Class PredictionServiceClient (2.29.0-rc)

Version 2.29.0-rc

• 2.37.0-rc (latest)
• 2.36.0
• 2.35.0
• 2.34.0
• 2.33.0
• 2.32.0
• 2.31.0
• 2.30.0
• 2.29.0
• 2.28.0
• 2.27.0
• 2.26.0
• 2.25.1
• 2.24.0
• 2.23.0
• 2.22.1
• 2.21.0
• 2.20.0
• 2.19.0
• 2.18.0
• 2.17.0
• 2.16.0
• 2.15.1
• 2.14.0
• 2.13.0
• 2.12.0

A service for online predictions and explanations.

Equality

Instances of this class created via copy-construction or copy-assignment always compare equal. Instances created with equal std::shared_ptr<*Connection> objects compare equal. Objects that compare equal share the same underlying resources.

Performance

Creating a new instance of this class is a relatively expensive operation, new objects establish new connections to the service. In contrast, copy-construction, move-construction, and the corresponding assignment operations are relatively efficient as the copies share all underlying resources.

Thread Safety

Concurrent access to different instances of this class, even if they compare equal, is guaranteed to work. Two or more threads operating on the same instance of this class is not guaranteed to work. Since copy-construction and move-construction is a relatively efficient operation, consider using such a copy when using this class from multiple threads.

Constructors

PredictionServiceClient(PredictionServiceClient const &)

Copy and move support

Parameter
Name	Description
	PredictionServiceClient const &

PredictionServiceClient(PredictionServiceClient &&)

Copy and move support

Parameter
Name	Description
	PredictionServiceClient &&

PredictionServiceClient(std::shared_ptr< PredictionServiceConnection >, Options)

Parameters
Name	Description
connection	std::shared_ptr< PredictionServiceConnection >
opts	Options

Operators

operator=(PredictionServiceClient const &)

Copy and move support

Parameter
Name	Description
	PredictionServiceClient const &

Returns
Type	Description
PredictionServiceClient &

operator=(PredictionServiceClient &&)

Copy and move support

Parameter
Name	Description
	PredictionServiceClient &&

Returns
Type	Description
PredictionServiceClient &

Functions

Predict(std::string const &, std::vector< google::protobuf::Value > const &, google::protobuf::Value const &, Options)

Perform an online prediction.

Parameters
Name	Description
endpoint	std::string const & Required. The name of the Endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
instances	std::vector< google::protobuf::Value > const & 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].
parameters	google::protobuf::Value const & 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].
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StatusOr< google::cloud::aiplatform::v1::PredictResponse >	the result of the RPC. The response message type (google.cloud.aiplatform.v1.PredictResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

Predict(google::cloud::aiplatform::v1::PredictRequest const &, Options)

Perform an online prediction.

Parameters
Name	Description
request	google::cloud::aiplatform::v1::PredictRequest const & Unary RPCs, such as the one wrapped by this function, receive a single request proto message which includes all the inputs for the RPC. In this case, the proto message is a google.cloud.aiplatform.v1.PredictRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StatusOr< google::cloud::aiplatform::v1::PredictResponse >	the result of the RPC. The response message type (google.cloud.aiplatform.v1.PredictResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

RawPredict(std::string const &, google::api::HttpBody const &, Options)

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.

Parameters
Name	Description
endpoint	std::string const & Required. The name of the Endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
http_body	google::api::HttpBody const & 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 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.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StatusOr< google::api::HttpBody >	the result of the RPC. The response message type (google.api.HttpBody) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

RawPredict(google::cloud::aiplatform::v1::RawPredictRequest const &, Options)

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.

Parameters
Name	Description
request	google::cloud::aiplatform::v1::RawPredictRequest const & Unary RPCs, such as the one wrapped by this function, receive a single request proto message which includes all the inputs for the RPC. In this case, the proto message is a google.cloud.aiplatform.v1.RawPredictRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StatusOr< google::api::HttpBody >	the result of the RPC. The response message type (google.api.HttpBody) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

StreamRawPredict(std::string const &, google::api::HttpBody const &, Options)

Perform a streaming online prediction with an arbitrary HTTP payload.

Parameters
Name	Description
endpoint	std::string const & Required. The name of the Endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
http_body	google::api::HttpBody const & The prediction input. Supports HTTP headers and arbitrary data payload.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StreamRange< google::api::HttpBody >	the result of the RPC. The response message type (google.api.HttpBody) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

StreamRawPredict(google::cloud::aiplatform::v1::StreamRawPredictRequest const &, Options)

Perform a streaming online prediction with an arbitrary HTTP payload.

Parameters
Name	Description
request	google::cloud::aiplatform::v1::StreamRawPredictRequest const & Unary RPCs, such as the one wrapped by this function, receive a single request proto message which includes all the inputs for the RPC. In this case, the proto message is a google.cloud.aiplatform.v1.StreamRawPredictRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StreamRange< google::api::HttpBody >	the result of the RPC. The response message type (google.api.HttpBody) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

DirectPredict(google::cloud::aiplatform::v1::DirectPredictRequest const &, Options)

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

Parameters
Name	Description
request	google::cloud::aiplatform::v1::DirectPredictRequest const & Unary RPCs, such as the one wrapped by this function, receive a single request proto message which includes all the inputs for the RPC. In this case, the proto message is a google.cloud.aiplatform.v1.DirectPredictRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StatusOr< google::cloud::aiplatform::v1::DirectPredictResponse >	the result of the RPC. The response message type (google.cloud.aiplatform.v1.DirectPredictResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

DirectRawPredict(google::cloud::aiplatform::v1::DirectRawPredictRequest const &, Options)

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

Parameters
Name	Description
request	google::cloud::aiplatform::v1::DirectRawPredictRequest const & Unary RPCs, such as the one wrapped by this function, receive a single request proto message which includes all the inputs for the RPC. In this case, the proto message is a google.cloud.aiplatform.v1.DirectRawPredictRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StatusOr< google::cloud::aiplatform::v1::DirectRawPredictResponse >	the result of the RPC. The response message type (google.cloud.aiplatform.v1.DirectRawPredictResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

AsyncStreamDirectPredict(Options)

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

Parameter
Name	Description
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
std::unique_ptr<::google::cloud::AsyncStreamingReadWriteRpc< google::cloud::aiplatform::v1::StreamDirectPredictRequest, google::cloud::aiplatform::v1::StreamDirectPredictResponse > >	An object representing the bidirectional streaming RPC. Applications can send multiple request messages and receive multiple response messages through this API. Bidirectional streaming RPCs can impose restrictions on the sequence of request and response messages. Please consult the service documentation for details. The request message type (google.cloud.aiplatform.v1.StreamDirectPredictRequest) and response messages (google.cloud.aiplatform.v1.StreamDirectPredictResponse) are mapped to C++ classes using the Protobuf mapping rules.

AsyncStreamDirectRawPredict(Options)

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

Parameter
Name	Description
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
std::unique_ptr<::google::cloud::AsyncStreamingReadWriteRpc< google::cloud::aiplatform::v1::StreamDirectRawPredictRequest, google::cloud::aiplatform::v1::StreamDirectRawPredictResponse > >	An object representing the bidirectional streaming RPC. Applications can send multiple request messages and receive multiple response messages through this API. Bidirectional streaming RPCs can impose restrictions on the sequence of request and response messages. Please consult the service documentation for details. The request message type (google.cloud.aiplatform.v1.StreamDirectRawPredictRequest) and response messages (google.cloud.aiplatform.v1.StreamDirectRawPredictResponse) are mapped to C++ classes using the Protobuf mapping rules.

AsyncStreamingPredict(Options)

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

Parameter
Name	Description
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
std::unique_ptr<::google::cloud::AsyncStreamingReadWriteRpc< google::cloud::aiplatform::v1::StreamingPredictRequest, google::cloud::aiplatform::v1::StreamingPredictResponse > >	An object representing the bidirectional streaming RPC. Applications can send multiple request messages and receive multiple response messages through this API. Bidirectional streaming RPCs can impose restrictions on the sequence of request and response messages. Please consult the service documentation for details. The request message type (google.cloud.aiplatform.v1.StreamingPredictRequest) and response messages (google.cloud.aiplatform.v1.StreamingPredictResponse) are mapped to C++ classes using the Protobuf mapping rules.

ServerStreamingPredict(google::cloud::aiplatform::v1::StreamingPredictRequest const &, Options)

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

Parameters
Name	Description
request	google::cloud::aiplatform::v1::StreamingPredictRequest const & Unary RPCs, such as the one wrapped by this function, receive a single request proto message which includes all the inputs for the RPC. In this case, the proto message is a google.cloud.aiplatform.v1.StreamingPredictRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StreamRange< google::cloud::aiplatform::v1::StreamingPredictResponse >	the result of the RPC. The response message type (google.cloud.aiplatform.v1.StreamingPredictResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

AsyncStreamingRawPredict(Options)

Perform a streaming online prediction request through gRPC.

Parameter
Name	Description
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
std::unique_ptr<::google::cloud::AsyncStreamingReadWriteRpc< google::cloud::aiplatform::v1::StreamingRawPredictRequest, google::cloud::aiplatform::v1::StreamingRawPredictResponse > >	An object representing the bidirectional streaming RPC. Applications can send multiple request messages and receive multiple response messages through this API. Bidirectional streaming RPCs can impose restrictions on the sequence of request and response messages. Please consult the service documentation for details. The request message type (google.cloud.aiplatform.v1.StreamingRawPredictRequest) and response messages (google.cloud.aiplatform.v1.StreamingRawPredictResponse) are mapped to C++ classes using the Protobuf mapping rules.

Explain(std::string const &, std::vector< google::protobuf::Value > const &, google::protobuf::Value const &, std::string const &, Options)

Perform an online explanation.

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

Parameters
Name	Description
endpoint	std::string const & Required. The name of the Endpoint requested to serve the explanation. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
instances	std::vector< google::protobuf::Value > const & 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].
parameters	google::protobuf::Value const & 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].
deployed_model_id	std::string const & If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding [Endpoint.traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split].
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StatusOr< google::cloud::aiplatform::v1::ExplainResponse >	the result of the RPC. The response message type (google.cloud.aiplatform.v1.ExplainResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

Explain(google::cloud::aiplatform::v1::ExplainRequest const &, Options)

Perform an online explanation.

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

Parameters
Name	Description
request	google::cloud::aiplatform::v1::ExplainRequest const & Unary RPCs, such as the one wrapped by this function, receive a single request proto message which includes all the inputs for the RPC. In this case, the proto message is a google.cloud.aiplatform.v1.ExplainRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StatusOr< google::cloud::aiplatform::v1::ExplainResponse >	the result of the RPC. The response message type (google.cloud.aiplatform.v1.ExplainResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

GenerateContent(std::string const &, std::vector< google::cloud::aiplatform::v1::Content > const &, Options)

Generate content with multimodal inputs.

Parameters
Name	Description
model	std::string const & 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}
contents	std::vector< google::cloud::aiplatform::v1::Content > const & 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.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StatusOr< google::cloud::aiplatform::v1::GenerateContentResponse >	the result of the RPC. The response message type (google.cloud.aiplatform.v1.GenerateContentResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

GenerateContent(google::cloud::aiplatform::v1::GenerateContentRequest const &, Options)

Generate content with multimodal inputs.

Parameters
Name	Description
request	google::cloud::aiplatform::v1::GenerateContentRequest const & Unary RPCs, such as the one wrapped by this function, receive a single request proto message which includes all the inputs for the RPC. In this case, the proto message is a google.cloud.aiplatform.v1.GenerateContentRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StatusOr< google::cloud::aiplatform::v1::GenerateContentResponse >	the result of the RPC. The response message type (google.cloud.aiplatform.v1.GenerateContentResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

StreamGenerateContent(std::string const &, std::vector< google::cloud::aiplatform::v1::Content > const &, Options)

Generate content with multimodal inputs with streaming support.

Parameters
Name	Description
model	std::string const & 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}
contents	std::vector< google::cloud::aiplatform::v1::Content > const & 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.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StreamRange< google::cloud::aiplatform::v1::GenerateContentResponse >	the result of the RPC. The response message type (google.cloud.aiplatform.v1.GenerateContentResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.

StreamGenerateContent(google::cloud::aiplatform::v1::GenerateContentRequest const &, Options)

Generate content with multimodal inputs with streaming support.

Parameters
Name	Description
request	google::cloud::aiplatform::v1::GenerateContentRequest const & Unary RPCs, such as the one wrapped by this function, receive a single request proto message which includes all the inputs for the RPC. In this case, the proto message is a google.cloud.aiplatform.v1.GenerateContentRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
opts	Options Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
StreamRange< google::cloud::aiplatform::v1::GenerateContentResponse >	the result of the RPC. The response message type (google.cloud.aiplatform.v1.GenerateContentResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the StatusOr contains the error details.