As of January 1, 2020 this library no longer supports Python 2 on the latest released version. Library versions released prior to that date will continue to be available. For more information please visit Python 2 support on Google Cloud.

PredictionService

class google.cloud.aiplatform_v1.services.prediction_service.PredictionServiceAsyncClient(*, credentials: ~typing.Optional[~google.auth.credentials.Credentials] = None, transport: ~typing.Optional[~typing.Union[str, ~google.cloud.aiplatform_v1.services.prediction_service.transports.base.PredictionServiceTransport, ~typing.Callable[[...], ~google.cloud.aiplatform_v1.services.prediction_service.transports.base.PredictionServiceTransport]]] = 'grpc_asyncio', client_options: ~typing.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 online predictions and explanations.

Instantiates the prediction service async client.

Parameters:

• 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 (Optional[Union[str,PredictionServiceTransport,Callable[..., PredictionServiceTransport]]]) – The transport to use, or a Callable that constructs and returns a new transport to use. If a Callable is given, it will be called with the same set of initialization arguments as used in the PredictionServiceTransport constructor. If set to None, a transport is chosen automatically.

• client_options (Optional[Union[google.api_core.client_options.ClientOptions, dict]]) –

  Custom options for the client.

  1. The api_endpoint property can be used to override the default endpoint provided by the client when transport is not explicitly provided. Only if this property is not set and transport was not explicitly provided, the endpoint is determined by the GOOGLE_API_USE_MTLS_ENDPOINT environment variable, which have one of the following values: “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).

  2. If the GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is “true”, then the client_cert_source property can be used to provide a client certificate for mTLS 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.

  3. The universe_domain property can be used to override the default “googleapis.com” universe. Note that api_endpoint property still takes precedence; and universe_domain is currently not supported for mTLS.

• client_info (google.api_core.gapic_v1.client_info.ClientInfo) – The client info used to send a user-agent string along with API requests. If None, then default info will be used. Generally, you only need to set this if you’re developing your own client library.

Raises:

google.auth.exceptions.MutualTlsChannelError – If mutual TLS transport creation failed for any reason.

property api_endpoint

Return the API endpoint used by the client instance.

Returns:

The API endpoint used by the client instance.

Return type:

str

async cancel_operation(request: Optional[CancelOperationRequest] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → None

Starts asynchronous cancellation on a long-running operation.

The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn’t support this method, it returns google.rpc.Code.UNIMPLEMENTED.

Parameters:

• request (CancelOperationRequest) – The request object. Request message for CancelOperation method.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

None

static common_billing_account_path(billing_account: str) → str

Returns a fully-qualified billing_account string.

static common_folder_path(folder: str) → str

Returns a fully-qualified folder string.

static common_location_path(project: str, location: str) → str

Returns a fully-qualified location string.

static common_organization_path(organization: str) → str

Returns a fully-qualified organization string.

static common_project_path(project: str) → str

Returns a fully-qualified project string.

async delete_operation(request: Optional[DeleteOperationRequest] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → None

Deletes a long-running operation.

This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn’t support this method, it returns google.rpc.Code.UNIMPLEMENTED.

Parameters:

• request (DeleteOperationRequest) – The request object. Request message for DeleteOperation method.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

None

async direct_predict(request: Optional[Union[DirectPredictRequest, dict]] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → DirectPredictResponse

Perform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_direct_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    request = aiplatform_v1.DirectPredictRequest(
        endpoint="endpoint_value",
    )

    # Make the request
    response = await client.direct_predict(request=request)

    # Handle the response
    print(response)

Parameters:

• request (Optional[Union[google.cloud.aiplatform_v1.types.DirectPredictRequest, dict]]) – The request object. Request message for [PredictionService.DirectPredict][google.cloud.aiplatform.v1.PredictionService.DirectPredict].

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for

[PredictionService.DirectPredict][google.cloud.aiplatform.v1.PredictionService.DirectPredict].

Return type:

google.cloud.aiplatform_v1.types.DirectPredictResponse

async direct_raw_predict(request: Optional[Union[DirectRawPredictRequest, dict]] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → DirectRawPredictResponse

Perform an unary online prediction request to a gRPC model server for custom containers.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_direct_raw_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    request = aiplatform_v1.DirectRawPredictRequest(
        endpoint="endpoint_value",
    )

    # Make the request
    response = await client.direct_raw_predict(request=request)

    # Handle the response
    print(response)

Parameters:

• request (Optional[Union[google.cloud.aiplatform_v1.types.DirectRawPredictRequest, dict]]) – The request object. Request message for [PredictionService.DirectRawPredict][google.cloud.aiplatform.v1.PredictionService.DirectRawPredict].

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for

[PredictionService.DirectRawPredict][google.cloud.aiplatform.v1.PredictionService.DirectRawPredict].

Return type:

google.cloud.aiplatform_v1.types.DirectRawPredictResponse

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

Returns a fully-qualified endpoint string.

async explain(request: Optional[Union[ExplainRequest, dict]] = None, *, endpoint: Optional[str] = None, instances: Optional[MutableSequence[Value]] = None, parameters: Optional[Value] = None, deployed_model_id: Optional[str] = None, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → ExplainResponse

Perform an online explanation.

If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_explain():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    instances = aiplatform_v1.Value()
    instances.null_value = "NULL_VALUE"

    request = aiplatform_v1.ExplainRequest(
        endpoint="endpoint_value",
        instances=instances,
    )

    # Make the request
    response = await client.explain(request=request)

    # Handle the response
    print(response)

Parameters:

• request (Optional[Union[google.cloud.aiplatform_v1.types.ExplainRequest, dict]]) – The request object. Request message for [PredictionService.Explain][google.cloud.aiplatform.v1.PredictionService.Explain].

• endpoint (str) –

  Required. The name of the Endpoint requested to serve the explanation. 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.

• instances (MutableSequence[google.protobuf.struct_pb2.Value]) –

  Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint’s DeployedModels’ [Model’s][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata’s][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri].

  This corresponds to the instances field on the request instance; if request is provided, this should not be set.

• parameters (google.protobuf.struct_pb2.Value) –

  The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint’s DeployedModels’ [Model’s ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata’s][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri].

  This corresponds to the parameters field on the request instance; if request is provided, this should not be set.

• deployed_model_id (str) –

  If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding [Endpoint.traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split].

  This corresponds to the deployed_model_id field on the request instance; if request is provided, this should not be set.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for

[PredictionService.Explain][google.cloud.aiplatform.v1.PredictionService.Explain].

Return type:

google.cloud.aiplatform_v1.types.ExplainResponse

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

Creates an instance of this client using the provided credentials

file.

Parameters:

• filename (str) – The path to the service account private key json file.

• args – Additional arguments to pass to the constructor.

• kwargs – Additional arguments to pass to the constructor.

Returns:

The constructed client.

Return type:

PredictionServiceAsyncClient

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

Creates an instance of this client using the provided credentials

info.

Parameters:

• info (dict) – The service account private key info.

• args – Additional arguments to pass to the constructor.

• kwargs – Additional arguments to pass to the constructor.

Returns:

The constructed client.

Return type:

PredictionServiceAsyncClient

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

Creates an instance of this client using the provided credentials

file.

Parameters:

• filename (str) – The path to the service account private key json file.

• args – Additional arguments to pass to the constructor.

• kwargs – Additional arguments to pass to the constructor.

Returns:

The constructed client.

Return type:

PredictionServiceAsyncClient

async generate_content(request: Optional[Union[GenerateContentRequest, dict]] = None, *, model: Optional[str] = None, contents: Optional[MutableSequence[Content]] = None, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → GenerateContentResponse

Generate content with multimodal inputs.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_generate_content():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    contents = aiplatform_v1.Content()
    contents.parts.text = "text_value"

    request = aiplatform_v1.GenerateContentRequest(
        model="model_value",
        contents=contents,
    )

    # Make the request
    response = await client.generate_content(request=request)

    # Handle the response
    print(response)

Parameters:

• request (Optional[Union[google.cloud.aiplatform_v1.types.GenerateContentRequest, dict]]) – The request object. Request message for [PredictionService.GenerateContent].

• model (str) –

  Required. The fully qualified name of the publisher model or tuned model endpoint to use.

  Publisher model format: projects/{project}/locations/{location}/publishers/*/models/*

  Tuned model endpoint format: projects/{project}/locations/{location}/endpoints/{endpoint}

  This corresponds to the model field on the request instance; if request is provided, this should not be set.

• contents (MutableSequence[google.cloud.aiplatform_v1.types.Content]) –

  Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.

  This corresponds to the contents field on the request instance; if request is provided, this should not be set.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for [PredictionService.GenerateContent].

Return type:

google.cloud.aiplatform_v1.types.GenerateContentResponse

async get_iam_policy(request: Optional[GetIamPolicyRequest] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Policy

Gets the IAM access control policy for a function.

Returns an empty policy if the function exists and does not have a policy set.

Parameters:

• request (GetIamPolicyRequest) – The request object. Request message for GetIamPolicy method.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Defines an Identity and Access Management (IAM) policy. It is used to specify access control policies for Cloud Platform resources. A Policy is a collection of bindings. A binding binds one or more members to a single role. Members can be user accounts, service accounts, Google groups, and domains (such as G Suite). A role is a named list of permissions (defined by IAM or configured by users). A binding can optionally specify a condition, which is a logic expression that further constrains the role binding based on attributes about the request and/or target resource.

JSON Example

{
  "bindings": [
    {
      "role": "roles/resourcemanager.organizationAdmin",
      "members": [
        "user:mike@example.com",
        "group:admins@example.com",
        "domain:google.com",
        "serviceAccount:my-project-id@appspot.gserviceaccount.com"
      ]
    },
    {
      "role": "roles/resourcemanager.organizationViewer",
      "members": ["user:eve@example.com"],
      "condition": {
        "title": "expirable access",
        "description": "Does not grant access after Sep 2020",
        "expression": "request.time <
        timestamp('2020-10-01T00:00:00.000Z')",
      }
    }
  ]
}

YAML Example

bindings:
- members:
  - user:mike@example.com
  - group:admins@example.com
  - domain:google.com
  - serviceAccount:my-project-id@appspot.gserviceaccount.com
  role: roles/resourcemanager.organizationAdmin
- members:
  - user:eve@example.com
  role: roles/resourcemanager.organizationViewer
  condition:
    title: expirable access
    description: Does not grant access after Sep 2020
    expression: request.time < timestamp('2020-10-01T00:00:00.000Z')

For a description of IAM and its features, see the IAM developer’s guide.

Return type:

Policy

async get_location(request: Optional[GetLocationRequest] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Location

Gets information about a location.

Parameters:

• request (GetLocationRequest) – The request object. Request message for GetLocation method.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Location object.

Return type:

Location

classmethod get_mtls_endpoint_and_cert_source(client_options: Optional[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 variable 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.

Parameters:

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.

Returns:

returns the API endpoint and the

client cert source to use.

Return type:

Tuple[str, Callable[[], Tuple[bytes, bytes]]]

Raises:

google.auth.exceptions.MutualTLSChannelError – If any errors happen.

async get_operation(request: Optional[GetOperationRequest] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Operation

Gets the latest state of a long-running operation.

Parameters:

• request (GetOperationRequest) – The request object. Request message for GetOperation method.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

An Operation object.

Return type:

Operation

classmethod get_transport_class(label: Optional[str] = None) → Type[PredictionServiceTransport]

Returns an appropriate transport class.

Parameters:

label – The name of the desired transport. If none is provided, then the first transport in the registry is used.

Returns:

The transport class to use.

async list_locations(request: Optional[ListLocationsRequest] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → ListLocationsResponse

Lists information about the supported locations for this service.

Parameters:

• request (ListLocationsRequest) – The request object. Request message for ListLocations method.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for ListLocations method.

Return type:

ListLocationsResponse

async list_operations(request: Optional[ListOperationsRequest] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → ListOperationsResponse

Lists operations that match the specified filter in the request.

Parameters:

• request (ListOperationsRequest) – The request object. Request message for ListOperations method.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for ListOperations method.

Return type:

ListOperationsResponse

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

Returns a fully-qualified model string.

static parse_common_billing_account_path(path: str) → Dict[str, str]

Parse a billing_account path into its component segments.

static parse_common_folder_path(path: str) → Dict[str, str]

Parse a folder path into its component segments.

static parse_common_location_path(path: str) → Dict[str, str]

Parse a location path into its component segments.

static parse_common_organization_path(path: str) → Dict[str, str]

Parse a organization path into its component segments.

static parse_common_project_path(path: str) → Dict[str, str]

Parse a project path into its component segments.

static parse_endpoint_path(path: str) → Dict[str, str]

Parses a endpoint path into its component segments.

static parse_model_path(path: str) → Dict[str, str]

Parses a model path into its component segments.

async predict(request: Optional[Union[PredictRequest, dict]] = None, *, endpoint: Optional[str] = None, instances: Optional[MutableSequence[Value]] = None, parameters: Optional[Value] = None, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → PredictResponse

Perform an online prediction.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    instances = aiplatform_v1.Value()
    instances.null_value = "NULL_VALUE"

    request = aiplatform_v1.PredictRequest(
        endpoint="endpoint_value",
        instances=instances,
    )

    # Make the request
    response = await client.predict(request=request)

    # Handle the response
    print(response)

Parameters:

• request (Optional[Union[google.cloud.aiplatform_v1.types.PredictRequest, dict]]) – The request object. Request message for [PredictionService.Predict][google.cloud.aiplatform.v1.PredictionService.Predict].

• endpoint (str) –

  Required. The name of the Endpoint requested to serve the prediction. 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.

• instances (MutableSequence[google.protobuf.struct_pb2.Value]) –

  Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint’s DeployedModels’ [Model’s][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata’s][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri].

  This corresponds to the instances field on the request instance; if request is provided, this should not be set.

• parameters (google.protobuf.struct_pb2.Value) –

  The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint’s DeployedModels’ [Model’s ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata’s][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri].

  This corresponds to the parameters field on the request instance; if request is provided, this should not be set.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for

[PredictionService.Predict][google.cloud.aiplatform.v1.PredictionService.Predict].

Return type:

google.cloud.aiplatform_v1.types.PredictResponse

async raw_predict(request: Optional[Union[RawPredictRequest, dict]] = None, *, endpoint: Optional[str] = None, http_body: Optional[HttpBody] = None, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → HttpBody

Perform an online prediction with an arbitrary HTTP payload.

The response includes the following HTTP headers:

• X-Vertex-AI-Endpoint-Id: ID of the [Endpoint][google.cloud.aiplatform.v1.Endpoint] that served this prediction.

• X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint’s [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_raw_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    request = aiplatform_v1.RawPredictRequest(
        endpoint="endpoint_value",
    )

    # Make the request
    response = await client.raw_predict(request=request)

    # Handle the response
    print(response)

Parameters:

• request (Optional[Union[google.cloud.aiplatform_v1.types.RawPredictRequest, dict]]) – The request object. Request message for [PredictionService.RawPredict][google.cloud.aiplatform.v1.PredictionService.RawPredict].

• endpoint (str) –

  Required. The name of the Endpoint requested to serve the prediction. 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.

• http_body (google.api.httpbody_pb2.HttpBody) –

  The prediction input. Supports HTTP headers and arbitrary data payload.

  A [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] may have an upper limit on the number of instances it supports per request. When this limit it is exceeded for an AutoML model, the [RawPredict][google.cloud.aiplatform.v1.PredictionService.RawPredict] method returns an error. When this limit is exceeded for a custom-trained model, the behavior varies depending on the model.

  You can specify the schema for each instance in the [predict_schemata.instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri] field when you create a [Model][google.cloud.aiplatform.v1.Model]. This schema applies when you deploy the Model as a DeployedModel to an [Endpoint][google.cloud.aiplatform.v1.Endpoint] and use the RawPredict method.

  This corresponds to the http_body field on the request instance; if request is provided, this should not be set.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Message that represents an arbitrary HTTP body. It should only be used for

payload formats that can’t be represented as JSON, such as raw binary or an HTML page.

This message can be used both in streaming and non-streaming API methods in the request as well as the response.

It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body.

Example:

message GetResourceRequest {

// A unique request id. string request_id = 1;

// The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2;

}

service ResourceService {

rpc GetResource(GetResourceRequest)

returns (google.api.HttpBody);

rpc UpdateResource(google.api.HttpBody)

returns (google.protobuf.Empty);

}

Example with streaming methods:

service CaldavService {

rpc GetCalendar(stream google.api.HttpBody)

returns (stream google.api.HttpBody);

rpc UpdateCalendar(stream google.api.HttpBody)

returns (stream google.api.HttpBody);

}

Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.

Return type:

google.api.httpbody_pb2.HttpBody

server_streaming_predict(request: Optional[Union[StreamingPredictRequest, dict]] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Awaitable[AsyncIterable[StreamingPredictResponse]]

Perform a server-side streaming online prediction request for Vertex LLM streaming.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_server_streaming_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamingPredictRequest(
        endpoint="endpoint_value",
    )

    # Make the request
    stream = await client.server_streaming_predict(request=request)

    # Handle the response
    async for response in stream:
        print(response)

Parameters:

• request (Optional[Union[google.cloud.aiplatform_v1.types.StreamingPredictRequest, dict]]) –

  The request object. Request message for [PredictionService.StreamingPredict][google.cloud.aiplatform.v1.PredictionService.StreamingPredict].

  The first message must contain [endpoint][google.cloud.aiplatform.v1.StreamingPredictRequest.endpoint] field and optionally [input][]. The subsequent messages must contain [input][].

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for

[PredictionService.StreamingPredict][google.cloud.aiplatform.v1.PredictionService.StreamingPredict].

Return type:

AsyncIterable[google.cloud.aiplatform_v1.types.StreamingPredictResponse]

async set_iam_policy(request: Optional[SetIamPolicyRequest] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Policy

Sets the IAM access control policy on the specified function.

Replaces any existing policy.

Parameters:

• request (SetIamPolicyRequest) – The request object. Request message for SetIamPolicy method.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Defines an Identity and Access Management (IAM) policy. It is used to specify access control policies for Cloud Platform resources. A Policy is a collection of bindings. A binding binds one or more members to a single role. Members can be user accounts, service accounts, Google groups, and domains (such as G Suite). A role is a named list of permissions (defined by IAM or configured by users). A binding can optionally specify a condition, which is a logic expression that further constrains the role binding based on attributes about the request and/or target resource.

JSON Example

{
  "bindings": [
    {
      "role": "roles/resourcemanager.organizationAdmin",
      "members": [
        "user:mike@example.com",
        "group:admins@example.com",
        "domain:google.com",
        "serviceAccount:my-project-id@appspot.gserviceaccount.com"
      ]
    },
    {
      "role": "roles/resourcemanager.organizationViewer",
      "members": ["user:eve@example.com"],
      "condition": {
        "title": "expirable access",
        "description": "Does not grant access after Sep 2020",
        "expression": "request.time <
        timestamp('2020-10-01T00:00:00.000Z')",
      }
    }
  ]
}

YAML Example

bindings:
- members:
  - user:mike@example.com
  - group:admins@example.com
  - domain:google.com
  - serviceAccount:my-project-id@appspot.gserviceaccount.com
  role: roles/resourcemanager.organizationAdmin
- members:
  - user:eve@example.com
  role: roles/resourcemanager.organizationViewer
  condition:
    title: expirable access
    description: Does not grant access after Sep 2020
    expression: request.time < timestamp('2020-10-01T00:00:00.000Z')

For a description of IAM and its features, see the IAM developer’s guide.

Return type:

Policy

stream_direct_predict(requests: Optional[AsyncIterator[StreamDirectPredictRequest]] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Awaitable[AsyncIterable[StreamDirectPredictResponse]]

Perform a streaming online prediction request to a gRPC model server for Vertex first-party products and frameworks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_stream_direct_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamDirectPredictRequest(
        endpoint="endpoint_value",
    )

    # This method expects an iterator which contains
    # 'aiplatform_v1.StreamDirectPredictRequest' objects
    # Here we create a generator that yields a single `request` for
    # demonstrative purposes.
    requests = [request]

    def request_generator():
        for request in requests:
            yield request

    # Make the request
    stream = await client.stream_direct_predict(requests=request_generator())

    # Handle the response
    async for response in stream:
        print(response)

Parameters:

• requests (AsyncIterator[google.cloud.aiplatform_v1.types.StreamDirectPredictRequest]) –

  The request object AsyncIterator. Request message for [PredictionService.StreamDirectPredict][google.cloud.aiplatform.v1.PredictionService.StreamDirectPredict].

  The first message must contain [endpoint][google.cloud.aiplatform.v1.StreamDirectPredictRequest.endpoint] field and optionally [input][]. The subsequent messages must contain [input][].

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for

[PredictionService.StreamDirectPredict][google.cloud.aiplatform.v1.PredictionService.StreamDirectPredict].

Return type:

AsyncIterable[google.cloud.aiplatform_v1.types.StreamDirectPredictResponse]

stream_direct_raw_predict(requests: Optional[AsyncIterator[StreamDirectRawPredictRequest]] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Awaitable[AsyncIterable[StreamDirectRawPredictResponse]]

Perform a streaming online prediction request to a gRPC model server for custom containers.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_stream_direct_raw_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamDirectRawPredictRequest(
        endpoint="endpoint_value",
    )

    # This method expects an iterator which contains
    # 'aiplatform_v1.StreamDirectRawPredictRequest' objects
    # Here we create a generator that yields a single `request` for
    # demonstrative purposes.
    requests = [request]

    def request_generator():
        for request in requests:
            yield request

    # Make the request
    stream = await client.stream_direct_raw_predict(requests=request_generator())

    # Handle the response
    async for response in stream:
        print(response)

Parameters:

• requests (AsyncIterator[google.cloud.aiplatform_v1.types.StreamDirectRawPredictRequest]) –

  The request object AsyncIterator. Request message for [PredictionService.StreamDirectRawPredict][google.cloud.aiplatform.v1.PredictionService.StreamDirectRawPredict].

  The first message must contain [endpoint][google.cloud.aiplatform.v1.StreamDirectRawPredictRequest.endpoint] and [method_name][google.cloud.aiplatform.v1.StreamDirectRawPredictRequest.method_name] fields and optionally [input][google.cloud.aiplatform.v1.StreamDirectRawPredictRequest.input]. The subsequent messages must contain [input][google.cloud.aiplatform.v1.StreamDirectRawPredictRequest.input]. [method_name][google.cloud.aiplatform.v1.StreamDirectRawPredictRequest.method_name] in the subsequent messages have no effect.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for

[PredictionService.StreamDirectRawPredict][google.cloud.aiplatform.v1.PredictionService.StreamDirectRawPredict].

Return type:

AsyncIterable[google.cloud.aiplatform_v1.types.StreamDirectRawPredictResponse]

stream_generate_content(request: Optional[Union[GenerateContentRequest, dict]] = None, *, model: Optional[str] = None, contents: Optional[MutableSequence[Content]] = None, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Awaitable[AsyncIterable[GenerateContentResponse]]

Generate content with multimodal inputs with streaming support.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_stream_generate_content():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    contents = aiplatform_v1.Content()
    contents.parts.text = "text_value"

    request = aiplatform_v1.GenerateContentRequest(
        model="model_value",
        contents=contents,
    )

    # Make the request
    stream = await client.stream_generate_content(request=request)

    # Handle the response
    async for response in stream:
        print(response)

Parameters:

• request (Optional[Union[google.cloud.aiplatform_v1.types.GenerateContentRequest, dict]]) – The request object. Request message for [PredictionService.GenerateContent].

• model (str) –

  Required. The fully qualified name of the publisher model or tuned model endpoint to use.

  Publisher model format: projects/{project}/locations/{location}/publishers/*/models/*

  Tuned model endpoint format: projects/{project}/locations/{location}/endpoints/{endpoint}

  This corresponds to the model field on the request instance; if request is provided, this should not be set.

• contents (MutableSequence[google.cloud.aiplatform_v1.types.Content]) –

  Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.

  This corresponds to the contents field on the request instance; if request is provided, this should not be set.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for [PredictionService.GenerateContent].

Return type:

AsyncIterable[google.cloud.aiplatform_v1.types.GenerateContentResponse]

stream_raw_predict(request: Optional[Union[StreamRawPredictRequest, dict]] = None, *, endpoint: Optional[str] = None, http_body: Optional[HttpBody] = None, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Awaitable[AsyncIterable[HttpBody]]

Perform a streaming online prediction with an arbitrary HTTP payload.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_stream_raw_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamRawPredictRequest(
        endpoint="endpoint_value",
    )

    # Make the request
    stream = await client.stream_raw_predict(request=request)

    # Handle the response
    async for response in stream:
        print(response)

Parameters:

• request (Optional[Union[google.cloud.aiplatform_v1.types.StreamRawPredictRequest, dict]]) – The request object. Request message for [PredictionService.StreamRawPredict][google.cloud.aiplatform.v1.PredictionService.StreamRawPredict].

• endpoint (str) –

  Required. The name of the Endpoint requested to serve the prediction. 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.

• http_body (google.api.httpbody_pb2.HttpBody) –

  The prediction input. Supports HTTP headers and arbitrary data payload.

  This corresponds to the http_body field on the request instance; if request is provided, this should not be set.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Message that represents an arbitrary HTTP body. It should only be used for

payload formats that can’t be represented as JSON, such as raw binary or an HTML page.

This message can be used both in streaming and non-streaming API methods in the request as well as the response.

It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body.

Example:

message GetResourceRequest {

// A unique request id. string request_id = 1;

// The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2;

}

service ResourceService {

rpc GetResource(GetResourceRequest)

returns (google.api.HttpBody);

rpc UpdateResource(google.api.HttpBody)

returns (google.protobuf.Empty);

}

Example with streaming methods:

service CaldavService {

rpc GetCalendar(stream google.api.HttpBody)

returns (stream google.api.HttpBody);

rpc UpdateCalendar(stream google.api.HttpBody)

returns (stream google.api.HttpBody);

}

Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.

Return type:

AsyncIterable[google.api.httpbody_pb2.HttpBody]

streaming_predict(requests: Optional[AsyncIterator[StreamingPredictRequest]] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Awaitable[AsyncIterable[StreamingPredictResponse]]

Perform a streaming online prediction request for Vertex first-party products and frameworks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_streaming_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamingPredictRequest(
        endpoint="endpoint_value",
    )

    # This method expects an iterator which contains
    # 'aiplatform_v1.StreamingPredictRequest' objects
    # Here we create a generator that yields a single `request` for
    # demonstrative purposes.
    requests = [request]

    def request_generator():
        for request in requests:
            yield request

    # Make the request
    stream = await client.streaming_predict(requests=request_generator())

    # Handle the response
    async for response in stream:
        print(response)

Parameters:

• requests (AsyncIterator[google.cloud.aiplatform_v1.types.StreamingPredictRequest]) –

  The request object AsyncIterator. Request message for [PredictionService.StreamingPredict][google.cloud.aiplatform.v1.PredictionService.StreamingPredict].

  The first message must contain [endpoint][google.cloud.aiplatform.v1.StreamingPredictRequest.endpoint] field and optionally [input][]. The subsequent messages must contain [input][].

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for

[PredictionService.StreamingPredict][google.cloud.aiplatform.v1.PredictionService.StreamingPredict].

Return type:

AsyncIterable[google.cloud.aiplatform_v1.types.StreamingPredictResponse]

streaming_raw_predict(requests: Optional[AsyncIterator[StreamingRawPredictRequest]] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Awaitable[AsyncIterable[StreamingRawPredictResponse]]

Perform a streaming online prediction request through gRPC.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

async def sample_streaming_raw_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceAsyncClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamingRawPredictRequest(
        endpoint="endpoint_value",
    )

    # This method expects an iterator which contains
    # 'aiplatform_v1.StreamingRawPredictRequest' objects
    # Here we create a generator that yields a single `request` for
    # demonstrative purposes.
    requests = [request]

    def request_generator():
        for request in requests:
            yield request

    # Make the request
    stream = await client.streaming_raw_predict(requests=request_generator())

    # Handle the response
    async for response in stream:
        print(response)

Parameters:

• requests (AsyncIterator[google.cloud.aiplatform_v1.types.StreamingRawPredictRequest]) –

  The request object AsyncIterator. Request message for [PredictionService.StreamingRawPredict][google.cloud.aiplatform.v1.PredictionService.StreamingRawPredict].

  The first message must contain [endpoint][google.cloud.aiplatform.v1.StreamingRawPredictRequest.endpoint] and [method_name][google.cloud.aiplatform.v1.StreamingRawPredictRequest.method_name] fields and optionally [input][google.cloud.aiplatform.v1.StreamingRawPredictRequest.input]. The subsequent messages must contain [input][google.cloud.aiplatform.v1.StreamingRawPredictRequest.input]. [method_name][google.cloud.aiplatform.v1.StreamingRawPredictRequest.method_name] in the subsequent messages have no effect.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for

[PredictionService.StreamingRawPredict][google.cloud.aiplatform.v1.PredictionService.StreamingRawPredict].

Return type:

AsyncIterable[google.cloud.aiplatform_v1.types.StreamingRawPredictResponse]

async test_iam_permissions(request: Optional[TestIamPermissionsRequest] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → TestIamPermissionsResponse

Tests the specified IAM permissions against the IAM access control

policy for a function.

If the function does not exist, this will return an empty set of permissions, not a NOT_FOUND error.

Parameters:

• request (TestIamPermissionsRequest) – The request object. Request message for TestIamPermissions method.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

Response message for TestIamPermissions method.

Return type:

TestIamPermissionsResponse

property transport: PredictionServiceTransport

Returns the transport used by the client instance.

Returns:

The transport used by the client instance.

Return type:

PredictionServiceTransport

property universe_domain: str

Return the universe domain used by the client instance.

Returns:

The universe domain used

by the client instance.

Return type:

str

async wait_operation(request: Optional[WaitOperationRequest] = None, *, retry: Optional[Union[AsyncRetry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Operation

Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state.

If the operation is already done, the latest state is immediately returned. If the timeout specified is greater than the default HTTP/RPC timeout, the HTTP/RPC timeout is used. If the server does not support this method, it returns google.rpc.Code.UNIMPLEMENTED.

Parameters:

• request (WaitOperationRequest) – The request object. Request message for WaitOperation method.

• retry (google.api_core.retry_async.AsyncRetry) – 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:

An Operation object.

Return type:

Operation

class google.cloud.aiplatform_v1.services.prediction_service.PredictionServiceClient(*, credentials: ~typing.Optional[~google.auth.credentials.Credentials] = None, transport: ~typing.Optional[~typing.Union[str, ~google.cloud.aiplatform_v1.services.prediction_service.transports.base.PredictionServiceTransport, ~typing.Callable[[...], ~google.cloud.aiplatform_v1.services.prediction_service.transports.base.PredictionServiceTransport]]] = None, client_options: ~typing.Optional[~typing.Union[~google.api_core.client_options.ClientOptions, dict]] = None, client_info: ~google.api_core.gapic_v1.client_info.ClientInfo = <google.api_core.gapic_v1.client_info.ClientInfo object>)

A service for online predictions and explanations.

Instantiates the prediction service client.

Parameters:

• 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 (Optional[Union[str,PredictionServiceTransport,Callable[..., PredictionServiceTransport]]]) – The transport to use, or a Callable that constructs and returns a new transport. If a Callable is given, it will be called with the same set of initialization arguments as used in the PredictionServiceTransport constructor. If set to None, a transport is chosen automatically.

• client_options (Optional[Union[google.api_core.client_options.ClientOptions, dict]]) –

  Custom options for the client.

  1. The api_endpoint property can be used to override the default endpoint provided by the client when transport is not explicitly provided. Only if this property is not set and transport was not explicitly provided, the endpoint is determined by the GOOGLE_API_USE_MTLS_ENDPOINT environment variable, which have one of the following values: “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).

  2. If the GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is “true”, then the client_cert_source property can be used to provide a client certificate for mTLS 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.

  3. The universe_domain property can be used to override the default “googleapis.com” universe. Note that the api_endpoint property still takes precedence; and universe_domain is currently not supported for mTLS.

• client_info (google.api_core.gapic_v1.client_info.ClientInfo) – The client info used to send a user-agent string along with API requests. If None, then default info will be used. Generally, you only need to set this if you’re developing your own client library.

Raises:

google.auth.exceptions.MutualTLSChannelError – If mutual TLS transport creation failed for any reason.

__exit__(type, value, traceback)

Releases underlying transport’s resources.

Warning

ONLY use as a context manager if the transport is NOT shared with other clients! Exiting the with block will CLOSE the transport and may cause errors in other clients!

property api_endpoint

Return the API endpoint used by the client instance.

Returns:

The API endpoint used by the client instance.

Return type:

str

cancel_operation(request: Optional[CancelOperationRequest] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → None

Starts asynchronous cancellation on a long-running operation.

The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn’t support this method, it returns google.rpc.Code.UNIMPLEMENTED.

Parameters:

• request (CancelOperationRequest) – The request object. Request message for CancelOperation method.

• 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:

None

static common_billing_account_path(billing_account: str) → str

Returns a fully-qualified billing_account string.

static common_folder_path(folder: str) → str

Returns a fully-qualified folder string.

static common_location_path(project: str, location: str) → str

Returns a fully-qualified location string.

static common_organization_path(organization: str) → str

Returns a fully-qualified organization string.

static common_project_path(project: str) → str

Returns a fully-qualified project string.

delete_operation(request: Optional[DeleteOperationRequest] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → None

Deletes a long-running operation.

This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn’t support this method, it returns google.rpc.Code.UNIMPLEMENTED.

Parameters:

• request (DeleteOperationRequest) – The request object. Request message for DeleteOperation method.

• 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:

None

direct_predict(request: Optional[Union[DirectPredictRequest, dict]] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → DirectPredictResponse

Perform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_direct_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1.DirectPredictRequest(
        endpoint="endpoint_value",
    )

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

    # Handle the response
    print(response)

Parameters:

• request (Union[google.cloud.aiplatform_v1.types.DirectPredictRequest, dict]) – The request object. Request message for [PredictionService.DirectPredict][google.cloud.aiplatform.v1.PredictionService.DirectPredict].

• 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:

Response message for

[PredictionService.DirectPredict][google.cloud.aiplatform.v1.PredictionService.DirectPredict].

Return type:

google.cloud.aiplatform_v1.types.DirectPredictResponse

direct_raw_predict(request: Optional[Union[DirectRawPredictRequest, dict]] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → DirectRawPredictResponse

Perform an unary online prediction request to a gRPC model server for custom containers.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_direct_raw_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1.DirectRawPredictRequest(
        endpoint="endpoint_value",
    )

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

    # Handle the response
    print(response)

Parameters:

• request (Union[google.cloud.aiplatform_v1.types.DirectRawPredictRequest, dict]) – The request object. Request message for [PredictionService.DirectRawPredict][google.cloud.aiplatform.v1.PredictionService.DirectRawPredict].

• 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:

Response message for

[PredictionService.DirectRawPredict][google.cloud.aiplatform.v1.PredictionService.DirectRawPredict].

Return type:

google.cloud.aiplatform_v1.types.DirectRawPredictResponse

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

Returns a fully-qualified endpoint string.

explain(request: Optional[Union[ExplainRequest, dict]] = None, *, endpoint: Optional[str] = None, instances: Optional[MutableSequence[Value]] = None, parameters: Optional[Value] = None, deployed_model_id: Optional[str] = None, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → ExplainResponse

Perform an online explanation.

If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_explain():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    instances = aiplatform_v1.Value()
    instances.null_value = "NULL_VALUE"

    request = aiplatform_v1.ExplainRequest(
        endpoint="endpoint_value",
        instances=instances,
    )

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

    # Handle the response
    print(response)

Parameters:

• request (Union[google.cloud.aiplatform_v1.types.ExplainRequest, dict]) – The request object. Request message for [PredictionService.Explain][google.cloud.aiplatform.v1.PredictionService.Explain].

• endpoint (str) –

  Required. The name of the Endpoint requested to serve the explanation. 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.

• instances (MutableSequence[google.protobuf.struct_pb2.Value]) –

  Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint’s DeployedModels’ [Model’s][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata’s][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri].

  This corresponds to the instances field on the request instance; if request is provided, this should not be set.

• parameters (google.protobuf.struct_pb2.Value) –

  The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint’s DeployedModels’ [Model’s ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata’s][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri].

  This corresponds to the parameters field on the request instance; if request is provided, this should not be set.

• deployed_model_id (str) –

  If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding [Endpoint.traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split].

  This corresponds to the deployed_model_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:

Response message for

[PredictionService.Explain][google.cloud.aiplatform.v1.PredictionService.Explain].

Return type:

google.cloud.aiplatform_v1.types.ExplainResponse

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

Creates an instance of this client using the provided credentials

file.

Parameters:

• filename (str) – The path to the service account private key json file.

• args – Additional arguments to pass to the constructor.

• kwargs – Additional arguments to pass to the constructor.

Returns:

The constructed client.

Return type:

PredictionServiceClient

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

Creates an instance of this client using the provided credentials

info.

Parameters:

• info (dict) – The service account private key info.

• args – Additional arguments to pass to the constructor.

• kwargs – Additional arguments to pass to the constructor.

Returns:

The constructed client.

Return type:

PredictionServiceClient

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

Creates an instance of this client using the provided credentials

file.

Parameters:

• filename (str) – The path to the service account private key json file.

• args – Additional arguments to pass to the constructor.

• kwargs – Additional arguments to pass to the constructor.

Returns:

The constructed client.

Return type:

PredictionServiceClient

generate_content(request: Optional[Union[GenerateContentRequest, dict]] = None, *, model: Optional[str] = None, contents: Optional[MutableSequence[Content]] = None, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → GenerateContentResponse

Generate content with multimodal inputs.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_generate_content():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    contents = aiplatform_v1.Content()
    contents.parts.text = "text_value"

    request = aiplatform_v1.GenerateContentRequest(
        model="model_value",
        contents=contents,
    )

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

    # Handle the response
    print(response)

Parameters:

• request (Union[google.cloud.aiplatform_v1.types.GenerateContentRequest, dict]) – The request object. Request message for [PredictionService.GenerateContent].

• model (str) –

  Required. The fully qualified name of the publisher model or tuned model endpoint to use.

  Publisher model format: projects/{project}/locations/{location}/publishers/*/models/*

  Tuned model endpoint format: projects/{project}/locations/{location}/endpoints/{endpoint}

  This corresponds to the model field on the request instance; if request is provided, this should not be set.

• contents (MutableSequence[google.cloud.aiplatform_v1.types.Content]) –

  Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.

  This corresponds to the contents 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:

Response message for [PredictionService.GenerateContent].

Return type:

google.cloud.aiplatform_v1.types.GenerateContentResponse

get_iam_policy(request: Optional[GetIamPolicyRequest] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Policy

Gets the IAM access control policy for a function.

Returns an empty policy if the function exists and does not have a policy set.

Parameters:

• request (GetIamPolicyRequest) – The request object. Request message for GetIamPolicy method.

• 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:

Defines an Identity and Access Management (IAM) policy. It is used to specify access control policies for Cloud Platform resources. A Policy is a collection of bindings. A binding binds one or more members to a single role. Members can be user accounts, service accounts, Google groups, and domains (such as G Suite). A role is a named list of permissions (defined by IAM or configured by users). A binding can optionally specify a condition, which is a logic expression that further constrains the role binding based on attributes about the request and/or target resource.

JSON Example

{
  "bindings": [
    {
      "role": "roles/resourcemanager.organizationAdmin",
      "members": [
        "user:mike@example.com",
        "group:admins@example.com",
        "domain:google.com",
        "serviceAccount:my-project-id@appspot.gserviceaccount.com"
      ]
    },
    {
      "role": "roles/resourcemanager.organizationViewer",
      "members": ["user:eve@example.com"],
      "condition": {
        "title": "expirable access",
        "description": "Does not grant access after Sep 2020",
        "expression": "request.time <
        timestamp('2020-10-01T00:00:00.000Z')",
      }
    }
  ]
}

YAML Example

bindings:
- members:
  - user:mike@example.com
  - group:admins@example.com
  - domain:google.com
  - serviceAccount:my-project-id@appspot.gserviceaccount.com
  role: roles/resourcemanager.organizationAdmin
- members:
  - user:eve@example.com
  role: roles/resourcemanager.organizationViewer
  condition:
    title: expirable access
    description: Does not grant access after Sep 2020
    expression: request.time < timestamp('2020-10-01T00:00:00.000Z')

For a description of IAM and its features, see the IAM developer’s guide.

Return type:

Policy

get_location(request: Optional[GetLocationRequest] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Location

Gets information about a location.

Parameters:

• request (GetLocationRequest) – The request object. Request message for GetLocation method.

• 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:

Location object.

Return type:

Location

classmethod get_mtls_endpoint_and_cert_source(client_options: Optional[ClientOptions] = None)

Deprecated. 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 variable 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.

Parameters:

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.

Returns:

returns the API endpoint and the

client cert source to use.

Return type:

Tuple[str, Callable[[], Tuple[bytes, bytes]]]

Raises:

google.auth.exceptions.MutualTLSChannelError – If any errors happen.

get_operation(request: Optional[GetOperationRequest] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Operation

Gets the latest state of a long-running operation.

Parameters:

• request (GetOperationRequest) – The request object. Request message for GetOperation method.

• 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:

An Operation object.

Return type:

Operation

list_locations(request: Optional[ListLocationsRequest] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → ListLocationsResponse

Lists information about the supported locations for this service.

Parameters:

• request (ListLocationsRequest) – The request object. Request message for ListLocations method.

• 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:

Response message for ListLocations method.

Return type:

ListLocationsResponse

list_operations(request: Optional[ListOperationsRequest] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → ListOperationsResponse

Lists operations that match the specified filter in the request.

Parameters:

• request (ListOperationsRequest) – The request object. Request message for ListOperations method.

• 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:

Response message for ListOperations method.

Return type:

ListOperationsResponse

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

Returns a fully-qualified model string.

static parse_common_billing_account_path(path: str) → Dict[str, str]

Parse a billing_account path into its component segments.

static parse_common_folder_path(path: str) → Dict[str, str]

Parse a folder path into its component segments.

static parse_common_location_path(path: str) → Dict[str, str]

Parse a location path into its component segments.

static parse_common_organization_path(path: str) → Dict[str, str]

Parse a organization path into its component segments.

static parse_common_project_path(path: str) → Dict[str, str]

Parse a project path into its component segments.

static parse_endpoint_path(path: str) → Dict[str, str]

Parses a endpoint path into its component segments.

static parse_model_path(path: str) → Dict[str, str]

Parses a model path into its component segments.

predict(request: Optional[Union[PredictRequest, dict]] = None, *, endpoint: Optional[str] = None, instances: Optional[MutableSequence[Value]] = None, parameters: Optional[Value] = None, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → PredictResponse

Perform an online prediction.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    instances = aiplatform_v1.Value()
    instances.null_value = "NULL_VALUE"

    request = aiplatform_v1.PredictRequest(
        endpoint="endpoint_value",
        instances=instances,
    )

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

    # Handle the response
    print(response)

Parameters:

• request (Union[google.cloud.aiplatform_v1.types.PredictRequest, dict]) – The request object. Request message for [PredictionService.Predict][google.cloud.aiplatform.v1.PredictionService.Predict].

• endpoint (str) –

  Required. The name of the Endpoint requested to serve the prediction. 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.

• instances (MutableSequence[google.protobuf.struct_pb2.Value]) –

  Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint’s DeployedModels’ [Model’s][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata’s][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri].

  This corresponds to the instances field on the request instance; if request is provided, this should not be set.

• parameters (google.protobuf.struct_pb2.Value) –

  The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint’s DeployedModels’ [Model’s ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata’s][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri].

  This corresponds to the parameters 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:

Response message for

[PredictionService.Predict][google.cloud.aiplatform.v1.PredictionService.Predict].

Return type:

google.cloud.aiplatform_v1.types.PredictResponse

raw_predict(request: Optional[Union[RawPredictRequest, dict]] = None, *, endpoint: Optional[str] = None, http_body: Optional[HttpBody] = None, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → HttpBody

Perform an online prediction with an arbitrary HTTP payload.

The response includes the following HTTP headers:

• X-Vertex-AI-Endpoint-Id: ID of the [Endpoint][google.cloud.aiplatform.v1.Endpoint] that served this prediction.

• X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint’s [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_raw_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1.RawPredictRequest(
        endpoint="endpoint_value",
    )

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

    # Handle the response
    print(response)

Parameters:

• request (Union[google.cloud.aiplatform_v1.types.RawPredictRequest, dict]) – The request object. Request message for [PredictionService.RawPredict][google.cloud.aiplatform.v1.PredictionService.RawPredict].

• endpoint (str) –

  Required. The name of the Endpoint requested to serve the prediction. 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.

• http_body (google.api.httpbody_pb2.HttpBody) –

  The prediction input. Supports HTTP headers and arbitrary data payload.

  A [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] may have an upper limit on the number of instances it supports per request. When this limit it is exceeded for an AutoML model, the [RawPredict][google.cloud.aiplatform.v1.PredictionService.RawPredict] method returns an error. When this limit is exceeded for a custom-trained model, the behavior varies depending on the model.

  You can specify the schema for each instance in the [predict_schemata.instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri] field when you create a [Model][google.cloud.aiplatform.v1.Model]. This schema applies when you deploy the Model as a DeployedModel to an [Endpoint][google.cloud.aiplatform.v1.Endpoint] and use the RawPredict method.

  This corresponds to the http_body 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:

Message that represents an arbitrary HTTP body. It should only be used for

payload formats that can’t be represented as JSON, such as raw binary or an HTML page.

This message can be used both in streaming and non-streaming API methods in the request as well as the response.

It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body.

Example:

message GetResourceRequest {

// A unique request id. string request_id = 1;

// The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2;

}

service ResourceService {

rpc GetResource(GetResourceRequest)

returns (google.api.HttpBody);

rpc UpdateResource(google.api.HttpBody)

returns (google.protobuf.Empty);

}

Example with streaming methods:

service CaldavService {

rpc GetCalendar(stream google.api.HttpBody)

returns (stream google.api.HttpBody);

rpc UpdateCalendar(stream google.api.HttpBody)

returns (stream google.api.HttpBody);

}

Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.

Return type:

google.api.httpbody_pb2.HttpBody

server_streaming_predict(request: Optional[Union[StreamingPredictRequest, dict]] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Iterable[StreamingPredictResponse]

Perform a server-side streaming online prediction request for Vertex LLM streaming.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_server_streaming_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamingPredictRequest(
        endpoint="endpoint_value",
    )

    # Make the request
    stream = client.server_streaming_predict(request=request)

    # Handle the response
    for response in stream:
        print(response)

Parameters:

• request (Union[google.cloud.aiplatform_v1.types.StreamingPredictRequest, dict]) –

  The request object. Request message for [PredictionService.StreamingPredict][google.cloud.aiplatform.v1.PredictionService.StreamingPredict].

  The first message must contain [endpoint][google.cloud.aiplatform.v1.StreamingPredictRequest.endpoint] field and optionally [input][]. The subsequent messages must contain [input][].

• 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:

Response message for

[PredictionService.StreamingPredict][google.cloud.aiplatform.v1.PredictionService.StreamingPredict].

Return type:

Iterable[google.cloud.aiplatform_v1.types.StreamingPredictResponse]

set_iam_policy(request: Optional[SetIamPolicyRequest] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Policy

Sets the IAM access control policy on the specified function.

Replaces any existing policy.

Parameters:

• request (SetIamPolicyRequest) – The request object. Request message for SetIamPolicy method.

• 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:

Defines an Identity and Access Management (IAM) policy. It is used to specify access control policies for Cloud Platform resources. A Policy is a collection of bindings. A binding binds one or more members to a single role. Members can be user accounts, service accounts, Google groups, and domains (such as G Suite). A role is a named list of permissions (defined by IAM or configured by users). A binding can optionally specify a condition, which is a logic expression that further constrains the role binding based on attributes about the request and/or target resource.

JSON Example

{
  "bindings": [
    {
      "role": "roles/resourcemanager.organizationAdmin",
      "members": [
        "user:mike@example.com",
        "group:admins@example.com",
        "domain:google.com",
        "serviceAccount:my-project-id@appspot.gserviceaccount.com"
      ]
    },
    {
      "role": "roles/resourcemanager.organizationViewer",
      "members": ["user:eve@example.com"],
      "condition": {
        "title": "expirable access",
        "description": "Does not grant access after Sep 2020",
        "expression": "request.time <
        timestamp('2020-10-01T00:00:00.000Z')",
      }
    }
  ]
}

YAML Example

bindings:
- members:
  - user:mike@example.com
  - group:admins@example.com
  - domain:google.com
  - serviceAccount:my-project-id@appspot.gserviceaccount.com
  role: roles/resourcemanager.organizationAdmin
- members:
  - user:eve@example.com
  role: roles/resourcemanager.organizationViewer
  condition:
    title: expirable access
    description: Does not grant access after Sep 2020
    expression: request.time < timestamp('2020-10-01T00:00:00.000Z')

For a description of IAM and its features, see the IAM developer’s guide.

Return type:

Policy

stream_direct_predict(requests: Optional[Iterator[StreamDirectPredictRequest]] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Iterable[StreamDirectPredictResponse]

Perform a streaming online prediction request to a gRPC model server for Vertex first-party products and frameworks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_stream_direct_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamDirectPredictRequest(
        endpoint="endpoint_value",
    )

    # This method expects an iterator which contains
    # 'aiplatform_v1.StreamDirectPredictRequest' objects
    # Here we create a generator that yields a single `request` for
    # demonstrative purposes.
    requests = [request]

    def request_generator():
        for request in requests:
            yield request

    # Make the request
    stream = client.stream_direct_predict(requests=request_generator())

    # Handle the response
    for response in stream:
        print(response)

Parameters:

• requests (Iterator[google.cloud.aiplatform_v1.types.StreamDirectPredictRequest]) –

  The request object iterator. Request message for [PredictionService.StreamDirectPredict][google.cloud.aiplatform.v1.PredictionService.StreamDirectPredict].

  The first message must contain [endpoint][google.cloud.aiplatform.v1.StreamDirectPredictRequest.endpoint] field and optionally [input][]. The subsequent messages must contain [input][].

• 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:

Response message for

[PredictionService.StreamDirectPredict][google.cloud.aiplatform.v1.PredictionService.StreamDirectPredict].

Return type:

Iterable[google.cloud.aiplatform_v1.types.StreamDirectPredictResponse]

stream_direct_raw_predict(requests: Optional[Iterator[StreamDirectRawPredictRequest]] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Iterable[StreamDirectRawPredictResponse]

Perform a streaming online prediction request to a gRPC model server for custom containers.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_stream_direct_raw_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamDirectRawPredictRequest(
        endpoint="endpoint_value",
    )

    # This method expects an iterator which contains
    # 'aiplatform_v1.StreamDirectRawPredictRequest' objects
    # Here we create a generator that yields a single `request` for
    # demonstrative purposes.
    requests = [request]

    def request_generator():
        for request in requests:
            yield request

    # Make the request
    stream = client.stream_direct_raw_predict(requests=request_generator())

    # Handle the response
    for response in stream:
        print(response)

Parameters:

• requests (Iterator[google.cloud.aiplatform_v1.types.StreamDirectRawPredictRequest]) –

  The request object iterator. Request message for [PredictionService.StreamDirectRawPredict][google.cloud.aiplatform.v1.PredictionService.StreamDirectRawPredict].

  The first message must contain [endpoint][google.cloud.aiplatform.v1.StreamDirectRawPredictRequest.endpoint] and [method_name][google.cloud.aiplatform.v1.StreamDirectRawPredictRequest.method_name] fields and optionally [input][google.cloud.aiplatform.v1.StreamDirectRawPredictRequest.input]. The subsequent messages must contain [input][google.cloud.aiplatform.v1.StreamDirectRawPredictRequest.input]. [method_name][google.cloud.aiplatform.v1.StreamDirectRawPredictRequest.method_name] in the subsequent messages have no effect.

• 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:

Response message for

[PredictionService.StreamDirectRawPredict][google.cloud.aiplatform.v1.PredictionService.StreamDirectRawPredict].

Return type:

Iterable[google.cloud.aiplatform_v1.types.StreamDirectRawPredictResponse]

stream_generate_content(request: Optional[Union[GenerateContentRequest, dict]] = None, *, model: Optional[str] = None, contents: Optional[MutableSequence[Content]] = None, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Iterable[GenerateContentResponse]

Generate content with multimodal inputs with streaming support.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_stream_generate_content():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    contents = aiplatform_v1.Content()
    contents.parts.text = "text_value"

    request = aiplatform_v1.GenerateContentRequest(
        model="model_value",
        contents=contents,
    )

    # Make the request
    stream = client.stream_generate_content(request=request)

    # Handle the response
    for response in stream:
        print(response)

Parameters:

• request (Union[google.cloud.aiplatform_v1.types.GenerateContentRequest, dict]) – The request object. Request message for [PredictionService.GenerateContent].

• model (str) –

  Required. The fully qualified name of the publisher model or tuned model endpoint to use.

  Publisher model format: projects/{project}/locations/{location}/publishers/*/models/*

  Tuned model endpoint format: projects/{project}/locations/{location}/endpoints/{endpoint}

  This corresponds to the model field on the request instance; if request is provided, this should not be set.

• contents (MutableSequence[google.cloud.aiplatform_v1.types.Content]) –

  Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.

  This corresponds to the contents 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:

Response message for [PredictionService.GenerateContent].

Return type:

Iterable[google.cloud.aiplatform_v1.types.GenerateContentResponse]

stream_raw_predict(request: Optional[Union[StreamRawPredictRequest, dict]] = None, *, endpoint: Optional[str] = None, http_body: Optional[HttpBody] = None, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Iterable[HttpBody]

Perform a streaming online prediction with an arbitrary HTTP payload.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_stream_raw_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamRawPredictRequest(
        endpoint="endpoint_value",
    )

    # Make the request
    stream = client.stream_raw_predict(request=request)

    # Handle the response
    for response in stream:
        print(response)

Parameters:

• request (Union[google.cloud.aiplatform_v1.types.StreamRawPredictRequest, dict]) – The request object. Request message for [PredictionService.StreamRawPredict][google.cloud.aiplatform.v1.PredictionService.StreamRawPredict].

• endpoint (str) –

  Required. The name of the Endpoint requested to serve the prediction. 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.

• http_body (google.api.httpbody_pb2.HttpBody) –

  The prediction input. Supports HTTP headers and arbitrary data payload.

  This corresponds to the http_body 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:

Message that represents an arbitrary HTTP body. It should only be used for

payload formats that can’t be represented as JSON, such as raw binary or an HTML page.

This message can be used both in streaming and non-streaming API methods in the request as well as the response.

It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body.

Example:

message GetResourceRequest {

// A unique request id. string request_id = 1;

// The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2;

}

service ResourceService {

rpc GetResource(GetResourceRequest)

returns (google.api.HttpBody);

rpc UpdateResource(google.api.HttpBody)

returns (google.protobuf.Empty);

}

Example with streaming methods:

service CaldavService {

rpc GetCalendar(stream google.api.HttpBody)

returns (stream google.api.HttpBody);

rpc UpdateCalendar(stream google.api.HttpBody)

returns (stream google.api.HttpBody);

}

Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.

Return type:

Iterable[google.api.httpbody_pb2.HttpBody]

streaming_predict(requests: Optional[Iterator[StreamingPredictRequest]] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Iterable[StreamingPredictResponse]

Perform a streaming online prediction request for Vertex first-party products and frameworks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_streaming_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamingPredictRequest(
        endpoint="endpoint_value",
    )

    # This method expects an iterator which contains
    # 'aiplatform_v1.StreamingPredictRequest' objects
    # Here we create a generator that yields a single `request` for
    # demonstrative purposes.
    requests = [request]

    def request_generator():
        for request in requests:
            yield request

    # Make the request
    stream = client.streaming_predict(requests=request_generator())

    # Handle the response
    for response in stream:
        print(response)

Parameters:

• requests (Iterator[google.cloud.aiplatform_v1.types.StreamingPredictRequest]) –

  The request object iterator. Request message for [PredictionService.StreamingPredict][google.cloud.aiplatform.v1.PredictionService.StreamingPredict].

  The first message must contain [endpoint][google.cloud.aiplatform.v1.StreamingPredictRequest.endpoint] field and optionally [input][]. The subsequent messages must contain [input][].

• 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:

Response message for

[PredictionService.StreamingPredict][google.cloud.aiplatform.v1.PredictionService.StreamingPredict].

Return type:

Iterable[google.cloud.aiplatform_v1.types.StreamingPredictResponse]

streaming_raw_predict(requests: Optional[Iterator[StreamingRawPredictRequest]] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Iterable[StreamingRawPredictResponse]

Perform a streaming online prediction request through gRPC.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.cloud import aiplatform_v1

def sample_streaming_raw_predict():
    # Create a client
    client = aiplatform_v1.PredictionServiceClient()

    # Initialize request argument(s)
    request = aiplatform_v1.StreamingRawPredictRequest(
        endpoint="endpoint_value",
    )

    # This method expects an iterator which contains
    # 'aiplatform_v1.StreamingRawPredictRequest' objects
    # Here we create a generator that yields a single `request` for
    # demonstrative purposes.
    requests = [request]

    def request_generator():
        for request in requests:
            yield request

    # Make the request
    stream = client.streaming_raw_predict(requests=request_generator())

    # Handle the response
    for response in stream:
        print(response)

Parameters:

• requests (Iterator[google.cloud.aiplatform_v1.types.StreamingRawPredictRequest]) –

  The request object iterator. Request message for [PredictionService.StreamingRawPredict][google.cloud.aiplatform.v1.PredictionService.StreamingRawPredict].

  The first message must contain [endpoint][google.cloud.aiplatform.v1.StreamingRawPredictRequest.endpoint] and [method_name][google.cloud.aiplatform.v1.StreamingRawPredictRequest.method_name] fields and optionally [input][google.cloud.aiplatform.v1.StreamingRawPredictRequest.input]. The subsequent messages must contain [input][google.cloud.aiplatform.v1.StreamingRawPredictRequest.input]. [method_name][google.cloud.aiplatform.v1.StreamingRawPredictRequest.method_name] in the subsequent messages have no effect.

• 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:

Response message for

[PredictionService.StreamingRawPredict][google.cloud.aiplatform.v1.PredictionService.StreamingRawPredict].

Return type:

Iterable[google.cloud.aiplatform_v1.types.StreamingRawPredictResponse]

test_iam_permissions(request: Optional[TestIamPermissionsRequest] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → TestIamPermissionsResponse

Tests the specified IAM permissions against the IAM access control

policy for a function.

If the function does not exist, this will return an empty set of permissions, not a NOT_FOUND error.

Parameters:

• request (TestIamPermissionsRequest) – The request object. Request message for TestIamPermissions method.

• 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:

Response message for TestIamPermissions method.

Return type:

TestIamPermissionsResponse

property transport: PredictionServiceTransport

Returns the transport used by the client instance.

Returns:

The transport used by the client

instance.

Return type:

PredictionServiceTransport

property universe_domain: str

Return the universe domain used by the client instance.

Returns:

The universe domain used by the client instance.

Return type:

str

wait_operation(request: Optional[WaitOperationRequest] = None, *, retry: Optional[Union[Retry, _MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) → Operation

Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state.

If the operation is already done, the latest state is immediately returned. If the timeout specified is greater than the default HTTP/RPC timeout, the HTTP/RPC timeout is used. If the server does not support this method, it returns google.rpc.Code.UNIMPLEMENTED.

Parameters:

• request (WaitOperationRequest) – The request object. Request message for WaitOperation method.

• 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:

An Operation object.

Return type:

Operation