Class PredictionServiceClient (2.15.1)

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][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.

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.

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.

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.