Class PredictionServiceGrpc.PredictionServiceBlockingStub (3.41.0)

public static final class PredictionServiceGrpc.PredictionServiceBlockingStub extends AbstractBlockingStub<PredictionServiceGrpc.PredictionServiceBlockingStub>

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

A service for online predictions and explanations.

Inheritance

java.lang.Object > io.grpc.stub.AbstractStub > io.grpc.stub.AbstractBlockingStub > PredictionServiceGrpc.PredictionServiceBlockingStub

Methods

build(Channel channel, CallOptions callOptions)

protected PredictionServiceGrpc.PredictionServiceBlockingStub build(Channel channel, CallOptions callOptions)
Parameters
NameDescription
channelio.grpc.Channel
callOptionsio.grpc.CallOptions
Returns
TypeDescription
PredictionServiceGrpc.PredictionServiceBlockingStub
Overrides
io.grpc.stub.AbstractStub.build(io.grpc.Channel,io.grpc.CallOptions)

countTokens(CountTokensRequest request)

public CountTokensResponse countTokens(CountTokensRequest request)

Perform a token counting.

Parameter
NameDescription
requestCountTokensRequest
Returns
TypeDescription
CountTokensResponse

directPredict(DirectPredictRequest request)

public DirectPredictResponse directPredict(DirectPredictRequest request)

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

Parameter
NameDescription
requestDirectPredictRequest
Returns
TypeDescription
DirectPredictResponse

directRawPredict(DirectRawPredictRequest request)

public DirectRawPredictResponse directRawPredict(DirectRawPredictRequest request)

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

Parameter
NameDescription
requestDirectRawPredictRequest
Returns
TypeDescription
DirectRawPredictResponse

explain(ExplainRequest request)

public ExplainResponse explain(ExplainRequest request)

Perform an online explanation. If deployed_model_id is specified, the corresponding DeployModel must have explanation_spec populated. If deployed_model_id is not specified, all DeployedModels must have explanation_spec populated.

Parameter
NameDescription
requestExplainRequest
Returns
TypeDescription
ExplainResponse

generateContent(GenerateContentRequest request)

public GenerateContentResponse generateContent(GenerateContentRequest request)

Generate content with multimodal inputs.

Parameter
NameDescription
requestGenerateContentRequest
Returns
TypeDescription
GenerateContentResponse

predict(PredictRequest request)

public PredictResponse predict(PredictRequest request)

Perform an online prediction.

Parameter
NameDescription
requestPredictRequest
Returns
TypeDescription
PredictResponse

rawPredict(RawPredictRequest request)

public HttpBody rawPredict(RawPredictRequest request)

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 that served this prediction.
  • X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint's DeployedModel that served this prediction.
Parameter
NameDescription
requestRawPredictRequest
Returns
TypeDescription
com.google.api.HttpBody

serverStreamingPredict(StreamingPredictRequest request)

public Iterator<StreamingPredictResponse> serverStreamingPredict(StreamingPredictRequest request)

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

Parameter
NameDescription
requestStreamingPredictRequest
Returns
TypeDescription
Iterator<StreamingPredictResponse>

streamGenerateContent(GenerateContentRequest request)

public Iterator<GenerateContentResponse> streamGenerateContent(GenerateContentRequest request)

Generate content with multimodal inputs with streaming support.

Parameter
NameDescription
requestGenerateContentRequest
Returns
TypeDescription
Iterator<GenerateContentResponse>