Class EndpointServiceAsyncClient (1.11.0) 

EndpointServiceAsyncClient(*, credentials: Optional[google.auth.credentials.Credentials] = None, transport: Union[str, google.cloud.aiplatform_v1beta1.services.endpoint_service.transports.base.EndpointServiceTransport] = 'grpc_asyncio', client_options: Optional[google.api_core.client_options.ClientOptions] = None, client_info: google.api_core.gapic_v1.client_info.ClientInfo = <google.api_core.gapic_v1.client_info.ClientInfo object>)

A service for managing Vertex AI's Endpoints.

Inheritance

builtins.object > EndpointServiceAsyncClient

Properties

transport

Returns the transport used by the client instance.

Returns
Type Description
EndpointServiceTransport The transport used by the client instance.

Methods

EndpointServiceAsyncClient

EndpointServiceAsyncClient(*, credentials: Optional[google.auth.credentials.Credentials] = None, transport: Union[str, google.cloud.aiplatform_v1beta1.services.endpoint_service.transports.base.EndpointServiceTransport] = 'grpc_asyncio', client_options: Optional[google.api_core.client_options.ClientOptions] = None, client_info: google.api_core.gapic_v1.client_info.ClientInfo = <google.api_core.gapic_v1.client_info.ClientInfo object>)

Instantiates the endpoint service client.

Parameters
Name Description
credentials Optional[google.auth.credentials.Credentials]

The authorization credentials to attach to requests. These credentials identify the application to the service; if none are specified, the client will attempt to ascertain the credentials from the environment.
transport Union[str, `.EndpointServiceTransport`]

The transport to use. If set to None, a transport is chosen automatically.
client_options ClientOptions

Custom options for the client. It won't take effect if a transport instance is provided. (1) The api_endpoint property can be used to override the default endpoint provided by the client. GOOGLE_API_USE_MTLS_ENDPOINT environment variable can also be used to override the endpoint: "always" (always use the default mTLS endpoint), "never" (always use the default regular endpoint) and "auto" (auto switch to the default mTLS endpoint if client certificate is present, this is the default value). However, the api_endpoint property takes precedence if provided. (2) If GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is "true", then the client_cert_source property can be used to provide client certificate for mutual TLS transport. If not provided, the default SSL client certificate will be used if present. If GOOGLE_API_USE_CLIENT_CERTIFICATE is "false" or not set, no client certificate will be used.
Exceptions
Type Description
google.auth.exceptions.MutualTlsChannelError If mutual TLS transport creation failed for any reason.

common_billing_account_path

common_billing_account_path(billing_account: str)

Returns a fully-qualified billing_account string.

common_folder_path

common_folder_path(folder: str)

Returns a fully-qualified folder string.

common_location_path

common_location_path(project: str, location: str)

Returns a fully-qualified location string.

common_organization_path

common_organization_path(organization: str)

Returns a fully-qualified organization string.

common_project_path

common_project_path(project: str)

Returns a fully-qualified project string.

create_endpoint

create_endpoint(request: Optional[Union[google.cloud.aiplatform_v1beta1.types.endpoint_service.CreateEndpointRequest, dict]] = None, *, parent: Optional[str] = None, endpoint: Optional[google.cloud.aiplatform_v1beta1.types.endpoint.Endpoint] = None, endpoint_id: Optional[str] = None, retry: Union[google.api_core.retry.Retry, google.api_core.gapic_v1.method._MethodDefault] = <_MethodDefault._DEFAULT_VALUE: <object object>>, timeout: Optional[float] = None, metadata: Sequence[Tuple[str, str]] = ())

Creates an Endpoint.

from google.cloud import aiplatform_v1beta1

def sample_create_endpoint():
    # Create a client
    client = aiplatform_v1beta1.EndpointServiceClient()

    # Initialize request argument(s)
    endpoint = aiplatform_v1beta1.Endpoint()
    endpoint.display_name = "display_name_value"

    request = aiplatform_v1beta1.CreateEndpointRequest(
        parent="parent_value",
        endpoint=endpoint,
    )

    # Make the request
    operation = client.create_endpoint(request=request)

    print("Waiting for operation to complete...")

    response = operation.result()

    # Handle the response
    print(response)
Parameters
Name Description
request Union[google.cloud.aiplatform_v1beta1.types.CreateEndpointRequest, dict]

The request object. Request message for EndpointService.CreateEndpoint.
parent `str`

Required. The resource name of the Location to create the Endpoint in. Format: projects/{project}/locations/{location} This corresponds to the parent field on the request instance; if request is provided, this should not be set.
endpoint Endpoint

Required. The Endpoint to create. This corresponds to the endpoint field on the request instance; if request is provided, this should not be set.
endpoint_id `str`

Immutable. The ID to use for endpoint, which will become the final component of the endpoint resource name. If not provided, Vertex AI will generate a value for this ID. This value should be 1-10 characters, and valid characters are /[0-9]/. When using HTTP/JSON, this field is populated based on a query string argument, such as ?endpoint_id=12345. This is the fallback for fields that are not included in either the URI or the body. This corresponds to the endpoint_id field on the request instance; if request is provided, this should not be set.
retry google.api_core.retry.Retry

Designation of what errors, if any, should be retried.
timeout float

The timeout for this request.
metadata Sequence[Tuple[str, str]]

Strings which should be sent along with the request as metadata.
Returns
Type Description
google.api_core.operation_async.AsyncOperation An object representing a long-running operation. The result type for the operation will be Endpoint Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.

delete_endpoint

delete_endpoint(request: Optional[Union[google.cloud.aiplatform_v1beta1.types.endpoint_service.DeleteEndpointRequest, dict]] = None, *, name: Optional[str] = None, retry: Union[google.api_core.retry.Retry, google.api_core.gapic_v1.method._MethodDefault] = <_MethodDefault._DEFAULT_VALUE: <object object>>, timeout: Optional[float] = None, metadata: Sequence[Tuple[str, str]] = ())

Deletes an Endpoint.

from google.cloud import aiplatform_v1beta1

def sample_delete_endpoint():
    # Create a client
    client = aiplatform_v1beta1.EndpointServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1beta1.DeleteEndpointRequest(
        name="name_value",
    )

    # Make the request
    operation = client.delete_endpoint(request=request)

    print("Waiting for operation to complete...")

    response = operation.result()

    # Handle the response
    print(response)
Parameters
Name Description
request Union[google.cloud.aiplatform_v1beta1.types.DeleteEndpointRequest, dict]

The request object. Request message for EndpointService.DeleteEndpoint.
name `str`

Required. The name of the Endpoint resource to be deleted. Format: projects/{project}/locations/{location}/endpoints/{endpoint} This corresponds to the name field on the request instance; if request is provided, this should not be set.
retry google.api_core.retry.Retry

Designation of what errors, if any, should be retried.
timeout float

The timeout for this request.
metadata Sequence[Tuple[str, str]]

Strings which should be sent along with the request as metadata.
Returns
Type Description
google.api_core.operation_async.AsyncOperation An object representing a long-running operation. The result type for the operation will be `google.protobuf.empty_pb2.Empty` A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } The JSON representation for Empty is empty JSON object {}.

deploy_model

deploy_model(request: Optional[Union[google.cloud.aiplatform_v1beta1.types.endpoint_service.DeployModelRequest, dict]] = None, *, endpoint: Optional[str] = None, deployed_model: Optional[google.cloud.aiplatform_v1beta1.types.endpoint.DeployedModel] = None, traffic_split: Optional[Sequence[google.cloud.aiplatform_v1beta1.types.endpoint_service.DeployModelRequest.TrafficSplitEntry]] = None, retry: Union[google.api_core.retry.Retry, google.api_core.gapic_v1.method._MethodDefault] = <_MethodDefault._DEFAULT_VALUE: <object object>>, timeout: Optional[float] = None, metadata: Sequence[Tuple[str, str]] = ())

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

from google.cloud import aiplatform_v1beta1

def sample_deploy_model():
    # Create a client
    client = aiplatform_v1beta1.EndpointServiceClient()

    # Initialize request argument(s)
    deployed_model = aiplatform_v1beta1.DeployedModel()
    deployed_model.dedicated_resources.min_replica_count = 1803
    deployed_model.model = "model_value"

    request = aiplatform_v1beta1.DeployModelRequest(
        endpoint="endpoint_value",
        deployed_model=deployed_model,
    )

    # Make the request
    operation = client.deploy_model(request=request)

    print("Waiting for operation to complete...")

    response = operation.result()

    # Handle the response
    print(response)
Parameters
Name Description
request Union[google.cloud.aiplatform_v1beta1.types.DeployModelRequest, dict]

The request object. Request message for EndpointService.DeployModel.
endpoint `str`

Required. The name of the Endpoint resource into which to deploy a Model. Format: projects/{project}/locations/{location}/endpoints/{endpoint} This corresponds to the endpoint field on the request instance; if request is provided, this should not be set.
deployed_model DeployedModel

Required. The DeployedModel to be created within the Endpoint. Note that Endpoint.traffic_split must be updated for the DeployedModel to start receiving traffic, either as part of this call, or via EndpointService.UpdateEndpoint. This corresponds to the deployed_model field on the request instance; if request is provided, this should not be set.
traffic_split :class:`Sequence[google.cloud.aiplatform_v1beta1.types.DeployModelRequest.TrafficSplitEntry]`

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

Designation of what errors, if any, should be retried.
timeout float

The timeout for this request.
metadata Sequence[Tuple[str, str]]

Strings which should be sent along with the request as metadata.
Returns
Type Description
google.api_core.operation_async.AsyncOperation An object representing a long-running operation. The result type for the operation will be DeployModelResponse Response message for EndpointService.DeployModel.

endpoint_path

endpoint_path(project: str, location: str, endpoint: str)

Returns a fully-qualified endpoint string.

from_service_account_file

from_service_account_file(filename: str, *args, **kwargs)

Creates an instance of this client using the provided credentials file.

Parameter
Name Description
filename str

The path to the service account private key json file.
Returns
Type Description
EndpointServiceAsyncClient The constructed client.

from_service_account_info

from_service_account_info(info: dict, *args, **kwargs)

Creates an instance of this client using the provided credentials info.

Parameter
Name Description
info dict

The service account private key info.
Returns
Type Description
EndpointServiceAsyncClient The constructed client.

from_service_account_json

from_service_account_json(filename: str, *args, **kwargs)

Creates an instance of this client using the provided credentials file.

Parameter
Name Description
filename str

The path to the service account private key json file.
Returns
Type Description
EndpointServiceAsyncClient The constructed client.

get_endpoint

get_endpoint(request: Optional[Union[google.cloud.aiplatform_v1beta1.types.endpoint_service.GetEndpointRequest, dict]] = None, *, name: Optional[str] = None, retry: Union[google.api_core.retry.Retry, google.api_core.gapic_v1.method._MethodDefault] = <_MethodDefault._DEFAULT_VALUE: <object object>>, timeout: Optional[float] = None, metadata: Sequence[Tuple[str, str]] = ())

Gets an Endpoint.

from google.cloud import aiplatform_v1beta1

def sample_get_endpoint():
    # Create a client
    client = aiplatform_v1beta1.EndpointServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1beta1.GetEndpointRequest(
        name="name_value",
    )

    # Make the request
    response = client.get_endpoint(request=request)

    # Handle the response
    print(response)
Parameters
Name Description
request Union[google.cloud.aiplatform_v1beta1.types.GetEndpointRequest, dict]

The request object. Request message for EndpointService.GetEndpoint
name `str`

Required. The name of the Endpoint resource. Format: projects/{project}/locations/{location}/endpoints/{endpoint} This corresponds to the name field on the request instance; if request is provided, this should not be set.
retry google.api_core.retry.Retry

Designation of what errors, if any, should be retried.
timeout float

The timeout for this request.
metadata Sequence[Tuple[str, str]]

Strings which should be sent along with the request as metadata.
Returns
Type Description
google.cloud.aiplatform_v1beta1.types.Endpoint Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.

get_mtls_endpoint_and_cert_source

get_mtls_endpoint_and_cert_source(
    client_options: Optional[google.api_core.client_options.ClientOptions] = None,
)

Return the API endpoint and client cert source for mutual TLS.

The client cert source is determined in the following order: (1) if GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is not "true", the client cert source is None. (2) if client_options.client_cert_source is provided, use the provided one; if the default client cert source exists, use the default one; otherwise the client cert source is None.

The API endpoint is determined in the following order: (1) if client_options.api_endpoint if provided, use the provided one. (2) if GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is "always", use the default mTLS endpoint; if the environment variabel is "never", use the default API endpoint; otherwise if client cert source exists, use the default mTLS endpoint, otherwise use the default API endpoint.

More details can be found at https://google.aip.dev/auth/4114.

Parameter
Name Description
client_options google.api_core.client_options.ClientOptions

Custom options for the client. Only the api_endpoint and client_cert_source properties may be used in this method.
Exceptions
Type Description
google.auth.exceptions.MutualTLSChannelError If any errors happen.
Returns
Type Description
Tuple[str, Callable[[], Tuple[bytes, bytes]]] returns the API endpoint and the client cert source to use.

get_transport_class

get_transport_class()

Returns an appropriate transport class.

list_endpoints

list_endpoints(request: Optional[Union[google.cloud.aiplatform_v1beta1.types.endpoint_service.ListEndpointsRequest, dict]] = None, *, parent: Optional[str] = None, retry: Union[google.api_core.retry.Retry, google.api_core.gapic_v1.method._MethodDefault] = <_MethodDefault._DEFAULT_VALUE: <object object>>, timeout: Optional[float] = None, metadata: Sequence[Tuple[str, str]] = ())

Lists Endpoints in a Location.

from google.cloud import aiplatform_v1beta1

def sample_list_endpoints():
    # Create a client
    client = aiplatform_v1beta1.EndpointServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1beta1.ListEndpointsRequest(
        parent="parent_value",
    )

    # Make the request
    page_result = client.list_endpoints(request=request)

    # Handle the response
    for response in page_result:
        print(response)
Parameters
Name Description
request Union[google.cloud.aiplatform_v1beta1.types.ListEndpointsRequest, dict]

The request object. Request message for EndpointService.ListEndpoints.
parent `str`

Required. The resource name of the Location from which to list the Endpoints. Format: projects/{project}/locations/{location} This corresponds to the parent field on the request instance; if request is provided, this should not be set.
retry google.api_core.retry.Retry

Designation of what errors, if any, should be retried.
timeout float

The timeout for this request.
metadata Sequence[Tuple[str, str]]

Strings which should be sent along with the request as metadata.
Returns
Type Description
google.cloud.aiplatform_v1beta1.services.endpoint_service.pagers.ListEndpointsAsyncPager Response message for EndpointService.ListEndpoints. Iterating over this object will yield results and resolve additional pages automatically.

model_deployment_monitoring_job_path

model_deployment_monitoring_job_path(
    project: str, location: str, model_deployment_monitoring_job: str
)

Returns a fully-qualified model_deployment_monitoring_job string.

model_path

model_path(project: str, location: str, model: str)

Returns a fully-qualified model string.

network_path

network_path(project: str, network: str)

Returns a fully-qualified network string.

parse_common_billing_account_path

parse_common_billing_account_path(path: str)

Parse a billing_account path into its component segments.

parse_common_folder_path

parse_common_folder_path(path: str)

Parse a folder path into its component segments.

parse_common_location_path

parse_common_location_path(path: str)

Parse a location path into its component segments.

parse_common_organization_path

parse_common_organization_path(path: str)

Parse a organization path into its component segments.

parse_common_project_path

parse_common_project_path(path: str)

Parse a project path into its component segments.

parse_endpoint_path

parse_endpoint_path(path: str)

Parses a endpoint path into its component segments.

parse_model_deployment_monitoring_job_path

parse_model_deployment_monitoring_job_path(path: str)

Parses a model_deployment_monitoring_job path into its component segments.

parse_model_path

parse_model_path(path: str)

Parses a model path into its component segments.

parse_network_path

parse_network_path(path: str)

Parses a network path into its component segments.

undeploy_model

undeploy_model(request: Optional[Union[google.cloud.aiplatform_v1beta1.types.endpoint_service.UndeployModelRequest, dict]] = None, *, endpoint: Optional[str] = None, deployed_model_id: Optional[str] = None, traffic_split: Optional[Sequence[google.cloud.aiplatform_v1beta1.types.endpoint_service.UndeployModelRequest.TrafficSplitEntry]] = None, retry: Union[google.api_core.retry.Retry, google.api_core.gapic_v1.method._MethodDefault] = <_MethodDefault._DEFAULT_VALUE: <object object>>, timeout: Optional[float] = None, metadata: Sequence[Tuple[str, str]] = ())

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

from google.cloud import aiplatform_v1beta1

def sample_undeploy_model():
    # Create a client
    client = aiplatform_v1beta1.EndpointServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1beta1.UndeployModelRequest(
        endpoint="endpoint_value",
        deployed_model_id="deployed_model_id_value",
    )

    # Make the request
    operation = client.undeploy_model(request=request)

    print("Waiting for operation to complete...")

    response = operation.result()

    # Handle the response
    print(response)
Parameters
Name Description
request Union[google.cloud.aiplatform_v1beta1.types.UndeployModelRequest, dict]

The request object. Request message for EndpointService.UndeployModel.
endpoint `str`

Required. The name of the Endpoint resource from which to undeploy a Model. Format: projects/{project}/locations/{location}/endpoints/{endpoint} This corresponds to the endpoint field on the request instance; if request is provided, this should not be set.
deployed_model_id `str`

Required. The ID of the DeployedModel to be undeployed from the Endpoint. This corresponds to the deployed_model_id field on the request instance; if request is provided, this should not be set.
traffic_split :class:`Sequence[google.cloud.aiplatform_v1beta1.types.UndeployModelRequest.TrafficSplitEntry]`

If this field is provided, then the Endpoint's 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. This corresponds to the traffic_split field on the request instance; if request is provided, this should not be set.
retry google.api_core.retry.Retry

Designation of what errors, if any, should be retried.
timeout float

The timeout for this request.
metadata Sequence[Tuple[str, str]]

Strings which should be sent along with the request as metadata.
Returns
Type Description
google.api_core.operation_async.AsyncOperation An object representing a long-running operation. The result type for the operation will be UndeployModelResponse Response message for EndpointService.UndeployModel.

update_endpoint

update_endpoint(request: Optional[Union[google.cloud.aiplatform_v1beta1.types.endpoint_service.UpdateEndpointRequest, dict]] = None, *, endpoint: Optional[google.cloud.aiplatform_v1beta1.types.endpoint.Endpoint] = None, update_mask: Optional[google.protobuf.field_mask_pb2.FieldMask] = None, retry: Union[google.api_core.retry.Retry, google.api_core.gapic_v1.method._MethodDefault] = <_MethodDefault._DEFAULT_VALUE: <object object>>, timeout: Optional[float] = None, metadata: Sequence[Tuple[str, str]] = ())

Updates an Endpoint.

from google.cloud import aiplatform_v1beta1

def sample_update_endpoint():
    # Create a client
    client = aiplatform_v1beta1.EndpointServiceClient()

    # Initialize request argument(s)
    endpoint = aiplatform_v1beta1.Endpoint()
    endpoint.display_name = "display_name_value"

    request = aiplatform_v1beta1.UpdateEndpointRequest(
        endpoint=endpoint,
    )

    # Make the request
    response = client.update_endpoint(request=request)

    # Handle the response
    print(response)
Parameters
Name Description
request Union[google.cloud.aiplatform_v1beta1.types.UpdateEndpointRequest, dict]

The request object. Request message for EndpointService.UpdateEndpoint.
endpoint Endpoint

Required. The Endpoint which replaces the resource on the server. This corresponds to the endpoint field on the request instance; if request is provided, this should not be set.
update_mask `google.protobuf.field_mask_pb2.FieldMask`

Required. The update mask applies to the resource. See google.protobuf.FieldMask][google.protobuf.FieldMask]. This corresponds to the update_mask field on the request instance; if request is provided, this should not be set.
retry google.api_core.retry.Retry

Designation of what errors, if any, should be retried.
timeout float

The timeout for this request.
metadata Sequence[Tuple[str, str]]

Strings which should be sent along with the request as metadata.
Returns
Type Description
google.cloud.aiplatform_v1beta1.types.Endpoint Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.