools.
ListSpecialistPoolsResponse: Response message for SpecialistPoolService.ListSpecialistPools.
ListStudiesRequest: Request message for VizierService.ListStudies.
ListStudiesResponse: Response message for VizierService.ListStudies.
ListTensorboardExperimentsRequest: Request message for TensorboardService.ListTensorboardExperiments.
ListTensorboardExperimentsResponse: Response message for TensorboardService.ListTensorboardExperiments.
ListTensorboardRunsRequest: Request message for TensorboardService.ListTensorboardRuns.
ListTensorboardRunsResponse: Response message for TensorboardService.ListTensorboardRuns.
ListTensorboardsRequest: Request message for TensorboardService.ListTensorboards.
ListTensorboardsResponse: Response message for TensorboardService.ListTensorboards.
ListTensorboardTimeSeriesRequest: Request message for TensorboardService.ListTensorboardTimeSeries.
ListTensorboardTimeSeriesResponse: Response message for TensorboardService.ListTensorboardTimeSeries.
ListTrainingPipelinesRequest: Request message for PipelineService.ListTrainingPipelines.
ListTrainingPipelinesResponse: Response message for PipelineService.ListTrainingPipelines
ListTrialsRequest: Request message for VizierService.ListTrials.
ListTrialsResponse: Response message for VizierService.ListTrials.
ListTuningJobsRequest: Request message for GenAiTuningService.ListTuningJobs.
ListTuningJobsResponse: Response message for GenAiTuningService.ListTuningJobs
LlmUtilityService: Service for LLM related utility functions.
LogprobsResult: Logprobs Result
LogprobsResult_Candidate: Candidate for the logprobs token and score.
LogprobsResult_TopCandidates: Candidates with top log probabilities at each decoding step.
LookupStudyRequest: Request message for VizierService.LookupStudy.
MachineSpec: Specification of a single machine.
ManualBatchTuningParameters: Manual batch tuning parameters.
MatchService: MatchService is a Google managed service for efficient vector similarity search at scale.
Measurement: A message representing a Measurement of a Trial. A Measurement contains the Metrics got by executing a Trial using suggested hyperparameter values.
Measurement_Metric: A message representing a metric in the measurement.
Memory: A memory.
MemoryBankService: A service for managing memories for LLM applications.
MergeVersionAliasesRequest: Request message for ModelService.MergeVersionAliases.
MetadataSchema: Instance of a general MetadataSchema.
MetadataSchema_MetadataSchemaType: Describes the type of the MetadataSchema.
MetadataService: Service for reading and writing metadata entries.
MetadataStore: Instance of a metadata store. Contains a set of metadata that can be queried.
MetadataStore_DataplexConfig: Represents Dataplex integration settings.
MetadataStore_MetadataStoreState: Represents state information for a MetadataStore.
Metric: The metric used for dataset level evaluation.
Metric_AggregationMetric: The aggregation metrics supported by EvaluationService.EvaluateDataset.
MetricxInput: Input for MetricX metric.
MetricxInstance: Spec for MetricX instance - The fields used for evaluation are dependent on the MetricX version.
MetricxResult: Spec for MetricX result - calculates the MetricX score for the given instance using the version specified in the spec.
MetricxSpec: Spec for MetricX metric.
MetricxSpec_MetricxVersion: MetricX Version options.
MigratableResource: Represents one resource that exists in automl.googleapis.com, datalabeling.googleapis.com or ml.googleapis.com.
MigratableResource_AutomlDataset: Represents one Dataset in automl.googleapis.com.
MigratableResource_AutomlModel: Represents one Model in automl.googleapis.com.
MigratableResource_DataLabelingDataset: Represents one Dataset in datalabeling.googleapis.com.
MigratableResource_DataLabelingDataset_DataLabelingAnnotatedDataset: Represents one AnnotatedDataset in datalabeling.googleapis.com.
MigratableResource_MlEngineModelVersion: Represents one model Version in ml.googleapis.com.
MigrateResourceRequest: Config of migrating one resource from automl.googleapis.com, datalabeling.googleapis.com and ml.googleapis.com to Vertex AI.
MigrateResourceRequest_MigrateAutomlDatasetConfig: Config for migrating Dataset in automl.googleapis.com to Vertex AI's Dataset.
MigrateResourceRequest_MigrateAutomlModelConfig: Config for migrating Model in automl.googleapis.com to Vertex AI's Model.
MigrateResourceRequest_MigrateDataLabelingDatasetConfig: Config for migrating Dataset in datalabeling.googleapis.com to Vertex AI's Dataset.
MigrateResourceRequest_MigrateDataLabelingDatasetConfig_MigrateDataLabelingAnnotatedDatasetConfig: Config for migrating AnnotatedDataset in datalabeling.googleapis.com to Vertex AI's SavedQuery.
MigrateResourceRequest_MigrateMlEngineModelVersionConfig: Config for migrating version in ml.googleapis.com to Vertex AI's Model.
MigrateResourceResponse: Describes a successfully migrated resource.
MigrationService: A service that migrates resources from automl.googleapis.com, datalabeling.googleapis.com and ml.googleapis.com to Vertex AI.
Modality: Content Part modality
ModalityTokenCount: Represents token counting info for a single modality.
Model: A trained machine learning Model.
Model_BaseModelSource: User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models.
Model_DeploymentResourcesType: Identifies a type of Model's prediction resources.
Model_ExportFormat: Represents export format supported by the Model. All formats export to Google Cloud Storage.
Model_ExportFormat_ExportableContent: The Model content that can be exported.
Model_OriginalModelInfo: Contains information about the original Model if this Model is a copy.
ModelArmorConfig: Configuration for Model Armor integrations of prompt and responses.
ModelContainerSpec: Specification of a container for serving predictions. Some fields in this message correspond to fields in the Kubernetes Container v1 core specification.
ModelDeploymentMonitoringBigQueryTable: ModelDeploymentMonitoringBigQueryTable specifies the BigQuery table name as well as some information of the logs stored in this table.
ModelDeploymentMonitoringBigQueryTable_LogSource: Indicates where does the log come from.
ModelDeploymentMonitoringBigQueryTable_LogType: Indicates what type of traffic does the log belong to.
ModelDeploymentMonitoringJob: Represents a job that runs periodically to monitor the deployed models in an endpoint. It will analyze the logged training & prediction data to detect any abnormal behaviors.
ModelDeploymentMonitoringJob_LatestMonitoringPipelineMetadata: All metadata of most recent monitoring pipelines.
ModelDeploymentMonitoringJob_MonitoringScheduleState: The state to Specify the monitoring pipeline.
ModelDeploymentMonitoringObjectiveConfig: ModelDeploymentMonitoringObjectiveConfig contains the pair of deployed_model_id to ModelMonitoringObjectiveConfig.
ModelDeploymentMonitoringObjectiveType: The Model Monitoring Objective types.
ModelDeploymentMonitoringScheduleConfig: The config for scheduling monitoring job.
ModelEvaluation: A collection of metrics calculated by comparing Model's predictions on all of the test data against annotations from the test data.
ModelEvaluation_BiasConfig: Configuration for bias detection.
ModelEvaluation_ModelEvaluationExplanationSpec
ModelEvaluationSlice: A collection of metrics calculated by comparing Model's predictions on a slice of the test data against ground truth annotations.
ModelEvaluationSlice_Slice: Definition of a slice.
ModelEvaluationSlice_Slice_SliceSpec: Specification for how the data should be sliced.
ModelEvaluationSlice_Slice_SliceSpec_Range: A range of values for slice(s). low is inclusive, high is exclusive.
ModelEvaluationSlice_Slice_SliceSpec_SliceConfig: Specification message containing the config for this SliceSpec. When kind is selected as value and/or range, only a single slice will be computed. When all_values is present, a separate slice will be computed for each possible label/value for the corresponding key in config. Examples, with feature zip_code with values 12345, 23334, 88888 and feature country with values "US", "Canada", "Mexico" in the dataset:
ModelEvaluationSlice_Slice_SliceSpec_Value: Single value that supports strings and floats.
ModelExplanation: Aggregated explanation metrics for a Model over a set of instances.
ModelGardenService: The interface of Model Garden Service.
ModelGardenSource: Contains information about the source of the models generated from Model Garden.
ModelMonitor: Vertex AI Model Monitoring Service serves as a central hub for the analysis and visualization of data quality and performance related to models. ModelMonitor stands as a top level resource for overseeing your model monitoring tasks.
ModelMonitor_ModelMonitoringTarget: The monitoring target refers to the entity that is subject to analysis. e.g. Vertex AI Model version.
ModelMonitor_ModelMonitoringTarget_VertexModelSource: Model in Vertex AI Model Registry.
ModelMonitoringAlert: Represents a single monitoring alert. This is currently used in the SearchModelMonitoringAlerts api, thus the alert wrapped in this message belongs to the resource asked in the request.
ModelMonitoringAlertCondition: Monitoring alert triggered condition.
ModelMonitoringAlertConfig: The alert config for model monitoring.
ModelMonitoringAlertConfig_EmailAlertConfig: The config for email alert.
ModelMonitoringAnomaly: Represents a single model monitoring anomaly.
ModelMonitoringAnomaly_TabularAnomaly: Tabular anomaly details.
ModelMonitoringConfig: The model monitoring configuration used for Batch Prediction Job.
ModelMonitoringInput: Model monitoring data input spec.
ModelMonitoringInput_BatchPredictionOutput: Data from Vertex AI Batch prediction job output.
ModelMonitoringInput_ModelMonitoringDataset: Input dataset spec.
ModelMonitoringInput_ModelMonitoringDataset_ModelMonitoringBigQuerySource: Dataset spec for data sotred in BigQuery.
ModelMonitoringInput_ModelMonitoringDataset_ModelMonitoringGcsSource: Dataset spec for data stored in Google Cloud Storage.
ModelMonitoringInput_ModelMonitoringDataset_ModelMonitoringGcsSource_DataFormat: Supported data format.
ModelMonitoringInput_TimeOffset: Time offset setting.
ModelMonitoringInput_VertexEndpointLogs: Data from Vertex AI Endpoint request response logging.
ModelMonitoringJob: Represents a model monitoring job that analyze dataset using different monitoring algorithm.
ModelMonitoringJobExecutionDetail: Represent the execution details of the job.
ModelMonitoringJobExecutionDetail_ProcessedDataset: Processed dataset information.
ModelMonitoringNotificationSpec: Notification spec(email, notification channel) for model monitoring statistics/alerts.
ModelMonitoringNotificationSpec_EmailConfig: The config for email alerts.
ModelMonitoringNotificationSpec_NotificationChannelConfig: Google Cloud Notification Channel config.
ModelMonitoringObjectiveConfig: The objective configuration for model monitoring, including the information needed to detect anomalies for one particular model.
ModelMonitoringObjectiveConfig_ExplanationConfig: The config for integrating with Vertex Explainable AI. Only applicable if the Model has explanation_spec populated.
ModelMonitoringObjectiveConfig_ExplanationConfig_ExplanationBaseline: Output from BatchPredictionJob for Model Monitoring baseline dataset, which can be used to generate baseline attribution scores.
ModelMonitoringObjectiveConfig_ExplanationConfig_ExplanationBaseline_PredictionFormat: The storage format of the predictions generated BatchPrediction job.
ModelMonitoringObjectiveConfig_PredictionDriftDetectionConfig: The config for Prediction data drift detection.
ModelMonitoringObjectiveConfig_TrainingDataset: Training Dataset information.
ModelMonitoringObjectiveConfig_TrainingPredictionSkewDetectionConfig: The config for Training & Prediction data skew detection. It specifies the training dataset sources and the skew detection parameters.
ModelMonitoringObjectiveSpec: Monitoring objectives spec.
ModelMonitoringObjectiveSpec_DataDriftSpec: Data drift monitoring spec. Data drift measures the distribution distance between the current dataset and a baseline dataset. A typical use case is to detect data drift between the recent production serving dataset and the training dataset, or to compare the recent production dataset with a dataset from a previous period.
ModelMonitoringObjectiveSpec_FeatureAttributionSpec: Feature attribution monitoring spec.
ModelMonitoringObjectiveSpec_TabularObjective: Tabular monitoring objective.
ModelMonitoringOutputSpec: Specification for the export destination of monitoring results, including metrics, logs, etc.
ModelMonitoringSchema: The Model Monitoring Schema definition.
ModelMonitoringSchema_FieldSchema: Schema field definition.
ModelMonitoringService: A service for creating and managing Vertex AI Model moitoring. This includes ModelMonitor resources, ModelMonitoringJob resources.
ModelMonitoringSpec: Monitoring monitoring job spec. It outlines the specifications for monitoring objectives, notifications, and result exports.
ModelMonitoringStats: Represents the collection of statistics for a metric.
ModelMonitoringStatsAnomalies: Statistics and anomalies generated by Model Monitoring.
ModelMonitoringStatsAnomalies_FeatureHistoricStatsAnomalies: Historical Stats (and Anomalies) for a specific Feature.
ModelMonitoringStatsDataPoint: Represents a single statistics data point.
ModelMonitoringStatsDataPoint_TypedValue: Typed value of the statistics.
ModelMonitoringStatsDataPoint_TypedValue_DistributionDataValue: Summary statistics for a population of values.
ModelMonitoringTabularStats: A collection of data points that describes the time-varying values of a tabular metric.
ModelService: A service for managing Vertex AI's machine learning Models.
ModelSourceInfo: Detail description of the source information of the model.
ModelSourceInfo_ModelSourceType: Source of the model. Different from objective field, this ModelSourceType enum indicates the source from which the model was accessed or obtained, whereas the objective indicates the overall aim or function of this model.
ModelVersionCheckpoint: A proto representation of a Spanner-stored ModelVersionCheckpoint. The meaning of the fields is equivalent to their in-Spanner counterparts.
MutateDeployedIndexOperationMetadata: Runtime operation information for IndexEndpointService.MutateDeployedIndex.
MutateDeployedIndexRequest: Request message for IndexEndpointService.MutateDeployedIndex.
MutateDeployedIndexResponse: Response message for IndexEndpointService.MutateDeployedIndex.
MutateDeployedModelOperationMetadata: Runtime operation information for EndpointService.MutateDeployedModel.
MutateDeployedModelRequest: Request message for EndpointService.MutateDeployedModel.
MutateDeployedModelResponse: Response message for EndpointService.MutateDeployedModel.
NasJob: Represents a Neural Architecture Search (NAS) job.
NasJobOutput: Represents a uCAIP NasJob output.
NasJobOutput_MultiTrialJobOutput: The output of a multi-trial Neural Architecture Search (NAS) jobs.
NasJobSpec: Represents the spec of a NasJob.
NasJobSpec_MultiTrialAlgorithmSpec: The spec of multi-trial Neural Architecture Search (NAS).
NasJobSpec_MultiTrialAlgorithmSpec_MetricSpec: Represents a metric to optimize.
NasJobSpec_MultiTrialAlgorithmSpec_MetricSpec_GoalType: The available types of optimization goals.
NasJobSpec_MultiTrialAlgorithmSpec_MultiTrialAlgorithm: The available types of multi-trial algorithms.
NasJobSpec_MultiTrialAlgorithmSpec_SearchTrialSpec: Represent spec for search trials.
NasJobSpec_MultiTrialAlgorithmSpec_TrainTrialSpec: Represent spec for train trials.
NasTrial: Represents a uCAIP NasJob trial.
NasTrial_State: Describes a NasTrial state.
NasTrialDetail: Represents a NasTrial details along with its parameters. If there is a corresponding train NasTrial, the train NasTrial is also returned.
NearestNeighborQuery: A query to find a number of similar entities.
NearestNeighborQuery_Embedding: The embedding vector.
NearestNeighborQuery_NumericFilter: Numeric filter is used to search a subset of the entities by using boolean rules on numeric columns. For example: Database Point 0: {name: “a” value_int: 42} {name: “b” value_float: 1.0} Database Point 1: {name: “a” value_int: 10} {name: “b” value_float: 2.0} Database Point 2: {name: “a” value_int: -1} {name: “b” value_float: 3.0} Query: {name: “a” value_int: 12 operator: LESS} // Matches Point 1, 2 {name: “b” value_float: 2.0 operator: EQUAL} // Matches Point 1
NearestNeighborQuery_NumericFilter_Operator: Datapoints for which Operator is true relative to the query’s Value field will be allowlisted.
NearestNeighborQuery_Parameters: Parameters that can be overrided in each query to tune query latency and recall.
NearestNeighborQuery_StringFilter: String filter is used to search a subset of the entities by using boolean rules on string columns. For example: if a query specifies string filter with 'name = color, allow_tokens = {red, blue}, deny_tokens = {purple}',' then that query will match entities that are red or blue, but if those points are also purple, then they will be excluded even if they are red/blue. Only string filter is supported for now, numeric filter will be supported in the near future.
NearestNeighbors: Nearest neighbors for one query.
NearestNeighbors_Neighbor: A neighbor of the query vector.
NearestNeighborSearchOperationMetadata: Runtime operation metadata with regard to Matching Engine Index.
NearestNeighborSearchOperationMetadata_ContentValidationStats
NearestNeighborSearchOperationMetadata_RecordError
NearestNeighborSearchOperationMetadata_RecordError_RecordErrorType
Neighbor: Neighbors for example-based explanations.
NetworkSpec: Network spec.
NfsMount: Represents a mount configuration for Network File System (NFS) to mount.
NotebookEucConfig: The euc configuration of NotebookRuntimeTemplate.
NotebookExecutionJob: NotebookExecutionJob represents an instance of a notebook execution.
NotebookExecutionJob_CustomEnvironmentSpec: Compute configuration to use for an execution job.
NotebookExecutionJob_DataformRepositorySource: The Dataform Repository containing the input notebook.
NotebookExecutionJob_DirectNotebookSource: The content of the input notebook in ipynb format.
NotebookExecutionJob_GcsNotebookSource: The Cloud Storage uri for the input notebook.
NotebookExecutionJob_WorkbenchRuntime: Configuration for a Workbench Instances-based environment.
NotebookExecutionJobView: Views for Get/List NotebookExecutionJob
NotebookIdleShutdownConfig: The idle shutdown configuration of NotebookRuntimeTemplate, which contains the idle_timeout as required field.
NotebookRuntime: A runtime is a virtual machine allocated to a particular user for a particular Notebook file on temporary basis with lifetime. Default runtimes have a lifetime of 18 hours, while custom runtimes last for 6 months from their creation or last upgrade.
NotebookRuntime_HealthState: The substate of the NotebookRuntime to display health information.
NotebookRuntime_RuntimeState: The substate of the NotebookRuntime to display state of runtime. The resource of NotebookRuntime is in ACTIVE state for these sub state.
NotebookRuntimeTemplate: A template that specifies runtime configurations such as machine type, runtime version, network configurations, etc. Multiple runtimes can be created from a runtime template.
NotebookRuntimeTemplateRef: Points to a NotebookRuntimeTemplateRef.
NotebookRuntimeType: Represents a notebook runtime type.
NotebookService: The interface for Vertex Notebook service (a.k.a. Colab on Workbench).
NotebookSoftwareConfig: Notebook Software Config. This is passed to the backend when user makes software configurations in UI.
OutputConfig: Config for evaluation output.
OutputInfo: Describes the info for output of EvaluationService.EvaluateDataset.
PairwiseChoice: Pairwise prediction autorater preference.
PairwiseMetricInput: Input for pairwise metric.
PairwiseMetricInstance: Pairwise metric instance. Usually one instance corresponds to one row in an evaluation dataset.
PairwiseMetricResult: Spec for pairwise metric result.
PairwiseMetricSpec: Spec for pairwise metric.
PairwiseQuestionAnsweringQualityInput: Input for pairwise question answering quality metric.
PairwiseQuestionAnsweringQualityInstance: Spec for pairwise question answering quality instance.
PairwiseQuestionAnsweringQualityResult: Spec for pairwise question answering quality result.
PairwiseQuestionAnsweringQualitySpec: Spec for pairwise question answering quality score metric.
PairwiseSummarizationQualityInput: Input for pairwise summarization quality metric.
PairwiseSummarizationQualityInstance: Spec for pairwise summarization quality instance.
PairwiseSummarizationQualityResult: Spec for pairwise summarization quality result.
PairwiseSummarizationQualitySpec: Spec for pairwise summarization quality score metric.
Part: A datatype containing media that is part of a multi-part Content message.
PartnerModelTuningSpec: Tuning spec for Partner models.
PauseModelDeploymentMonitoringJobRequest: Request message for JobService.PauseModelDeploymentMonitoringJob.
PauseScheduleRequest: Request message for ScheduleService.PauseSchedule.
PersistentDiskSpec: Represents the spec of https://cloud.google.com/compute/docs/disks/persistent-disks options.
PersistentResource: Represents long-lasting resources that are dedicated to users to runs custom workloads. A PersistentResource can have multiple node pools and each node pool can have its own machine spec.
PersistentResource_State: Describes the PersistentResource state.
PersistentResourceService: A service for managing Vertex AI's machine learning PersistentResource.
PipelineFailurePolicy: Represents the failure policy of a pipeline. Currently, the default of a pipeline is that the pipeline will continue to run until no more tasks can be executed, also known as PIPELINE_FAILURE_POLICY_FAIL_SLOW. However, if a pipeline is set to PIPELINE_FAILURE_POLICY_FAIL_FAST, it will stop scheduling any new tasks when a task has failed. Any scheduled tasks will continue to completion.
PipelineJob: An instance of a machine learning PipelineJob.
PipelineJob_RuntimeConfig: The runtime config of a PipelineJob.
PipelineJob_RuntimeConfig_DefaultRuntime: The default runtime for the PipelineJob.
PipelineJob_RuntimeConfig_InputArtifact: The type of an input artifact.
PipelineJob_RuntimeConfig_PersistentResourceRuntimeDetail: Persistent resource based runtime detail. For more information, refer to https://cloud.google.com/vertex-ai/docs/training/persistent-resource-overview
PipelineJob_RuntimeConfig_PersistentResourceRuntimeDetail_TaskResourceUnavailableTimeoutBehavior: An enum that specifies the behavior to take if the timeout is reached.
PipelineJobDetail: The runtime detail of PipelineJob.
PipelineService: A service for creating and managing Vertex AI's pipelines. This includes both TrainingPipeline resources (used for AutoML and custom training) and PipelineJob resources (used for Vertex AI Pipelines).
PipelineState: Describes the state of a pipeline.
PipelineTaskDetail: The runtime detail of a task execution.
PipelineTaskDetail_ArtifactList: A list of artifact metadata.
PipelineTaskDetail_PipelineTaskStatus: A single record of the task status.
PipelineTaskDetail_State: Specifies state of TaskExecution
PipelineTaskExecutorDetail: The runtime detail of a pipeline executor.
PipelineTaskExecutorDetail_ContainerDetail: The detail of a container execution. It contains the job names of the lifecycle of a container execution.
PipelineTaskExecutorDetail_CustomJobDetail: The detailed info for a custom job executor.
PipelineTaskRerunConfig: User provided rerun config to submit a rerun pipelinejob. This includes
PipelineTaskRerunConfig_ArtifactList: A list of artifact metadata.
PipelineTaskRerunConfig_Inputs: Runtime inputs data of the task.
PipelineTemplateMetadata: Pipeline template metadata if PipelineJob.template_uri is from supported template registry. Currently, the only supported registry is Artifact Registry.
PointwiseMetricInput: Input for pointwise metric.
PointwiseMetricInstance: Pointwise metric instance. Usually one instance corresponds to one row in an evaluation dataset.
PointwiseMetricResult: Spec for pointwise metric result.
PointwiseMetricSpec: Spec for pointwise metric.
Port: Represents a network port in a container.
PostStartupScriptConfig
PostStartupScriptConfig_PostStartupScriptBehavior
PrebuiltVoiceConfig: The configuration for the prebuilt speaker to use.
PredefinedSplit: Assigns input data to training, validation, and test sets based on the value of a provided key.
PredictionService: A service for online predictions and explanations.
PredictLongRunningMetadata: Metadata for PredictLongRunning long running operations.
PredictLongRunningResponse: Response message for PredictionService.PredictLongRunning
PredictRequest: Request message for PredictionService.Predict.
PredictRequestResponseLoggingConfig: Configuration for logging request-response to a BigQuery table.
PredictResponse: Response message for PredictionService.Predict.
PredictSchemata: Contains the schemata used in Model's predictions and explanations via PredictionService.Predict, PredictionService.Explain and BatchPredictionJob.
Presets: Preset configuration for example-based explanations
Presets_Modality: Preset option controlling parameters for different modalities
Presets_Query: Preset option controlling parameters for query speed-precision trade-off
PreTunedModel: A pre-tuned model for continuous tuning.
PrivateEndpoints: PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predict_http_uri, explain_http_uri or health_http_uri. To send request via private service connect, use service_attachment.
PrivateServiceConnectConfig: Represents configuration for private service connect.
Probe: Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic.
Probe_ExecAction: ExecAction specifies a command to execute.
Probe_GrpcAction: GrpcAction checks the health of a container using a gRPC service.
Probe_HttpGetAction: HttpGetAction describes an action based on HTTP Get requests.
Probe_HttpHeader: HttpHeader describes a custom header to be used in HTTP probes
Probe_TcpSocketAction: TcpSocketAction probes the health of a container by opening a TCP socket connection.
PscAutomatedEndpoints: PscAutomatedEndpoints defines the output of the forwarding rule automatically created by each PscAutomationConfig.
PscautomationConfig: PSC config that is used to automatically create PSC endpoints in the user projects.
PscautomationState: The state of the PSC service automation.
PscInterfaceConfig: Configuration for PSC-I.
PublisherModel: A Model Garden Publisher Model.
PublisherModel_CallToAction: Actions could take on this Publisher Model.
PublisherModel_CallToAction_Deploy: Model metadata that is needed for UploadModel or DeployModel/CreateEndpoint requests.
PublisherModel_CallToAction_Deploy_DeployMetadata: Metadata information about the deployment for managing deployment config.
PublisherModel_CallToAction_DeployGke: Configurations for PublisherModel GKE deployment
PublisherModel_CallToAction_DeployVertex: Multiple setups to deploy the PublisherModel.
PublisherModel_CallToAction_OpenFineTuningPipelines: Open fine tuning pipelines.
PublisherModel_CallToAction_OpenNotebooks: Open notebooks.
PublisherModel_CallToAction_RegionalResourceReferences: The regional resource name or the URI. Key is region, e.g., us-central1, europe-west2, global, etc..
PublisherModel_CallToAction_ViewRestApi: Rest API docs.
PublisherModel_Documentation: A named piece of documentation.
PublisherModel_LaunchStage: An enum representing the launch stage of a PublisherModel.
PublisherModel_OpenSourceCategory: An enum representing the open source category of a PublisherModel.
PublisherModel_Parent: The information about the parent of a model.
PublisherModel_ResourceReference: Reference to a resource.
PublisherModel_VersionState: An enum representing the state of the PublicModelVersion.
PublisherModelConfig: This message contains configs of a publisher model.
PublisherModelEulaAcceptance: Response message for ModelGardenService.UpdatePublisherModelEula.
PublisherModelView: View enumeration of PublisherModel.
PurgeArtifactsMetadata: Details of operations that perform MetadataService.PurgeArtifacts.
PurgeArtifactsRequest: Request message for MetadataService.PurgeArtifacts.
PurgeArtifactsResponse: Response message for MetadataService.PurgeArtifacts.
PurgeContextsMetadata: Details of operations that perform MetadataService.PurgeContexts.
PurgeContextsRequest: Request message for MetadataService.PurgeContexts.
PurgeContextsResponse: Response message for MetadataService.PurgeContexts.
PurgeExecutionsMetadata: Details of operations that perform MetadataService.PurgeExecutions.
PurgeExecutionsRequest: Request message for MetadataService.PurgeExecutions.
PurgeExecutionsResponse: Response message for MetadataService.PurgeExecutions.
PythonPackageSpec: The spec of a Python packaged code.
QueryArtifactLineageSubgraphRequest: Request message for MetadataService.QueryArtifactLineageSubgraph.
QueryContextLineageSubgraphRequest: Request message for MetadataService.QueryContextLineageSubgraph.
QueryDeployedModelsRequest: Request message for QueryDeployedModels method.
QueryDeployedModelsResponse: Response message for QueryDeployedModels method.
QueryExecutionInputsAndOutputsRequest: Request message for MetadataService.QueryExecutionInputsAndOutputs.
QueryExtensionRequest: Request message for ExtensionExecutionService.QueryExtension.
QueryExtensionResponse: Response message for ExtensionExecutionService.QueryExtension.
QueryReasoningEngineRequest: Request message for ReasoningEngineExecutionService.Query.
QueryReasoningEngineResponse: Response message for ReasoningEngineExecutionService.Query
QuestionAnsweringCorrectnessInput: Input for question answering correctness metric.
QuestionAnsweringCorrectnessInstance: Spec for question answering correctness instance.
QuestionAnsweringCorrectnessResult: Spec for question answering correctness result.
QuestionAnsweringCorrectnessSpec: Spec for question answering correctness metric.
QuestionAnsweringHelpfulnessInput: Input for question answering helpfulness metric.
QuestionAnsweringHelpfulnessInstance: Spec for question answering helpfulness instance.
QuestionAnsweringHelpfulnessResult: Spec for question answering helpfulness result.
QuestionAnsweringHelpfulnessSpec: Spec for question answering helpfulness metric.
QuestionAnsweringQualityInput: Input for question answering quality metric.
QuestionAnsweringQualityInstance: Spec for question answering quality instance.
QuestionAnsweringQualityResult: Spec for question answering quality result.
QuestionAnsweringQualitySpec: Spec for question answering quality score metric.
QuestionAnsweringRelevanceInput: Input for question answering relevance metric.
QuestionAnsweringRelevanceInstance: Spec for question answering relevance instance.
QuestionAnsweringRelevanceResult: Spec for question answering relevance result.
QuestionAnsweringRelevanceSpec: Spec for question answering relevance metric.
RagChunk: A RagChunk includes the content of a chunk of a RagFile, and associated metadata.
RagChunk_PageSpan: Represents where the chunk starts and ends in the document.
RagContexts: Relevant contexts for one query.
RagContexts_Context: A context of the query.
RagCorpus: A RagCorpus is a RagFile container and a project can have multiple RagCorpora.
RagCorpus_CorpusTypeConfig: The config for the corpus type of the RagCorpus.
RagCorpus_CorpusTypeConfig_DocumentCorpus: Config for the document corpus.
RagCorpus_CorpusTypeConfig_MemoryCorpus: Config for the memory corpus.
RagEmbeddingModelConfig: Config for the embedding model to use for RAG.
RagEmbeddingModelConfig_HybridSearchConfig: Config for hybrid search.
RagEmbeddingModelConfig_SparseEmbeddingConfig: Configuration for sparse emebdding generation.
RagEmbeddingModelConfig_SparseEmbeddingConfig_Bm25: Message for BM25 parameters.
RagEmbeddingModelConfig_VertexPredictionEndpoint: Config representing a model hosted on Vertex Prediction Endpoint.
RagEngineConfig: Config for RagEngine.
RagFile: A RagFile contains user data for chunking, embedding and indexing.
RagFile_RagFileType: The type of the RagFile.
RagFileChunkingConfig: Specifies the size and overlap of chunks for RagFiles.
RagFileChunkingConfig_FixedLengthChunking: Specifies the fixed length chunking config.
RagFileMetadataConfig: Metadata config for RagFile.
RagFileParsingConfig: Specifies the parsing config for RagFiles.
RagFileParsingConfig_AdvancedParser: Specifies the advanced parsing for RagFiles.
RagFileParsingConfig_LayoutParser: Document AI Layout Parser config.
RagFileParsingConfig_LlmParser: Specifies the LLM parsing for RagFiles.
RagFileTransformationConfig: Specifies the transformation config for RagFiles.
RagManagedDbConfig: Configuration message for RagManagedDb used by RagEngine.
RagManagedDbConfig_Basic: Basic tier is a cost-effective and low compute tier suitable for the following cases:
RagManagedDbConfig_Enterprise: Deprecated: Please use Scaled tier instead. Enterprise tier offers production grade performance along with autoscaling functionality. It is suitable for customers with large amounts of data or performance sensitive workloads.
RagManagedDbConfig_Scaled: Scaled tier offers production grade performance along with autoscaling functionality. It is suitable for customers with large amounts of data or performance sensitive workloads.
RagManagedDbConfig_Unprovisioned: Disables the RAG Engine service and deletes all your data held within this service. This will halt the billing of the service.
RagQuery: A query to retrieve relevant contexts.
RagQuery_Ranking: Configurations for hybrid search results ranking.
RagRetrievalConfig: Specifies the context retrieval config.
RagRetrievalConfig_Filter: Config for filters.
RagRetrievalConfig_HybridSearch: Config for Hybrid Search.
RagRetrievalConfig_Ranking: Config for ranking and reranking.
RagRetrievalConfig_Ranking_LlmRanker: Config for LlmRanker.
RagRetrievalConfig_Ranking_RankService: Config for Rank Service.
RagVectorDbConfig: Config for the Vector DB to use for RAG.
RagVectorDbConfig_Pinecone: The config for the Pinecone.
RagVectorDbConfig_RagManagedDb: The config for the default RAG-managed Vector DB.
RagVectorDbConfig_RagManagedDb_Ann: Config for ANN search.
RagVectorDbConfig_RagManagedDb_Knn: Config for KNN search.
RagVectorDbConfig_VertexFeatureStore: The config for the Vertex Feature Store.
RagVectorDbConfig_VertexVectorSearch: The config for the Vertex Vector Search.
RagVectorDbConfig_Weaviate: The config for the Weaviate.
RawOutput: Raw output.
RawPredictRequest: Request message for PredictionService.RawPredict.
RayLogsSpec: Configuration for the Ray OSS Logs.
RayMetricSpec: Configuration for the Ray metrics.
RaySpec: Configuration information for the Ray cluster. For experimental launch, Ray cluster creation and Persistent cluster creation are 1:1 mapping: We will provision all the nodes within the Persistent cluster as Ray nodes.
ReadFeatureValuesRequest: Request message for FeaturestoreOnlineServingService.ReadFeatureValues.
ReadFeatureValuesResponse: Response message for FeaturestoreOnlineServingService.ReadFeatureValues.
ReadFeatureValuesResponse_EntityView: Entity view with Feature values.
ReadFeatureValuesResponse_EntityView_Data: Container to hold value(s), successive in time, for one Feature from the request.
ReadFeatureValuesResponse_FeatureDescriptor: Metadata for requested Features.
ReadFeatureValuesResponse_Header: Response header with metadata for the requested ReadFeatureValuesRequest.entity_type and Features.
ReadIndexDatapointsRequest: The request message for MatchService.ReadIndexDatapoints.
ReadIndexDatapointsResponse: The response message for MatchService.ReadIndexDatapoints.
ReadTensorboardBlobDataRequest: Request message for TensorboardService.ReadTensorboardBlobData.
ReadTensorboardBlobDataResponse: Response message for TensorboardService.ReadTensorboardBlobData.
ReadTensorboardSizeRequest: Request message for TensorboardService.ReadTensorboardSize.
ReadTensorboardSizeResponse: Response message for TensorboardService.ReadTensorboardSize.
ReadTensorboardTimeSeriesDataRequest: Request message for TensorboardService.ReadTensorboardTimeSeriesData.
ReadTensorboardTimeSeriesDataResponse: Response message for TensorboardService.ReadTensorboardTimeSeriesData.
ReadTensorboardUsageRequest: Request message for TensorboardService.ReadTensorboardUsage.
ReadTensorboardUsageResponse: Response message for TensorboardService.ReadTensorboardUsage.
ReadTensorboardUsageResponse_PerMonthUsageData: Per month usage data
ReadTensorboardUsageResponse_PerUserUsageData: Per user usage data.
ReasoningEngine: ReasoningEngine provides a customizable runtime for models to determine which actions to take and in which order.
ReasoningEngineContextSpec: Configuration for how Agent Engine sub-resources should manage context.
ReasoningEngineContextSpec_MemoryBankConfig: Specification for a Memory Bank.
ReasoningEngineContextSpec_MemoryBankConfig_GenerationConfig: Configuration for how to generate memories.
ReasoningEngineContextSpec_MemoryBankConfig_SimilaritySearchConfig: Configuration for how to perform similarity search on memories.
ReasoningEngineContextSpec_MemoryBankConfig_TtlConfig: Configuration for automatically setting the TTL ("time-to-live") of the memories in the Memory Bank.
ReasoningEngineContextSpec_MemoryBankConfig_TtlConfig_GranularTtlConfig: Configuration for TTL of the memories in the Memory Bank based on the action that created or updated the memory.
ReasoningEngineExecutionService: A service for executing queries on Reasoning Engine.
ReasoningEngineService: A service for managing Vertex AI's Reasoning Engines.
ReasoningEngineSpec: ReasoningEngine configurations
ReasoningEngineSpec_DeploymentSpec: The specification of a Reasoning Engine deployment.
ReasoningEngineSpec_PackageSpec: User-provided package specification, containing pickled object and package requirements.
ReasoningEngineSpec_SourceCodeSpec: Specification for deploying from source code.
ReasoningEngineSpec_SourceCodeSpec_InlineSource: Specifies source code provided as a byte stream.
ReasoningEngineSpec_SourceCodeSpec_PythonSpec: Specification for running a Python application from source.
RebaseTunedModelOperationMetadata: Runtime operation information for GenAiTuningService.RebaseTunedModel.
RebaseTunedModelRequest: Request message for GenAiTuningService.RebaseTunedModel.
RebootPersistentResourceOperationMetadata: Details of operations that perform reboot PersistentResource.
RebootPersistentResourceRequest: Request message for PersistentResourceService.RebootPersistentResource.
RecommendSpecRequest: Request message for ModelService.RecommendSpec.
RecommendSpecResponse: Response message for ModelService.RecommendSpec.
RecommendSpecResponse_MachineAndModelContainerSpec: A machine and model container spec.
RecommendSpecResponse_Recommendation: Recommendation of one deployment option for the given custom weights model in one region. Contains the machine and container spec, and user accelerator quota state.
RecommendSpecResponse_Recommendation_QuotaState: The user accelerator quota state.
RemoveContextChildrenRequest: Request message for MetadataService.DeleteContextChildrenRequest.
RemoveContextChildrenResponse: Response message for MetadataService.RemoveContextChildren.
RemoveDatapointsRequest: Request message for IndexService.RemoveDatapoints
RemoveDatapointsResponse: Response message for IndexService.RemoveDatapoints
RemoveExamplesRequest: Request message for ExampleStoreService.RemoveExamples.
RemoveExamplesResponse: Response message for ExampleStoreService.RemoveExamples.
ReservationAffinity: A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity.
ReservationAffinity_Type: Identifies a type of reservation affinity.
ResourcePool: Represents the spec of a group of resources of the same type, for example machine type, disk, and accelerators, in a PersistentResource.
ResourcePool_AutoscalingSpec: The min/max number of replicas allowed if enabling autoscaling
ResourceRuntime: Persistent Cluster runtime information as output
ResourceRuntimeSpec: Configuration for the runtime on a PersistentResource instance, including but not limited to:
ResourcesConsumed: Statistics information about resource consumption.
RestoreDatasetVersionOperationMetadata: Runtime operation information for DatasetService.RestoreDatasetVersion.
RestoreDatasetVersionRequest: Request message for DatasetService.RestoreDatasetVersion.
ResumeModelDeploymentMonitoringJobRequest: Request message for JobService.ResumeModelDeploymentMonitoringJob.
ResumeScheduleRequest: Request message for ScheduleService.ResumeSchedule.
Retrieval: Defines a retrieval tool that model can call to access external knowledge.
RetrievalConfig: Retrieval config.
RetrievalMetadata: Metadata related to retrieval in the grounding flow.
RetrieveContextsRequest: Request message for VertexRagService.RetrieveContexts.
RetrieveContextsRequest_VertexRagStore: The data source for Vertex RagStore.
RetrieveContextsRequest_VertexRagStore_RagResource: The definition of the Rag resource.
RetrieveContextsResponse: Response message for VertexRagService.RetrieveContexts.
RetrieveMemoriesRequest: Request message for MemoryBankService.RetrieveMemories.
RetrieveMemoriesRequest_SimilaritySearchParams: Parameters for semantic similarity search based retrieval.
RetrieveMemoriesRequest_SimpleRetrievalParams: Parameters for simple (non-similarity search) retrieval.
RetrieveMemoriesResponse: Response message for MemoryBankService.RetrieveMemories.
RetrieveMemoriesResponse_RetrievedMemory: A retrieved memory.
RolloutOptions: Configuration for rolling deployments.
RougeInput: Input for rouge metric.
RougeInstance: Spec for rouge instance.
RougeMetricValue: Rouge metric value for an instance.
RougeResults: Results for rouge metric.
RougeSpec: Spec for rouge score metric - calculates the recall of n-grams in prediction as compared to reference - returns a score ranging between 0 and 1.
RubricBasedInstructionFollowingInput: Instance and metric spec for RubricBasedInstructionFollowing metric.
RubricBasedInstructionFollowingInstance: Instance for RubricBasedInstructionFollowing metric - one instance corresponds to one row in an evaluation dataset.
RubricBasedInstructionFollowingResult: Result for RubricBasedInstructionFollowing metric.
RubricBasedInstructionFollowingSpec: Spec for RubricBasedInstructionFollowing metric - returns rubrics and verdicts corresponding to rubrics along with overall score.
RubricCritiqueResult: Rubric critique result.
RuntimeArtifact: The definition of a runtime artifact.
RuntimeConfig: Runtime configuration to run the extension.
RuntimeConfig_CodeInterpreterRuntimeConfig
RuntimeConfig_VertexAisearchRuntimeConfig
SafetyInput: Input for safety metric.
SafetyInstance: Spec for safety instance.
SafetyRating: Safety rating corresponding to the generated content.
SafetyRating_HarmProbability: Harm probability levels in the content.
SafetyRating_HarmSeverity: Harm severity levels.
SafetyResult: Spec for safety result.
SafetySetting: Safety settings.
SafetySetting_HarmBlockMethod: Probability vs severity.
SafetySetting_HarmBlockThreshold: Probability based thresholds levels for blocking.
SafetySpec: Spec for safety metric.
SampleConfig: Active learning data sampling config. For every active learning labeling iteration, it will select a batch of data based on the sampling strategy.
SampleConfig_SampleStrategy: Sample strategy decides which subset of DataItems should be selected for human labeling in every batch.
SampledShapleyAttribution: An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
SamplingStrategy: Sampling Strategy for logging, can be for both training and prediction dataset.
SamplingStrategy_RandomSampleConfig: Requests are randomly selected.
SavedQuery: A SavedQuery is a view of the dataset. It references a subset of annotations by problem type and filters.
Scalar: One point viewable on a scalar metric plot.
Schedule: An instance of a Schedule periodically schedules runs to make API calls based on user specified time specification and API request type.
Schedule_RunResponse: Status of a scheduled run.
Schedule_State: Possible state of the schedule.
ScheduleConfig: Schedule configuration for the FeatureMonitor.
ScheduleService: A service for creating and managing Vertex AI's Schedule resources to periodically launch shceudled runs to make API calls.
Scheduling: All parameters related to queuing and scheduling of custom jobs.
Scheduling_Strategy: Optional. This determines which type of scheduling strategy to use. Right now users have two options such as STANDARD which will use regular on demand resources to schedule the job, the other is SPOT which would leverage spot resources alongwith regular resources to schedule the job.
Schema: Schema is used to define the format of input/output data. Represents a select subset of an OpenAPI 3.0 schema object. More fields may be added in the future as needed.
SearchDataItemsRequest: Request message for DatasetService.SearchDataItems.
SearchDataItemsRequest_OrderByAnnotation: Expression that allows ranking results based on annotation's property.
SearchDataItemsResponse: Response message for DatasetService.SearchDataItems.
SearchEntryPoint: Google search entry point.
SearchExamplesRequest: Request message for ExampleStoreService.SearchExamples.
SearchExamplesResponse: Response message for ExampleStoreService.SearchExamples.
SearchExamplesResponse_SimilarExample: The result of the similar example.
SearchFeaturesRequest: Request message for FeaturestoreService.SearchFeatures.
SearchFeaturesResponse: Response message for FeaturestoreService.SearchFeatures.
SearchMigratableResourcesRequest: Request message for MigrationService.SearchMigratableResources.
SearchMigratableResourcesResponse: Response message for MigrationService.SearchMigratableResources.
SearchModelDeploymentMonitoringStatsAnomaliesRequest: Request message for JobService.SearchModelDeploymentMonitoringStatsAnomalies.
SearchModelDeploymentMonitoringStatsAnomaliesRequest_StatsAnomaliesObjective: Stats requested for specific objective.
SearchModelDeploymentMonitoringStatsAnomaliesResponse: Response message for JobService.SearchModelDeploymentMonitoringStatsAnomalies.
SearchModelMonitoringAlertsRequest: Request message for ModelMonitoringService.SearchModelMonitoringAlerts.
SearchModelMonitoringAlertsResponse: Response message for ModelMonitoringService.SearchModelMonitoringAlerts.
SearchModelMonitoringStatsFilter: Filter for searching ModelMonitoringStats.
SearchModelMonitoringStatsFilter_TabularStatsFilter: Tabular statistics filter.
SearchModelMonitoringStatsRequest: Request message for ModelMonitoringService.SearchModelMonitoringStats.
SearchModelMonitoringStatsResponse: Response message for ModelMonitoringService.SearchModelMonitoringStats.
SearchNearestEntitiesRequest: The request message for FeatureOnlineStoreService.SearchNearestEntities.
SearchNearestEntitiesResponse: Response message for FeatureOnlineStoreService.SearchNearestEntities
SecretEnvVar: Represents an environment variable where the value is a secret in Cloud Secret Manager.
SecretRef: Reference to a secret stored in the Cloud Secret Manager that will provide the value for this environment variable.
Segment: Segment of the content.
ServiceAccountSpec: Configuration for the use of custom service account to run the workloads.
Session: A session contains a set of actions between users and Vertex agents.
SessionEvent: An event represents a message from either the user or agent.
SessionService: The service that manages Vertex Session related resources.
SetPublisherModelConfigOperationMetadata: Runtime operation information for EndpointService.SetPublisherModelConfig.
SetPublisherModelConfigRequest: Request message for EndpointService.SetPublisherModelConfig.
SharePointSources: The SharePointSources to pass to ImportRagFiles.
SharePointSources_SharePointSource: An individual SharePointSource.
ShieldedVmConfig: A set of Shielded Instance options. See Images using supported Shielded VM features.
SlackSource: The Slack source for the ImportRagFilesRequest.
SlackSource_SlackChannels: SlackChannels contains the Slack channels and corresponding access token.
SlackSource_SlackChannels_SlackChannel: SlackChannel contains the Slack channel ID and the time range to import.
SmoothGradConfig: Config for SmoothGrad approximation of gradients.
SpecialistPool: SpecialistPool represents customers' own workforce to work on their data labeling jobs. It includes a group of specialist managers and workers. Managers are responsible for managing the workers in this pool as well as customers' data labeling jobs associated with this pool. Customers create specialist pool as well as start data labeling jobs on Cloud, managers and workers handle the jobs using CrowdCompute console.
SpecialistPoolService: A service for creating and managing Customer SpecialistPools. When customers start Data Labeling jobs, they can reuse/create Specialist Pools to bring their own Specialists to label the data. Customers can add/remove Managers for the Specialist Pool on Cloud console, then Managers will get email notifications to manage Specialists and tasks on CrowdCompute console.
SpeculativeDecodingSpec: Configuration for Speculative Decoding.
SpeculativeDecodingSpec_DraftModelSpeculation: Draft model speculation works by using the smaller model to generate candidate tokens for speculative decoding.
SpeculativeDecodingSpec_NgramSpeculation: N-Gram speculation works by trying to find matching tokens in the previous prompt sequence and use those as speculation for generating new tokens.
SpeechConfig: The speech generation config.
StartNotebookRuntimeOperationMetadata: Metadata information for NotebookService.StartNotebookRuntime.
StartNotebookRuntimeRequest: Request message for NotebookService.StartNotebookRuntime.
StartNotebookRuntimeResponse: Response message for NotebookService.StartNotebookRuntime.
StopNotebookRuntimeOperationMetadata: Metadata information for NotebookService.StopNotebookRuntime.
StopNotebookRuntimeRequest: Request message for NotebookService.StopNotebookRuntime.
StopNotebookRuntimeResponse: Response message for NotebookService.StopNotebookRuntime.
StopTrialRequest: Request message for VizierService.StopTrial.
StoredContentsExample: A ContentsExample to be used with GenerateContent alongside information required for storage and retrieval with Example Store.
StoredContentsExample_SearchKeyGenerationMethod: Options for generating the search key from the conversation history.
StoredContentsExample_SearchKeyGenerationMethod_LastEntry: Configuration for using only the last entry of the conversation history as the search key.
StoredContentsExampleFilter: The metadata filters that will be used to remove or fetch StoredContentsExamples. If a field is unspecified, then no filtering for that field will be applied.
StoredContentsExampleParameters: The metadata filters that will be used to search StoredContentsExamples. If a field is unspecified, then no filtering for that field will be applied
StoredContentsExampleParameters_ContentSearchKey: The chat history to use to generate the search key for retrieval.
StratifiedSplit: Assigns input data to the training, validation, and test sets so that the distribution of values found in the categorical column (as specified by the key field) is mirrored within each split. The fraction values determine the relative sizes of the splits.
StreamDirectPredictRequest: Request message for PredictionService.StreamDirectPredict.
StreamDirectPredictResponse: Response message for PredictionService.StreamDirectPredict.
StreamDirectRawPredictRequest: Request message for PredictionService.StreamDirectRawPredict.
StreamDirectRawPredictResponse: Response message for PredictionService.StreamDirectRawPredict.
StreamingFetchFeatureValuesRequest: Request message for FeatureOnlineStoreService.StreamingFetchFeatureValues. For the entities requested, all features under the requested feature view will be returned.
StreamingFetchFeatureValuesResponse: Response message for FeatureOnlineStoreService.StreamingFetchFeatureValues.
StreamingPredictRequest: Request message for PredictionService.StreamingPredict.
StreamingPredictResponse: Response message for PredictionService.StreamingPredict.
StreamingRawPredictRequest: Request message for PredictionService.StreamingRawPredict.
StreamingRawPredictResponse: Response message for PredictionService.StreamingRawPredict.
StreamingReadFeatureValuesRequest: Request message for FeaturestoreOnlineServingService.StreamingReadFeatureValues.
StreamQueryReasoningEngineRequest: Request message for ReasoningEngineExecutionService.StreamQuery.
StreamRawPredictRequest: Request message for PredictionService.StreamRawPredict.
StringArray: A list of string values.
StructFieldValue: One field of a Struct (or object) type feature value.
StructValue: Struct (or object) type feature value.
Study: A message representing a Study.
Study_State: Describes the Study state.
StudySpec: Represents specification of a Study.
StudySpec_Algorithm: The available search algorithms for the Study.
StudySpec_ConvexAutomatedStoppingSpec: Configuration for ConvexAutomatedStoppingSpec. When there are enough completed trials (configured by min_measurement_count), for pending trials with enough measurements and steps, the policy first computes an overestimate of the objective value at max_num_steps according to the slope of the incomplete objective value curve. No prediction can be made if the curve is completely flat. If the overestimation is worse than the best objective value of the completed trials, this pending trial will be early-stopped, but a last measurement will be added to the pending trial with max_num_steps and predicted objective value from the autoregression model.
StudySpec_ConvexStopConfig: Configuration for ConvexStopPolicy.
StudySpec_DecayCurveAutomatedStoppingSpec: The decay curve automated stopping rule builds a Gaussian Process Regressor to predict the final objective value of a Trial based on the already completed Trials and the intermediate measurements of the current Trial. Early stopping is requested for the current Trial if there is very low probability to exceed the optimal value found so far.
StudySpec_MeasurementSelectionType: This indicates which measurement to use if/when the service automatically selects the final measurement from previously reported intermediate measurements. Choose this based on two considerations: A) Do you expect your measurements to monotonically improve? If so, choose LAST_MEASUREMENT. On the other hand, if you're in a situation where your system can "over-train" and you expect the performance to get better for a while but then start declining, choose BEST_MEASUREMENT. B) Are your measurements significantly noisy and/or irreproducible? If so, BEST_MEASUREMENT will tend to be over-optimistic, and it may be better to choose LAST_MEASUREMENT. If both or neither of (A) and (B) apply, it doesn't matter which selection type is chosen.
StudySpec_MedianAutomatedStoppingSpec: The median automated stopping rule stops a pending Trial if the Trial's best objective_value is strictly below the median 'performance' of all completed Trials reported up to the Trial's last measurement. Currently, 'performance' refers to the running average of the objective values reported by the Trial in each measurement.
StudySpec_MetricSpec: Represents a metric to optimize.
StudySpec_MetricSpec_GoalType: The available types of optimization goals.
StudySpec_MetricSpec_SafetyMetricConfig: Used in safe optimization to specify threshold levels and risk tolerance.
StudySpec_ObservationNoise: Describes the noise level of the repeated observations.
StudySpec_ParameterSpec: Represents a single parameter to optimize.
StudySpec_ParameterSpec_CategoricalValueSpec: Value specification for a parameter in CATEGORICAL type.
StudySpec_ParameterSpec_ConditionalParameterSpec: Represents a parameter spec with condition from its parent parameter.
StudySpec_ParameterSpec_ConditionalParameterSpec_CategoricalValueCondition: Represents the spec to match categorical values from parent parameter.
StudySpec_ParameterSpec_ConditionalParameterSpec_DiscreteValueCondition: Represents the spec to match discrete values from parent parameter.
StudySpec_ParameterSpec_ConditionalParameterSpec_IntValueCondition: Represents the spec to match integer values from parent parameter.
StudySpec_ParameterSpec_DiscreteValueSpec: Value specification for a parameter in DISCRETE type.
StudySpec_ParameterSpec_DoubleValueSpec: Value specification for a parameter in DOUBLE type.
StudySpec_ParameterSpec_IntegerValueSpec: Value specification for a parameter in INTEGER type.
StudySpec_ParameterSpec_ScaleType: The type of scaling that should be applied to this parameter.
StudySpec_StudyStoppingConfig: The configuration (stopping conditions) for automated stopping of a Study. Conditions include trial budgets, time budgets, and convergence detection.
StudySpec_TransferLearningConfig: This contains flag for manually disabling transfer learning for a study. The names of prior studies being used for transfer learning (if any) are also listed here.
StudyTimeConstraint: Time-based Constraint for Study
SuggestTrialsMetadata: Details of operations that perform Trials suggestion.
SuggestTrialsRequest: Request message for VizierService.SuggestTrials.
SuggestTrialsResponse: Response message for VizierService.SuggestTrials.
SummarizationHelpfulnessInput: Input for summarization helpfulness metric.
SummarizationHelpfulnessInstance: Spec for summarization helpfulness instance.
SummarizationHelpfulnessResult: Spec for summarization helpfulness result.
SummarizationHelpfulnessSpec: Spec for summarization helpfulness score metric.
SummarizationQualityInput: Input for summarization quality metric.
SummarizationQualityInstance: Spec for summarization quality instance.
SummarizationQualityResult: Spec for summarization quality result.
SummarizationQualitySpec: Spec for summarization quality score metric.
SummarizationVerbosityInput: Input for summarization verbosity metric.
SummarizationVerbosityInstance: Spec for summarization verbosity instance.
SummarizationVerbosityResult: Spec for summarization verbosity result.
SummarizationVerbositySpec: Spec for summarization verbosity score metric.
SupervisedHyperParameters: Hyperparameters for SFT.
SupervisedHyperParameters_AdapterSize: Supported adapter sizes for tuning.
SupervisedTuningDatasetDistribution: Dataset distribution for Supervised Tuning.
SupervisedTuningDatasetDistribution_DatasetBucket: Dataset bucket used to create a histogram for the distribution given a population of values.
SupervisedTuningDataStats: Tuning data statistics for Supervised Tuning.
SupervisedTuningSpec: Tuning Spec for Supervised Tuning for first party models.
SupervisedTuningSpec_TuningMode: Supported tuning modes.
SyncFeatureViewRequest: Request message for FeatureOnlineStoreAdminService.SyncFeatureView.
SyncFeatureViewResponse: Response message for FeatureOnlineStoreAdminService.SyncFeatureView.
Tensor: A tensor value type.
Tensor_DataType: Data type of the tensor.
Tensorboard: Tensorboard is a physical database that stores users' training metrics. A default Tensorboard is provided in each region of a Google Cloud project. If needed users can also create extra Tensorboards in their projects.
TensorboardBlob: One blob (e.g, image, graph) viewable on a blob metric plot.
TensorboardBlobSequence: One point viewable on a blob metric plot, but mostly just a wrapper message to work around repeated fields can't be used directly within oneof fields.
TensorboardExperiment: A TensorboardExperiment is a group of TensorboardRuns, that are typically the results of a training job run, in a Tensorboard.
TensorboardRun: TensorboardRun maps to a specific execution of a training job with a given set of hyperparameter values, model definition, dataset, etc
TensorboardService: TensorboardService
TensorboardTensor: One point viewable on a tensor metric plot.
TensorboardTimeSeries: TensorboardTimeSeries maps to times series produced in training runs
TensorboardTimeSeries_Metadata: Describes metadata for a TensorboardTimeSeries.
TensorboardTimeSeries_ValueType: An enum representing the value type of a TensorboardTimeSeries.
TfrecordDestination: The storage details for TFRecord output content.
ThresholdConfig: The config for feature monitoring threshold.
TimeSeriesData: All the data stored in a TensorboardTimeSeries.
TimeSeriesDataPoint: A TensorboardTimeSeries data point.
TimestampSplit: Assigns input data to training, validation, and test sets based on a provided timestamps. The youngest data pieces are assigned to training set, next to validation set, and the oldest to the test set.
TokensInfo: Tokens info with a list of tokens and the corresponding list of token ids.
Tool: Tool details that the model may use to generate response.
Tool_CodeExecution: Tool that executes code generated by the model, and automatically returns the result to the model.
Tool_ComputerUse: Tool to support computer use.
Tool_ComputerUse_Environment: Represents the environment being operated, such as a web browser.
Tool_GoogleSearch: GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google.
Tool_PhishBlockThreshold: These are available confidence level user can set to block malicious urls with chosen confidence and above. For understanding different confidence of webrisk, please refer to https://cloud.google.com/web-risk/docs/reference/rpc/google.cloud.webrisk.v1eap1#confidencelevel
ToolCall: Spec for tool call.
ToolCallValidInput: Input for tool call valid metric.
ToolCallValidInstance: Spec for tool call valid instance.
ToolCallValidMetricValue: Tool call valid metric value for an instance.
ToolCallValidResults: Results for tool call valid metric.
ToolCallValidSpec: Spec for tool call valid metric.
ToolConfig: Tool config. This config is shared for all tools provided in the request.
ToolNameMatchInput: Input for tool name match metric.
ToolNameMatchInstance: Spec for tool name match instance.
ToolNameMatchMetricValue: Tool name match metric value for an instance.
ToolNameMatchResults: Results for tool name match metric.
ToolNameMatchSpec: Spec for tool name match metric.
ToolParameterKeyMatchInput: Input for tool parameter key match metric.
ToolParameterKeyMatchInstance: Spec for tool parameter key match instance.
ToolParameterKeyMatchMetricValue: Tool parameter key match metric value for an instance.
ToolParameterKeyMatchResults: Results for tool parameter key match metric.
ToolParameterKeyMatchSpec: Spec for tool parameter key match metric.
ToolParameterKvmatchInput: Input for tool parameter key value match metric.
ToolParameterKvmatchInstance: Spec for tool parameter key value match instance.
ToolParameterKvmatchMetricValue: Tool parameter key value match metric value for an instance.
ToolParameterKvmatchResults: Results for tool parameter key value match metric.
ToolParameterKvmatchSpec: Spec for tool parameter key value match metric.
ToolUseExample: A single example of the tool usage.
ToolUseExample_ExtensionOperation: Identifies one operation of the extension.
TrainingConfig: 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.
TrainingPipeline: The TrainingPipeline orchestrates tasks associated with training a Model. It always executes the training task, and optionally may also export data from Vertex AI's Dataset which becomes the training input, upload the Model to Vertex AI, and evaluate the Model.
Trajectory: Spec for trajectory.
TrajectoryAnyOrderMatchInput: Instances and metric spec for TrajectoryAnyOrderMatch metric.
TrajectoryAnyOrderMatchInstance: Spec for TrajectoryAnyOrderMatch instance.
TrajectoryAnyOrderMatchMetricValue: TrajectoryAnyOrderMatch metric value for an instance.
TrajectoryAnyOrderMatchResults: Results for TrajectoryAnyOrderMatch metric.
TrajectoryAnyOrderMatchSpec: Spec for TrajectoryAnyOrderMatch metric - returns 1 if all tool calls in the reference trajectory appear in the predicted trajectory in any order, else 0.
TrajectoryExactMatchInput: Instances and metric spec for TrajectoryExactMatch metric.
TrajectoryExactMatchInstance: Spec for TrajectoryExactMatch instance.
TrajectoryExactMatchMetricValue: TrajectoryExactMatch metric value for an instance.
TrajectoryExactMatchResults: Results for TrajectoryExactMatch metric.
TrajectoryExactMatchSpec: Spec for TrajectoryExactMatch metric - returns 1 if tool calls in the reference trajectory exactly match the predicted trajectory, else 0.
TrajectoryInOrderMatchInput: Instances and metric spec for TrajectoryInOrderMatch metric.
TrajectoryInOrderMatchInstance: Spec for TrajectoryInOrderMatch instance.
TrajectoryInOrderMatchMetricValue: TrajectoryInOrderMatch metric value for an instance.
TrajectoryInOrderMatchResults: Results for TrajectoryInOrderMatch metric.
TrajectoryInOrderMatchSpec: Spec for TrajectoryInOrderMatch metric - returns 1 if tool calls in the reference trajectory appear in the predicted trajectory in the same order, else 0.
TrajectoryPrecisionInput: Instances and metric spec for TrajectoryPrecision metric.
TrajectoryPrecisionInstance: Spec for TrajectoryPrecision instance.
TrajectoryPrecisionMetricValue: TrajectoryPrecision metric value for an instance.
TrajectoryPrecisionResults: Results for TrajectoryPrecision metric.
TrajectoryPrecisionSpec: Spec for TrajectoryPrecision metric - returns a float score based on average precision of individual tool calls.
TrajectoryRecallInput: Instances and metric spec for TrajectoryRecall metric.
TrajectoryRecallInstance: Spec for TrajectoryRecall instance.
TrajectoryRecallMetricValue: TrajectoryRecall metric value for an instance.
TrajectoryRecallResults: Results for TrajectoryRecall metric.
TrajectoryRecallSpec: Spec for TrajectoryRecall metric - returns a float score based on average recall of individual tool calls.
TrajectorySingleToolUseInput: Instances and metric spec for TrajectorySingleToolUse metric.
TrajectorySingleToolUseInstance: Spec for TrajectorySingleToolUse instance.
TrajectorySingleToolUseMetricValue: TrajectorySingleToolUse metric value for an instance.
TrajectorySingleToolUseResults: Results for TrajectorySingleToolUse metric.
TrajectorySingleToolUseSpec: Spec for TrajectorySingleToolUse metric - returns 1 if tool is present in the predicted trajectory, else 0.
Trial: A message representing a Trial. A Trial contains a unique set of Parameters that has been or will be evaluated, along with the objective metrics got by running the Trial.
Trial_Parameter: A message representing a parameter to be tuned.
Trial_State: Describes a Trial state.
TrialContext
TunedModel: The Model Registry Model and Online Prediction Endpoint associated with this TuningJob.
TunedModelCheckpoint: TunedModelCheckpoint for the Tuned Model of a Tuning Job.
TunedModelRef: TunedModel Reference for legacy model migration.
TuningDataStats: The tuning data statistic values for TuningJob.
TuningJob: Represents a TuningJob that runs with Google owned models.
Type: Type contains the list of OpenAPI data types as defined by https://swagger.io/docs/specification/data-models/data-types/
UndeployIndexOperationMetadata: Runtime operation information for IndexEndpointService.UndeployIndex.
UndeployIndexRequest: Request message for IndexEndpointService.UndeployIndex.
UndeployIndexResponse: Response message for IndexEndpointService.UndeployIndex.
UndeployModelOperationMetadata: Runtime operation information for EndpointService.UndeployModel.
UndeployModelRequest: Request message for EndpointService.UndeployModel.
UndeployModelResponse: Response message for EndpointService.UndeployModel.
UnmanagedContainerModel: Contains model information necessary to perform batch prediction without requiring a full model import.
UpdateArtifactRequest: Request message for MetadataService.UpdateArtifact.
UpdateCachedContentRequest: Request message for GenAiCacheService.UpdateCachedContent. Only expire_time or ttl can be updated.
UpdateContextRequest: Request message for MetadataService.UpdateContext.
UpdateDatasetRequest: Request message for DatasetService.UpdateDataset.
UpdateDatasetVersionRequest: Request message for DatasetService.UpdateDatasetVersion.
UpdateDeploymentResourcePoolOperationMetadata: Runtime operation information for UpdateDeploymentResourcePool method.
UpdateDeploymentResourcePoolRequest: Request message for UpdateDeploymentResourcePool method.
UpdateEndpointLongRunningRequest: Request message for EndpointService.UpdateEndpointLongRunning.
UpdateEndpointOperationMetadata: Runtime operation information for EndpointService.UpdateEndpointLongRunning.
UpdateEndpointRequest: Request message for EndpointService.UpdateEndpoint.
UpdateEntityTypeRequest: Request message for FeaturestoreService.UpdateEntityType.
UpdateExampleStoreOperationMetadata: Details of ExampleStoreService.UpdateExampleStore operation.
UpdateExampleStoreRequest: Request message for ExampleStoreService.UpdateExampleStore.
UpdateExecutionRequest: Request message for MetadataService.UpdateExecution.
UpdateExplanationDatasetOperationMetadata: Runtime operation information for ModelService.UpdateExplanationDataset.
UpdateExplanationDatasetRequest: Request message for ModelService.UpdateExplanationDataset.
UpdateExplanationDatasetResponse: Response message of ModelService.UpdateExplanationDataset operation.
UpdateExtensionRequest: Request message for ExtensionRegistryService.UpdateExtension.
UpdateFeatureGroupOperationMetadata: Details of operations that perform update FeatureGroup.
UpdateFeatureGroupRequest: Request message for FeatureRegistryService.UpdateFeatureGroup.
UpdateFeatureMonitorOperationMetadata: Details of operations that perform update FeatureMonitor.
UpdateFeatureMonitorRequest: Request message for FeatureRegistryService.UpdateFeatureMonitor.
UpdateFeatureOnlineStoreOperationMetadata: Details of operations that perform update FeatureOnlineStore.
UpdateFeatureOnlineStoreRequest: Request message for FeatureOnlineStoreAdminService.UpdateFeatureOnlineStore.
UpdateFeatureOperationMetadata: Details of operations that perform update Feature.
UpdateFeatureRequest: Request message for FeaturestoreService.UpdateFeature. Request message for FeatureRegistryService.UpdateFeature.
UpdateFeaturestoreOperationMetadata: Details of operations that perform update Featurestore.
UpdateFeaturestoreRequest: Request message for FeaturestoreService.UpdateFeaturestore.
UpdateFeatureViewOperationMetadata: Details of operations that perform update FeatureView.
UpdateFeatureViewRequest: Request message for FeatureOnlineStoreAdminService.UpdateFeatureView.
UpdateIndexEndpointRequest: Request message for IndexEndpointService.UpdateIndexEndpoint.
UpdateIndexOperationMetadata: Runtime operation information for IndexService.UpdateIndex.
UpdateIndexRequest: Request message for IndexService.UpdateIndex.
UpdateMemoryOperationMetadata: Details of MemoryBankService.UpdateMemory operation.
UpdateMemoryRequest: Request message for MemoryBankService.UpdateMemory.
UpdateModelDeploymentMonitoringJobOperationMetadata: Runtime operation information for JobService.UpdateModelDeploymentMonitoringJob.
UpdateModelDeploymentMonitoringJobRequest: Request message for JobService.UpdateModelDeploymentMonitoringJob.
UpdateModelMonitorOperationMetadata: Runtime operation information for ModelMonitoringService.UpdateModelMonitor.
UpdateModelMonitorRequest: Request message for ModelMonitoringService.UpdateModelMonitor.
UpdateModelRequest: Request message for ModelService.UpdateModel.
UpdateNotebookRuntimeTemplateRequest: Request message for NotebookService.UpdateNotebookRuntimeTemplate.
UpdatePersistentResourceOperationMetadata: Details of operations that perform update PersistentResource.
UpdatePersistentResourceRequest: Request message for UpdatePersistentResource method.
UpdateRagCorpusOperationMetadata: Runtime operation information for VertexRagDataService.UpdateRagCorpus.
UpdateRagCorpusRequest: Request message for VertexRagDataService.UpdateRagCorpus.
UpdateRagEngineConfigOperationMetadata: Runtime operation information for VertexRagDataService.UpdateRagEngineConfig.
UpdateRagEngineConfigRequest: Request message for VertexRagDataService.UpdateRagEngineConfig.
UpdateReasoningEngineOperationMetadata: Details of ReasoningEngineService.UpdateReasoningEngine operation.
UpdateReasoningEngineRequest: Request message for ReasoningEngineService.UpdateReasoningEngine.
UpdateScheduleRequest: Request message for ScheduleService.UpdateSchedule.
UpdateSessionRequest: Request message for SessionService.UpdateSession.
UpdateSpecialistPoolOperationMetadata: Runtime operation metadata for SpecialistPoolService.UpdateSpecialistPool.
UpdateSpecialistPoolRequest: Request message for SpecialistPoolService.UpdateSpecialistPool.
UpdateTensorboardExperimentRequest: Request message for TensorboardService.UpdateTensorboardExperiment.
UpdateTensorboardOperationMetadata: Details of operations that perform update Tensorboard.
UpdateTensorboardRequest: Request message for TensorboardService.UpdateTensorboard.
UpdateTensorboardRunRequest: Request message for TensorboardService.UpdateTensorboardRun.
UpdateTensorboardTimeSeriesRequest: Request message for TensorboardService.UpdateTensorboardTimeSeries.
UpgradeNotebookRuntimeOperationMetadata: Metadata information for NotebookService.UpgradeNotebookRuntime.
UpgradeNotebookRuntimeRequest: Request message for NotebookService.UpgradeNotebookRuntime.
UpgradeNotebookRuntimeResponse: Response message for NotebookService.UpgradeNotebookRuntime.
UploadModelOperationMetadata: Details of ModelService.UploadModel operation.
UploadModelRequest: Request message for ModelService.UploadModel.
UploadModelResponse: Response message of ModelService.UploadModel operation.
UploadRagFileConfig: Config for uploading RagFile.
UploadRagFileRequest: Request message for VertexRagDataService.UploadRagFile.
UploadRagFileResponse: Response message for VertexRagDataService.UploadRagFile.
UpsertDatapointsRequest: Request message for IndexService.UpsertDatapoints
UpsertDatapointsResponse: Response message for IndexService.UpsertDatapoints
UpsertExamplesRequest: Request message for ExampleStoreService.UpsertExamples.
UpsertExamplesResponse: Response message for ExampleStoreService.UpsertExamples.
UpsertExamplesResponse_UpsertResult: The result for creating/updating a single example.
UrlContext: Tool to support URL context.
UrlContextMetadata: Metadata related to url context retrieval tool.
UrlMetadata: Context of the a single url retrieval.
UrlMetadata_UrlRetrievalStatus: Status of the url retrieval.
UserActionReference: References an API call. It contains more information about long running operation and Jobs that are triggered by the API call.
Value: Value is the value of the field.
VeoHyperParameters: Hyperparameters for Veo.
VeoHyperParameters_TuningTask: An enum defining the tuning task used for Veo.
VeoTuningSpec: Tuning Spec for Veo Model Tuning.
VertexAisearch: Retrieve from Vertex AI Search datastore or engine for grounding. datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder
VertexAisearch_DataStoreSpec: Define data stores within engine to filter on in a search call and configurations for those data stores. For more information, see https://cloud.google.com/generative-ai-app-builder/docs/reference/rpc/google.cloud.discoveryengine.v1#datastorespec
VertexAiSearchConfig: Config for the Vertex AI Search.
VertexRagDataService: A service for managing user data for RAG.
VertexRagService: A service for retrieving relevant contexts.
VertexRagStore: Retrieve from Vertex RAG Store for grounding.
VertexRagStore_RagResource: The definition of the Rag resource.
VideoMetadata: Metadata describes the input video content.
VizierService: Vertex AI Vizier API.
VoiceConfig: The configuration for the voice to use.
WorkerPoolSpec: Represents the spec of a worker pool in a job.
WriteFeatureValuesPayload: Contains Feature values to be written for a specific entity.
WriteFeatureValuesRequest: Request message for FeaturestoreOnlineServingService.WriteFeatureValues.
WriteFeatureValuesResponse: Response message for FeaturestoreOnlineServingService.WriteFeatureValues.
WriteTensorboardExperimentDataRequest: Request message for TensorboardService.WriteTensorboardExperimentData.
WriteTensorboardExperimentDataResponse: Response message for TensorboardService.WriteTensorboardExperimentData.
WriteTensorboardRunDataRequest: Request message for TensorboardService.WriteTensorboardRunData.
WriteTensorboardRunDataResponse: Response message for TensorboardService.WriteTensorboardRunData.
XraiAttribution: An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825

aiplatform library

Classes

google_cloud_aiplatform_v1beta1 package

aiplatform library