Method: googleapis.aiplatform.v1.projects.locations.endpoints.undeployModel

Preview

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

Undeploys a Model from an Endpoint, removing a DeployedModel from it, and freeing all resources it's using.

This method waits—the workflow execution is paused—until the operation is complete, fails, or times out. The default timeout value is 1800 seconds (30 minutes) and can be changed to a maximum value of 31536000 seconds (one year) for long-running operations using the connector_params field. See the Connectors reference.

The connector uses polling to monitor the long-running operation, which might generate additional billable steps. For more information about retries and long-running operations, refer to Understand connectors.

The polling policy for the long-running operation can be configured. To set the connector-specific parameters (connector_params), refer to Invoke a connector call.

Arguments

Parameters
endpoint	string Required. The name of the Endpoint resource from which to undeploy a Model. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
region	string Required. Region of the HTTP endpoint. For example, if region is set to us-central1, the endpoint https://us-central1-integrations.googleapis.com will be used. See service endpoints.
body	object (GoogleCloudAiplatformV1UndeployModelRequest) Required.

Raised exceptions

Exceptions
ConnectionError	In case of a network problem (such as DNS failure or refused connection).
HttpError	If the response status is >= 400 (excluding 429 and 503).
TimeoutError	If a long-running operation takes longer to finish than the specified timeout limit.
TypeError	If an operation or function receives an argument of the wrong type.
ValueError	If an operation or function receives an argument of the right type but an inappropriate value. For example, a negative timeout.
OperationError	If the long-running operation finished unsuccessfully.
ResponseTypeError	If the long-running operation returned a response of the wrong type.

Response

If successful, the response contains an instance of GoogleLongrunningOperation.

Subworkflow snippet

Some fields might be optional or required. To identify required fields, refer to the API documentation.

YAML

- undeployModel:
    call: googleapis.aiplatform.v1.projects.locations.endpoints.undeployModel
    args:
        endpoint: ...
        region: ...
        body:
            deployedModelId: ...
            trafficSplit: ...
    result: undeployModelResult

JSON

[
  {
    "undeployModel": {
      "call": "googleapis.aiplatform.v1.projects.locations.endpoints.undeployModel",
      "args": {
        "endpoint": "...",
        "region": "...",
        "body": {
          "deployedModelId": "...",
          "trafficSplit": "..."
        }
      },
      "result": "undeployModelResult"
    }
  }
]