Google Vertex AI

App · 25 actions

Generate content, count tokens, and manage Vertex AI models, endpoints, datasets and prediction or training jobs.

Actions

ActionWhat it does
Cancel batch prediction jobCancel batch prediction job.
Cancel custom jobCancel custom job.
Count tokensCount tokens.
Delete batch prediction jobDelete batch prediction job.
Delete custom jobDelete custom job.
Delete datasetDelete dataset.
Delete endpointDelete endpoint.
Delete modelDelete model.
Delete pipeline jobDelete pipeline job.
Delete training pipelineDelete training pipeline.
Generate contentGenerate content.
Get batch prediction jobGet batch prediction job.
Get custom jobGet custom job.
Get datasetGet dataset.
Get endpointGet endpoint.
Get modelGet model.
Get pipeline jobGet pipeline job.
Get training pipelineGet training pipeline.
List batch prediction jobsList batch prediction jobs.
List custom jobsList custom jobs.
List datasetsList datasets.
List endpointsList endpoints.
List modelsList models.
List pipeline jobsList pipeline jobs.
List training pipelinesList training pipelines.

Cancel batch prediction job

Cancel batch prediction job.

Inputs

Resource idresource_idtextRequired
Resource id.

Outputs

dataobject
Response.
Example output
{
  "data": {}
}

Cancel custom job

Cancel custom job.

Inputs

Resource idresource_idtextRequired
Resource id.

Outputs

dataobject
Response.
Example output
{
  "data": {}
}

Count tokens

Count tokens.

Inputs

ModelmodeltextRequired
Publisher model ID, for example gemini-2.5-flash.
PromptprompttextRequired
Prompt.

Outputs

dataobject
Response message for PredictionService.CountTokens.
Example output
{
  "data": {
    "promptTokensDetails": [],
    "totalBillableCharacters": 1,
    "totalTokens": 1
  }
}

Delete batch prediction job

Delete batch prediction job.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
This resource represents a long-running operation that is the result of a network API call.
Example output
{
  "data": {
    "done": false,
    "error": {
      "code": 1,
      "details": [],
      "message": "example"
    },
    "metadata": {},
    "name": "example",
    "response": {}
  }
}

Delete custom job

Delete custom job.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
This resource represents a long-running operation that is the result of a network API call.
Example output
{
  "data": {
    "done": false,
    "error": {
      "code": 1,
      "details": [],
      "message": "example"
    },
    "metadata": {},
    "name": "example",
    "response": {}
  }
}

Delete dataset

Delete dataset.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
This resource represents a long-running operation that is the result of a network API call.
Example output
{
  "data": {
    "done": false,
    "error": {
      "code": 1,
      "details": [],
      "message": "example"
    },
    "metadata": {},
    "name": "example",
    "response": {}
  }
}

Delete endpoint

Delete endpoint.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
This resource represents a long-running operation that is the result of a network API call.
Example output
{
  "data": {
    "done": false,
    "error": {
      "code": 1,
      "details": [],
      "message": "example"
    },
    "metadata": {},
    "name": "example",
    "response": {}
  }
}

Delete model

Delete model.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
This resource represents a long-running operation that is the result of a network API call.
Example output
{
  "data": {
    "done": false,
    "error": {
      "code": 1,
      "details": [],
      "message": "example"
    },
    "metadata": {},
    "name": "example",
    "response": {}
  }
}

Delete pipeline job

Delete pipeline job.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
This resource represents a long-running operation that is the result of a network API call.
Example output
{
  "data": {
    "done": false,
    "error": {
      "code": 1,
      "details": [],
      "message": "example"
    },
    "metadata": {},
    "name": "example",
    "response": {}
  }
}

Delete training pipeline

Delete training pipeline.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
This resource represents a long-running operation that is the result of a network API call.
Example output
{
  "data": {
    "done": false,
    "error": {
      "code": 1,
      "details": [],
      "message": "example"
    },
    "metadata": {},
    "name": "example",
    "response": {}
  }
}

Generate content

Generate content.

Inputs

ModelmodeltextRequired
Publisher model ID, for example gemini-2.5-flash.
PromptprompttextRequired
Prompt.
Temperaturetemperaturenumber
Temperature.From 0 to 2.
Max output tokensmax_output_tokensnumber
Max output tokens.At least 1.

Outputs

dataobject
Response message for [PredictionService.GenerateContent].
Example output
{
  "data": {
    "candidates": [],
    "createTime": "example",
    "modelVersion": "example",
    "promptFeedback": {
      "blockReason": "BLOCKED_REASON_UNSPECIFIED",
      "blockReasonMessage": "example",
      "safetyRatings": []
    },
    "responseId": "example",
    "usageMetadata": {
      "cacheTokensDetails": [],
      "cachedContentTokenCount": 1,
      "candidatesTokenCount": 1,
      "candidatesTokensDetails": [],
      "promptTokenCount": 1,
      "promptTokensDetails": [],
      "thoughtsTokenCount": 1,
      "toolUsePromptTokenCount": 1,
      "toolUsePromptTokensDetails": [],
      "totalTokenCount": 1,
      "trafficType": "TRAFFIC_TYPE_UNSPECIFIED"
    }
  }
}

Get batch prediction job

Get batch prediction job.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
A job that uses a Model to produce predictions on multiple input instances. If predictions for significant portion of the instances fail, the job may finish without attempting predictions for all remaining instances.
Example output
{
  "data": {
    "completionStats": {
      "failedCount": "example",
      "incompleteCount": "example",
      "successfulCount": "example",
      "successfulForecastPointCount": "example"
    },
    "createTime": "example",
    "dedicatedResources": {
      "machineSpec": {
        "acceleratorCount": 1,
        "acceleratorType": "ACCELERATOR_TYPE_UNSPECIFIED",
        "gpuPartitionSize": "example",
        "machineType": "example",
        "reservationAffinity": {
          "key": "example",
          "reservationAffinityType": "TYPE_UNSPECIFIED",
          "values": []
        },
        "tpuTopology": "example"
      },
      "maxReplicaCount": 1,
      "startingReplicaCount": 1
    },
    "disableContainerLogging": false,
    "displayName": "example",
    "encryptionSpec": {
      "kmsKeyName": "example"
    },
    "endTime": "example",
    "error": {
      "code": 1,
      "details": [],
      "message": "example"
    },
    "explanationSpec": {
      "metadata": {
        "featureAttributionsSchemaUri": "example",
        "inputs": {},
        "latentSpaceSource": "example",
        "outputs": {}
      },
      "parameters": {
        "examples": {
          "exampleGcsSource": {
            "dataFormat": "DATA_FORMAT_UNSPECIFIED",
            "gcsSource": {}
          },
          "nearestNeighborSearchConfig": {},
          "neighborCount": 1,
          "presets": {
            "modality": "MODALITY_UNSPECIFIED",
            "query": "PRECISE"
          }
        },
        "integratedGradientsAttribution": {
          "blurBaselineConfig": {
            "maxBlurSigma": 1.0
          },
          "smoothGradConfig": {
            "featureNoiseSigma": {},
            "noiseSigma": 1.0,
            "noisySampleCount": 1
          },
          "stepCount": 1
        },
        "outputIndices": [],
        "sampledShapleyAttribution": {
          "pathCount": 1
        },
        "topK": 1,
        "xraiAttribution": {
          "blurBaselineConfig": {
            "maxBlurSigma": 1.0
          },
          "smoothGradConfig": {
            "featureNoiseSigma": {},
            "noiseSigma": 1.0,
            "noisySampleCount": 1
          },
          "stepCount": 1
        }
      }
    },
    "generateExplanation": false,
    "inputConfig": {
      "bigquerySource": {
        "inputUri": "example"
      },
      "gcsSource": {
        "uris": []
      },
      "instancesFormat": "example",
      "vertexMultimodalDatasetSource": {
        "datasetName": "example"
      }
    },
    "instanceConfig": {
      "excludedFields": [],
      "includedFields": [],
      "instanceType": "example",
      "keyField": "example"
    },
    "labels": {},
    "manualBatchTuningParameters": {
      "batchSize": 1
    },
    "model": "example",
    "modelParameters": {},
    "modelVersionId": "example",
    "name": "example",
    "outputConfig": {
      "bigqueryDestination": {
        "outputUri": "example"
      },
      "gcsDestination": {
        "outputUriPrefix": "example"
      },
      "predictionsFormat": "example",
      "vertexMultimodalDatasetDestination": {
        "bigqueryDestination": {
          "outputUri": "example"
        },
        "displayName": "example"
      }
    },
    "outputInfo": {
      "bigqueryOutputDataset": "example",
      "bigqueryOutputTable": "example",
      "gcsOutputDirectory": "example",
      "vertexMultimodalDatasetName": "example"
    },
    "partialFailures": [],
    "resourcesConsumed": {
      "replicaHours": 1.0
    },
    "satisfiesPzi": false,
    "satisfiesPzs": false,
    "serviceAccount": "example",
    "startTime": "example",
    "state": "JOB_STATE_UNSPECIFIED",
    "unmanagedContainerModel": {
      "artifactUri": "example",
      "containerSpec": {
        "args": [],
        "command": [],
        "deploymentTimeout": "example",
        "env": [],
        "grpcPorts": [],
        "healthProbe": {
          "exec": {
            "command": []
          },
          "failureThreshold": 1,
          "grpc": {
            "port": 1,
            "service": "example"
          },
          "httpGet": {
            "host": "example",
            "httpHeaders": [],
            "path": "example",
            "port": 1,
            "scheme": "example"
          },
          "initialDelaySeconds": 1,
          "periodSeconds": 1,
          "successThreshold": 1,
          "tcpSocket": {
            "host": "example",
            "port": 1
          },
          "timeoutSeconds": 1
        },
        "healthRoute": "example",
        "imageUri": "example",
        "invokeRoutePrefix": "example",
        "livenessProbe": {
          "exec": {
            "command": []
          },
          "failureThreshold": 1,
          "grpc": {
            "port": 1,
            "service": "example"
          },
          "httpGet": {
            "host": "example",
            "httpHeaders": [],
            "path": "example",
            "port": 1,
            "scheme": "example"
          },
          "initialDelaySeconds": 1,
          "periodSeconds": 1,
          "successThreshold": 1,
          "tcpSocket": {
            "host": "example",
            "port": 1
          },
          "timeoutSeconds": 1
        },
        "ports": [],
        "predictRoute": "example",
        "sharedMemorySizeMb": "example",
        "startupProbe": {
          "exec": {
            "command": []
          },
          "failureThreshold": 1,
          "grpc": {
            "port": 1,
            "service": "example"
          },
          "httpGet": {
            "host": "example",
            "httpHeaders": [],
            "path": "example",
            "port": 1,
            "scheme": "example"
          },
          "initialDelaySeconds": 1,
          "periodSeconds": 1,
          "successThreshold": 1,
          "tcpSocket": {
            "host": "example",
            "port": 1
          },
          "timeoutSeconds": 1
        }
      },
      "predictSchemata": {
        "instanceSchemaUri": "example",
        "parametersSchemaUri": "example",
        "predictionSchemaUri": "example"
      }
    },
    "updateTime": "example"
  }
}

Get custom job

Get custom job.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
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).
Example output
{
  "data": {
    "createTime": "example",
    "displayName": "example",
    "encryptionSpec": {
      "kmsKeyName": "example"
    },
    "endTime": "example",
    "error": {
      "code": 1,
      "details": [],
      "message": "example"
    },
    "jobSpec": {
      "baseOutputDirectory": {
        "outputUriPrefix": "example"
      },
      "enableDashboardAccess": false,
      "enableWebAccess": false,
      "experiment": "example",
      "experimentRun": "example",
      "models": [],
      "network": "example",
      "persistentResourceId": "example",
      "protectedArtifactLocationId": "example",
      "pscInterfaceConfig": {
        "dnsPeeringConfigs": [],
        "networkAttachment": "example"
      },
      "reservedIpRanges": [],
      "scheduling": {
        "disableRetries": false,
        "maxWaitDuration": "example",
        "restartJobOnWorkerRestart": false,
        "strategy": "STRATEGY_UNSPECIFIED",
        "timeout": "example"
      },
      "serviceAccount": "example",
      "tensorboard": "example",
      "workerPoolSpecs": []
    },
    "labels": {},
    "name": "example",
    "satisfiesPzi": false,
    "satisfiesPzs": false,
    "startTime": "example",
    "state": "JOB_STATE_UNSPECIFIED",
    "updateTime": "example",
    "webAccessUris": {}
  }
}

Get dataset

Get dataset.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
A collection of DataItems and Annotations on them.
Example output
{
  "data": {
    "createTime": "example",
    "dataItemCount": "example",
    "description": "example",
    "displayName": "example",
    "encryptionSpec": {
      "kmsKeyName": "example"
    },
    "etag": "example",
    "labels": {},
    "metadata": {},
    "metadataArtifact": "example",
    "metadataSchemaUri": "example",
    "modelReference": "example",
    "name": "example",
    "satisfiesPzi": false,
    "satisfiesPzs": false,
    "savedQueries": [],
    "updateTime": "example"
  }
}

Get endpoint

Get endpoint.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.
Example output
{
  "data": {
    "clientConnectionConfig": {
      "inferenceTimeout": "example"
    },
    "createTime": "example",
    "dedicatedEndpointDns": "example",
    "dedicatedEndpointEnabled": false,
    "deployedModels": [],
    "description": "example",
    "displayName": "example",
    "enablePrivateServiceConnect": false,
    "encryptionSpec": {
      "kmsKeyName": "example"
    },
    "etag": "example",
    "gdcConfig": {
      "zone": "example"
    },
    "genAiAdvancedFeaturesConfig": {
      "ragConfig": {
        "enableRag": false
      }
    },
    "labels": {},
    "modelDeploymentMonitoringJob": "example",
    "name": "example",
    "network": "example",
    "predictRequestResponseLoggingConfig": {
      "bigqueryDestination": {
        "outputUri": "example"
      },
      "enabled": false,
      "samplingRate": 1.0
    },
    "privateServiceConnectConfig": {
      "enablePrivateServiceConnect": false,
      "projectAllowlist": [],
      "pscAutomationConfigs": [],
      "serviceAttachment": "example"
    },
    "satisfiesPzi": false,
    "satisfiesPzs": false,
    "trafficSplit": {},
    "updateTime": "example"
  }
}

Get model

Get model.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
A trained machine learning Model.
Example output
{
  "data": {
    "artifactUri": "example",
    "baseModelSource": {
      "genieSource": {
        "baseModelUri": "example"
      },
      "modelGardenSource": {
        "publicModelName": "example",
        "skipHfModelCache": false,
        "versionId": "example"
      }
    },
    "checkpoints": [],
    "containerSpec": {
      "args": [],
      "command": [],
      "deploymentTimeout": "example",
      "env": [],
      "grpcPorts": [],
      "healthProbe": {
        "exec": {
          "command": []
        },
        "failureThreshold": 1,
        "grpc": {
          "port": 1,
          "service": "example"
        },
        "httpGet": {
          "host": "example",
          "httpHeaders": [],
          "path": "example",
          "port": 1,
          "scheme": "example"
        },
        "initialDelaySeconds": 1,
        "periodSeconds": 1,
        "successThreshold": 1,
        "tcpSocket": {
          "host": "example",
          "port": 1
        },
        "timeoutSeconds": 1
      },
      "healthRoute": "example",
      "imageUri": "example",
      "invokeRoutePrefix": "example",
      "livenessProbe": {
        "exec": {
          "command": []
        },
        "failureThreshold": 1,
        "grpc": {
          "port": 1,
          "service": "example"
        },
        "httpGet": {
          "host": "example",
          "httpHeaders": [],
          "path": "example",
          "port": 1,
          "scheme": "example"
        },
        "initialDelaySeconds": 1,
        "periodSeconds": 1,
        "successThreshold": 1,
        "tcpSocket": {
          "host": "example",
          "port": 1
        },
        "timeoutSeconds": 1
      },
      "ports": [],
      "predictRoute": "example",
      "sharedMemorySizeMb": "example",
      "startupProbe": {
        "exec": {
          "command": []
        },
        "failureThreshold": 1,
        "grpc": {
          "port": 1,
          "service": "example"
        },
        "httpGet": {
          "host": "example",
          "httpHeaders": [],
          "path": "example",
          "port": 1,
          "scheme": "example"
        },
        "initialDelaySeconds": 1,
        "periodSeconds": 1,
        "successThreshold": 1,
        "tcpSocket": {
          "host": "example",
          "port": 1
        },
        "timeoutSeconds": 1
      }
    },
    "createTime": "example",
    "dataStats": {
      "testAnnotationsCount": "example",
      "testDataItemsCount": "example",
      "trainingAnnotationsCount": "example",
      "trainingDataItemsCount": "example",
      "validationAnnotationsCount": "example",
      "validationDataItemsCount": "example"
    },
    "defaultCheckpointId": "example",
    "deployedModels": [],
    "description": "example",
    "displayName": "example",
    "encryptionSpec": {
      "kmsKeyName": "example"
    },
    "etag": "example",
    "explanationSpec": {
      "metadata": {
        "featureAttributionsSchemaUri": "example",
        "inputs": {},
        "latentSpaceSource": "example",
        "outputs": {}
      },
      "parameters": {
        "examples": {
          "exampleGcsSource": {
            "dataFormat": "DATA_FORMAT_UNSPECIFIED",
            "gcsSource": {}
          },
          "nearestNeighborSearchConfig": {},
          "neighborCount": 1,
          "presets": {
            "modality": "MODALITY_UNSPECIFIED",
            "query": "PRECISE"
          }
        },
        "integratedGradientsAttribution": {
          "blurBaselineConfig": {
            "maxBlurSigma": 1.0
          },
          "smoothGradConfig": {
            "featureNoiseSigma": {},
            "noiseSigma": 1.0,
            "noisySampleCount": 1
          },
          "stepCount": 1
        },
        "outputIndices": [],
        "sampledShapleyAttribution": {
          "pathCount": 1
        },
        "topK": 1,
        "xraiAttribution": {
          "blurBaselineConfig": {
            "maxBlurSigma": 1.0
          },
          "smoothGradConfig": {
            "featureNoiseSigma": {},
            "noiseSigma": 1.0,
            "noisySampleCount": 1
          },
          "stepCount": 1
        }
      }
    },
    "labels": {},
    "metadata": {},
    "metadataArtifact": "example",
    "metadataSchemaUri": "example",
    "modelSourceInfo": {
      "copy": false,
      "sourceType": "MODEL_SOURCE_TYPE_UNSPECIFIED"
    },
    "name": "example",
    "originalModelInfo": {
      "model": "example"
    },
    "pipelineJob": "example",
    "predictSchemata": {
      "instanceSchemaUri": "example",
      "parametersSchemaUri": "example",
      "predictionSchemaUri": "example"
    },
    "satisfiesPzi": false,
    "satisfiesPzs": false,
    "supportedDeploymentResourcesTypes": [],
    "supportedExportFormats": [],
    "supportedInputStorageFormats": [],
    "supportedOutputStorageFormats": [],
    "trainingPipeline": "example",
    "updateTime": "example",
    "versionAliases": [],
    "versionCreateTime": "example",
    "versionDescription": "example",
    "versionId": "example",
    "versionUpdateTime": "example"
  }
}

Get pipeline job

Get pipeline job.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
An instance of a machine learning PipelineJob.
Example output
{
  "data": {
    "createTime": "example",
    "displayName": "example",
    "encryptionSpec": {
      "kmsKeyName": "example"
    },
    "endTime": "example",
    "error": {
      "code": 1,
      "details": [],
      "message": "example"
    },
    "jobDetail": {
      "pipelineContext": {
        "createTime": "example",
        "description": "example",
        "displayName": "example",
        "etag": "example",
        "labels": {},
        "metadata": {},
        "name": "example",
        "parentContexts": [],
        "schemaTitle": "example",
        "schemaVersion": "example",
        "updateTime": "example"
      },
      "pipelineRunContext": {
        "createTime": "example",
        "description": "example",
        "displayName": "example",
        "etag": "example",
        "labels": {},
        "metadata": {},
        "name": "example",
        "parentContexts": [],
        "schemaTitle": "example",
        "schemaVersion": "example",
        "updateTime": "example"
      },
      "taskDetails": []
    },
    "labels": {},
    "name": "example",
    "network": "example",
    "pipelineSpec": {},
    "preflightValidations": false,
    "pscInterfaceConfig": {
      "dnsPeeringConfigs": [],
      "networkAttachment": "example"
    },
    "reservedIpRanges": [],
    "runtimeConfig": {
      "failurePolicy": "PIPELINE_FAILURE_POLICY_UNSPECIFIED",
      "gcsOutputDirectory": "example",
      "inputArtifacts": {},
      "parameterValues": {},
      "parameters": {}
    },
    "scheduleName": "example",
    "serviceAccount": "example",
    "startTime": "example",
    "state": "PIPELINE_STATE_UNSPECIFIED",
    "templateMetadata": {
      "version": "example"
    },
    "templateUri": "example",
    "updateTime": "example"
  }
}

Get training pipeline

Get training pipeline.

Inputs

Resourceresource_idtextRequired
Resource ID, the final part of its Vertex AI name.

Outputs

dataobject
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.
Example output
{
  "data": {
    "createTime": "example",
    "displayName": "example",
    "encryptionSpec": {
      "kmsKeyName": "example"
    },
    "endTime": "example",
    "error": {
      "code": 1,
      "details": [],
      "message": "example"
    },
    "inputDataConfig": {
      "annotationSchemaUri": "example",
      "annotationsFilter": "example",
      "bigqueryDestination": {
        "outputUri": "example"
      },
      "datasetId": "example",
      "filterSplit": {
        "testFilter": "example",
        "trainingFilter": "example",
        "validationFilter": "example"
      },
      "fractionSplit": {
        "testFraction": 1.0,
        "trainingFraction": 1.0,
        "validationFraction": 1.0
      },
      "gcsDestination": {
        "outputUriPrefix": "example"
      },
      "persistMlUseAssignment": false,
      "predefinedSplit": {
        "key": "example"
      },
      "savedQueryId": "example",
      "stratifiedSplit": {
        "key": "example",
        "testFraction": 1.0,
        "trainingFraction": 1.0,
        "validationFraction": 1.0
      },
      "timestampSplit": {
        "key": "example",
        "testFraction": 1.0,
        "trainingFraction": 1.0,
        "validationFraction": 1.0
      }
    },
    "labels": {},
    "modelId": "example",
    "modelToUpload": {
      "artifactUri": "example",
      "baseModelSource": {
        "genieSource": {
          "baseModelUri": "example"
        },
        "modelGardenSource": {
          "publicModelName": "example",
          "skipHfModelCache": false,
          "versionId": "example"
        }
      },
      "checkpoints": [],
      "containerSpec": {
        "args": [],
        "command": [],
        "deploymentTimeout": "example",
        "env": [],
        "grpcPorts": [],
        "healthProbe": {
          "exec": {
            "command": []
          },
          "failureThreshold": 1,
          "grpc": {
            "port": 1,
            "service": "example"
          },
          "httpGet": {
            "host": "example",
            "httpHeaders": [],
            "path": "example",
            "port": 1,
            "scheme": "example"
          },
          "initialDelaySeconds": 1,
          "periodSeconds": 1,
          "successThreshold": 1,
          "tcpSocket": {
            "host": "example",
            "port": 1
          },
          "timeoutSeconds": 1
        },
        "healthRoute": "example",
        "imageUri": "example",
        "invokeRoutePrefix": "example",
        "livenessProbe": {
          "exec": {
            "command": []
          },
          "failureThreshold": 1,
          "grpc": {
            "port": 1,
            "service": "example"
          },
          "httpGet": {
            "host": "example",
            "httpHeaders": [],
            "path": "example",
            "port": 1,
            "scheme": "example"
          },
          "initialDelaySeconds": 1,
          "periodSeconds": 1,
          "successThreshold": 1,
          "tcpSocket": {
            "host": "example",
            "port": 1
          },
          "timeoutSeconds": 1
        },
        "ports": [],
        "predictRoute": "example",
        "sharedMemorySizeMb": "example",
        "startupProbe": {
          "exec": {
            "command": []
          },
          "failureThreshold": 1,
          "grpc": {
            "port": 1,
            "service": "example"
          },
          "httpGet": {
            "host": "example",
            "httpHeaders": [],
            "path": "example",
            "port": 1,
            "scheme": "example"
          },
          "initialDelaySeconds": 1,
          "periodSeconds": 1,
          "successThreshold": 1,
          "tcpSocket": {
            "host": "example",
            "port": 1
          },
          "timeoutSeconds": 1
        }
      },
      "createTime": "example",
      "dataStats": {
        "testAnnotationsCount": "example",
        "testDataItemsCount": "example",
        "trainingAnnotationsCount": "example",
        "trainingDataItemsCount": "example",
        "validationAnnotationsCount": "example",
        "validationDataItemsCount": "example"
      },
      "defaultCheckpointId": "example",
      "deployedModels": [],
      "description": "example",
      "displayName": "example",
      "encryptionSpec": {
        "kmsKeyName": "example"
      },
      "etag": "example",
      "explanationSpec": {
        "metadata": {
          "featureAttributionsSchemaUri": "example",
          "inputs": {},
          "latentSpaceSource": "example",
          "outputs": {}
        },
        "parameters": {
          "examples": {
            "exampleGcsSource": {},
            "nearestNeighborSearchConfig": {},
            "neighborCount": 1,
            "presets": {}
          },
          "integratedGradientsAttribution": {
            "blurBaselineConfig": {},
            "smoothGradConfig": {},
            "stepCount": 1
          },
          "outputIndices": [],
          "sampledShapleyAttribution": {
            "pathCount": 1
          },
          "topK": 1,
          "xraiAttribution": {
            "blurBaselineConfig": {},
            "smoothGradConfig": {},
            "stepCount": 1
          }
        }
      },
      "labels": {},
      "metadata": {},
      "metadataArtifact": "example",
      "metadataSchemaUri": "example",
      "modelSourceInfo": {
        "copy": false,
        "sourceType": "MODEL_SOURCE_TYPE_UNSPECIFIED"
      },
      "name": "example",
      "originalModelInfo": {
        "model": "example"
      },
      "pipelineJob": "example",
      "predictSchemata": {
        "instanceSchemaUri": "example",
        "parametersSchemaUri": "example",
        "predictionSchemaUri": "example"
      },
      "satisfiesPzi": false,
      "satisfiesPzs": false,
      "supportedDeploymentResourcesTypes": [],
      "supportedExportFormats": [],
      "supportedInputStorageFormats": [],
      "supportedOutputStorageFormats": [],
      "trainingPipeline": "example",
      "updateTime": "example",
      "versionAliases": [],
      "versionCreateTime": "example",
      "versionDescription": "example",
      "versionId": "example",
      "versionUpdateTime": "example"
    },
    "name": "example",
    "parentModel": "example",
    "startTime": "example",
    "state": "PIPELINE_STATE_UNSPECIFIED",
    "trainingTaskDefinition": "example",
    "trainingTaskInputs": {},
    "trainingTaskMetadata": {},
    "updateTime": "example"
  }
}

List batch prediction jobs

List batch prediction jobs.

Inputs

Page sizepage_sizenumber
Page size.From 1 to 100.
Page tokenpage_tokentext
Page token.
Filterfiltertext
Filter.

Outputs

dataobject
Response message for JobService.ListBatchPredictionJobs
Example output
{
  "data": {
    "batchPredictionJobs": [],
    "nextPageToken": "example"
  }
}

List custom jobs

List custom jobs.

Inputs

Page sizepage_sizenumber
Page size.From 1 to 100.
Page tokenpage_tokentext
Page token.
Filterfiltertext
Filter.

Outputs

dataobject
Response message for JobService.ListCustomJobs
Example output
{
  "data": {
    "customJobs": [],
    "nextPageToken": "example"
  }
}

List datasets

List datasets.

Inputs

Page sizepage_sizenumber
Page size.From 1 to 100.
Page tokenpage_tokentext
Page token.
Filterfiltertext
Filter.

Outputs

dataobject
Response message for DatasetService.ListDatasets.
Example output
{
  "data": {
    "datasets": [],
    "nextPageToken": "example"
  }
}

List endpoints

List endpoints.

Inputs

Page sizepage_sizenumber
Page size.From 1 to 100.
Page tokenpage_tokentext
Page token.
Filterfiltertext
Filter.

Outputs

dataobject
Response message for EndpointService.ListEndpoints.
Example output
{
  "data": {
    "endpoints": [],
    "nextPageToken": "example"
  }
}

List models

List models.

Inputs

Page sizepage_sizenumber
Page size.From 1 to 100.
Page tokenpage_tokentext
Page token.
Filterfiltertext
Filter.

Outputs

dataobject
Response message for ModelService.ListModels
Example output
{
  "data": {
    "models": [],
    "nextPageToken": "example"
  }
}

List pipeline jobs

List pipeline jobs.

Inputs

Page sizepage_sizenumber
Page size.From 1 to 100.
Page tokenpage_tokentext
Page token.
Filterfiltertext
Filter.

Outputs

dataobject
Response message for PipelineService.ListPipelineJobs
Example output
{
  "data": {
    "nextPageToken": "example",
    "pipelineJobs": []
  }
}

List training pipelines

List training pipelines.

Inputs

Page sizepage_sizenumber
Page size.From 1 to 100.
Page tokenpage_tokentext
Page token.
Filterfiltertext
Filter.

Outputs

dataobject
Response message for PipelineService.ListTrainingPipelines
Example output
{
  "data": {
    "nextPageToken": "example",
    "trainingPipelines": []
  }
}

On this page