docs-archive/apache-airflow-providers-google/8.4.0/_sources/_api/airflow/providers/google/cloud/hooks/vertex_ai/endpoint_service/index.rst.txt

:py:mod:`airflow.providers.google.cloud.hooks.vertex_ai.endpoint_service`
=========================================================================

.. py:module:: airflow.providers.google.cloud.hooks.vertex_ai.endpoint_service

.. autoapi-nested-parse::

   This module contains a Google Cloud Vertex AI hook.

   .. spelling::

       undeployed
       undeploy
       Undeploys
       aiplatform
       FieldMask
       unassigns



Module Contents
---------------

Classes
~~~~~~~

.. autoapisummary::

   airflow.providers.google.cloud.hooks.vertex_ai.endpoint_service.EndpointServiceHook




.. py:class:: EndpointServiceHook(gcp_conn_id = 'google_cloud_default', delegate_to = None, impersonation_chain = None)

   Bases: :py:obj:`airflow.providers.google.common.hooks.base_google.GoogleBaseHook`

   Hook for Google Cloud Vertex AI Endpoint Service APIs.

   .. py:method:: get_endpoint_service_client(region = None)

      Returns EndpointServiceClient.


   .. py:method:: wait_for_operation(operation, timeout = None)

      Waits for long-lasting operation to complete.


   .. py:method:: extract_endpoint_id(obj)
      :staticmethod:

      Returns unique id of the endpoint.


   .. py:method:: extract_deployed_model_id(obj)
      :staticmethod:

      Returns unique id of the deploy model.


   .. py:method:: create_endpoint(project_id, region, endpoint, endpoint_id = None, retry = DEFAULT, timeout = None, metadata = ())

      Creates an Endpoint.

      :param project_id: Required. The ID of the Google Cloud project that the service belongs to.
      :param region: Required. The ID of the Google Cloud region that the service belongs to.
      :param endpoint: Required. The Endpoint to create.
      :param endpoint_id: The ID of Endpoint. This value should be 1-10 characters, and valid characters
          are /[0-9]/. If not provided, Vertex AI will generate a value for this ID.
      :param retry: Designation of what errors, if any, should be retried.
      :param timeout: The timeout for this request.
      :param metadata: Strings which should be sent along with the request as metadata.


   .. py:method:: delete_endpoint(project_id, region, endpoint, retry = DEFAULT, timeout = None, metadata = ())

      Deletes an Endpoint.

      :param project_id: Required. The ID of the Google Cloud project that the service belongs to.
      :param region: Required. The ID of the Google Cloud region that the service belongs to.
      :param endpoint: Required. The Endpoint to delete.
      :param retry: Designation of what errors, if any, should be retried.
      :param timeout: The timeout for this request.
      :param metadata: Strings which should be sent along with the request as metadata.


   .. py:method:: deploy_model(project_id, region, endpoint, deployed_model, traffic_split = None, retry = DEFAULT, timeout = None, metadata = ())

      Deploys a Model into this Endpoint, creating a DeployedModel within it.

      :param project_id: Required. The ID of the Google Cloud project that the service belongs to.
      :param region: Required. The ID of the Google Cloud region that the service belongs to.
      :param endpoint:  Required. The name of the Endpoint resource into which to deploy a Model. Format:
          ``projects/{project}/locations/{location}/endpoints/{endpoint}``
      :param deployed_model:  Required. The DeployedModel to be created within the Endpoint. Note that
          [Endpoint.traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split] must be updated for
          the DeployedModel to start receiving traffic, either as part of this call, or via
          [EndpointService.UpdateEndpoint][google.cloud.aiplatform.v1.EndpointService.UpdateEndpoint].
      :param traffic_split:  A map from a DeployedModel's ID to the percentage of this Endpoint's traffic
          that should be forwarded to that DeployedModel.

          If this field is non-empty, then the Endpoint's
          [traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split] will be overwritten with it. To
          refer to the ID of the just being deployed Model, a "0" should be used, and the actual ID of the
          new DeployedModel will be filled in its place by this method. The traffic percentage values must
          add up to 100.

          If this field is empty, then the Endpoint's
          [traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split] is not updated.
      :param retry: Designation of what errors, if any, should be retried.
      :param timeout: The timeout for this request.
      :param metadata: Strings which should be sent along with the request as metadata.


   .. py:method:: get_endpoint(project_id, region, endpoint, retry = DEFAULT, timeout = None, metadata = ())

      Gets an Endpoint.

      :param project_id: Required. The ID of the Google Cloud project that the service belongs to.
      :param region: Required. The ID of the Google Cloud region that the service belongs to.
      :param endpoint: Required. The Endpoint to get.
      :param retry: Designation of what errors, if any, should be retried.
      :param timeout: The timeout for this request.
      :param metadata: Strings which should be sent along with the request as metadata.


   .. py:method:: list_endpoints(project_id, region, filter = None, page_size = None, page_token = None, read_mask = None, order_by = None, retry = DEFAULT, timeout = None, metadata = ())

      Lists Endpoints in a Location.

      :param project_id: Required. The ID of the Google Cloud project that the service belongs to.
      :param region: Required. The ID of the Google Cloud region that the service belongs to.
      :param filter: The standard list filter.
          Supported fields:
          -  ``display_name`` supports = and !=.
          -  ``state`` supports = and !=.
          -  ``model_display_name`` supports = and !=
          Some examples of using the filter are:
          -  ``state="JOB_STATE_SUCCEEDED" AND display_name="my_job"``
          -  ``state="JOB_STATE_RUNNING" OR display_name="my_job"``
          -  ``NOT display_name="my_job"``
          -  ``state="JOB_STATE_FAILED"``
      :param page_size: The standard list page size.
      :param page_token: The standard list page token.
      :param read_mask: Mask specifying which fields to read.
      :param order_by: A comma-separated list of fields to order by, sorted in
          ascending order. Use "desc" after a field name for
          descending. Supported fields:

          -  ``display_name``
          -  ``create_time``
          -  ``update_time``

          Example: ``display_name, create_time desc``.
      :param retry: Designation of what errors, if any, should be retried.
      :param timeout: The timeout for this request.
      :param metadata: Strings which should be sent along with the request as metadata.


   .. py:method:: undeploy_model(project_id, region, endpoint, deployed_model_id, traffic_split = None, retry = DEFAULT, timeout = None, metadata = ())

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

      :param project_id: Required. The ID of the Google Cloud project that the service belongs to.
      :param region: Required. The ID of the Google Cloud region that the service belongs to.
      :param endpoint:  Required. The name of the Endpoint resource from which to undeploy a Model.
      :param deployed_model_id:  Required. The ID of the DeployedModel to be undeployed from the Endpoint.
      :param traffic_split:  If this field is provided, then the Endpoint's
          [traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split] will be overwritten with it. If
          last DeployedModel is being undeployed from the Endpoint, the [Endpoint.traffic_split] will always
          end up empty when this call returns. A DeployedModel will be successfully undeployed only if it
          doesn't have any traffic assigned to it when this method executes, or if this field unassigns any
          traffic to it.
      :param retry: Designation of what errors, if any, should be retried.
      :param timeout: The timeout for this request.
      :param metadata: Strings which should be sent along with the request as metadata.


   .. py:method:: update_endpoint(project_id, region, endpoint_id, endpoint, update_mask, retry = DEFAULT, timeout = None, metadata = ())

      Updates an Endpoint.

      :param project_id: Required. The ID of the Google Cloud project that the service belongs to.
      :param region: Required. The ID of the Google Cloud region that the service belongs to.
      :param endpoint:  Required. The Endpoint which replaces the resource on the server.
      :param update_mask:  Required. The update mask applies to the resource. See
          [google.protobuf.FieldMask][google.protobuf.FieldMask].
      :param retry: Designation of what errors, if any, should be retried.
      :param timeout: The timeout for this request.
      :param metadata: Strings which should be sent along with the request as metadata.