Package com.google.cloud.aiplatform.v1beta1

Class PredictionServiceGrpc.PredictionServiceStub

java.lang.Object

io.grpc.stub.AbstractStub<S>

io.grpc.stub.AbstractAsyncStub<PredictionServiceGrpc.PredictionServiceStub>

com.google.cloud.aiplatform.v1beta1.PredictionServiceGrpc.PredictionServiceStub

Enclosing class:

PredictionServiceGrpc

public static final class PredictionServiceGrpc.PredictionServiceStub
extends io.grpc.stub.AbstractAsyncStub<PredictionServiceGrpc.PredictionServiceStub>

A stub to allow clients to do asynchronous rpc calls to service PredictionService.

 A service for online predictions and explanations.
 

Nested Class Summary

Nested classes/interfaces inherited from class io.grpc.stub.AbstractStub

io.grpc.stub.AbstractStub.StubFactory<T extends io.grpc.stub.AbstractStub<T>>

Method Summary

Modifier and Type	Method	Description
protected PredictionServiceGrpc.PredictionServiceStub	build(io.grpc.Channel channel, io.grpc.CallOptions callOptions)
void	countTokens(CountTokensRequest request, io.grpc.stub.StreamObserver<CountTokensResponse> responseObserver)	Perform a token counting.
void	explain(ExplainRequest request, io.grpc.stub.StreamObserver<ExplainResponse> responseObserver)	Perform an online explanation.
void	predict(PredictRequest request, io.grpc.stub.StreamObserver<PredictResponse> responseObserver)	Perform an online prediction.
void	rawPredict(RawPredictRequest request, io.grpc.stub.StreamObserver<com.google.api.HttpBody> responseObserver)	Perform an online prediction with an arbitrary HTTP payload.
void	serverStreamingPredict(StreamingPredictRequest request, io.grpc.stub.StreamObserver<StreamingPredictResponse> responseObserver)	Perform a server-side streaming online prediction request for Vertex LLM streaming.

Methods inherited from class io.grpc.stub.AbstractAsyncStub

newStub, newStub

Methods inherited from class io.grpc.stub.AbstractStub

getCallOptions, getChannel, withCallCredentials, withChannel, withCompression, withDeadline, withDeadlineAfter, withExecutor, withInterceptors, withMaxInboundMessageSize, withMaxOutboundMessageSize, withOption, withWaitForReady

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

build

protected PredictionServiceGrpc.PredictionServiceStub build(io.grpc.Channel channel,
                                                            io.grpc.CallOptions callOptions)

Specified by:

build in class io.grpc.stub.AbstractStub<PredictionServiceGrpc.PredictionServiceStub>

predict

public void predict(PredictRequest request,
                    io.grpc.stub.StreamObserver<PredictResponse> responseObserver)

 Perform an online prediction.
 

rawPredict

public void rawPredict(RawPredictRequest request,
                       io.grpc.stub.StreamObserver<com.google.api.HttpBody> responseObserver)

 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.v1beta1.Endpoint] that served this
 prediction.
 * `X-Vertex-AI-Deployed-Model-Id`: ID of the Endpoint's
 [DeployedModel][google.cloud.aiplatform.v1beta1.DeployedModel] that served
 this prediction.
 

serverStreamingPredict

public void serverStreamingPredict(StreamingPredictRequest request,
                                   io.grpc.stub.StreamObserver<StreamingPredictResponse> responseObserver)

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

explain

public void explain(ExplainRequest request,
                    io.grpc.stub.StreamObserver<ExplainResponse> responseObserver)

 Perform an online explanation.
 If
 [deployed_model_id][google.cloud.aiplatform.v1beta1.ExplainRequest.deployed_model_id]
 is specified, the corresponding DeployModel must have
 [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec]
 populated. If
 [deployed_model_id][google.cloud.aiplatform.v1beta1.ExplainRequest.deployed_model_id]
 is not specified, all DeployedModels must have
 [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec]
 populated.
 

countTokens

public void countTokens(CountTokensRequest request,
                        io.grpc.stub.StreamObserver<CountTokensResponse> responseObserver)

 Perform a token counting.