Class PredictionServiceGrpc.PredictionServiceBlockingV2Stub (3.82.0)

public static final class PredictionServiceGrpc.PredictionServiceBlockingV2Stub extends AbstractBlockingStub<PredictionServiceGrpc.PredictionServiceBlockingV2Stub>

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.PredictionServiceBlockingV2Stub

Methods

build(Channel channel, CallOptions callOptions)

protected PredictionServiceGrpc.PredictionServiceBlockingV2Stub build(Channel channel, CallOptions callOptions)
Parameters
Name Description
channel io.grpc.Channel
callOptions io.grpc.CallOptions
Returns
Type Description
PredictionServiceGrpc.PredictionServiceBlockingV2Stub
Overrides
io.grpc.stub.AbstractStub.build(io.grpc.Channel,io.grpc.CallOptions)

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
Name Description
request DirectPredictRequest
Returns
Type Description
DirectPredictResponse
Exceptions
Type Description
io.grpc.StatusException

directRawPredict(DirectRawPredictRequest request)

public DirectRawPredictResponse directRawPredict(DirectRawPredictRequest request)

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

Parameter
Name Description
request DirectRawPredictRequest
Returns
Type Description
DirectRawPredictResponse
Exceptions
Type Description
io.grpc.StatusException

embedContent(EmbedContentRequest request)

public EmbedContentResponse embedContent(EmbedContentRequest request)

Embed content with multimodal inputs.

Parameter
Name Description
request EmbedContentRequest
Returns
Type Description
EmbedContentResponse
Exceptions
Type Description
io.grpc.StatusException

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
Name Description
request ExplainRequest
Returns
Type Description
ExplainResponse
Exceptions
Type Description
io.grpc.StatusException

generateContent(GenerateContentRequest request)

public GenerateContentResponse generateContent(GenerateContentRequest request)

Generate content with multimodal inputs.

Parameter
Name Description
request GenerateContentRequest
Returns
Type Description
GenerateContentResponse
Exceptions
Type Description
io.grpc.StatusException

predict(PredictRequest request)

public PredictResponse predict(PredictRequest request)

Perform an online prediction.

Parameter
Name Description
request PredictRequest
Returns
Type Description
PredictResponse
Exceptions
Type Description
io.grpc.StatusException

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
Name Description
request RawPredictRequest
Returns
Type Description
com.google.api.HttpBody
Exceptions
Type Description
io.grpc.StatusException

serverStreamingPredict(StreamingPredictRequest request)

public BlockingClientCall<?,StreamingPredictResponse> serverStreamingPredict(StreamingPredictRequest request)

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

Parameter
Name Description
request StreamingPredictRequest
Returns
Type Description
io.grpc.stub.BlockingClientCall<?,StreamingPredictResponse>

streamDirectPredict()

public BlockingClientCall<StreamDirectPredictRequest,StreamDirectPredictResponse> streamDirectPredict()

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

Returns
Type Description
io.grpc.stub.BlockingClientCall<StreamDirectPredictRequest,StreamDirectPredictResponse>

streamDirectRawPredict()

public BlockingClientCall<StreamDirectRawPredictRequest,StreamDirectRawPredictResponse> streamDirectRawPredict()

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

Returns
Type Description
io.grpc.stub.BlockingClientCall<StreamDirectRawPredictRequest,StreamDirectRawPredictResponse>

streamGenerateContent(GenerateContentRequest request)

public BlockingClientCall<?,GenerateContentResponse> streamGenerateContent(GenerateContentRequest request)

Generate content with multimodal inputs with streaming support.

Parameter
Name Description
request GenerateContentRequest
Returns
Type Description
io.grpc.stub.BlockingClientCall<?,GenerateContentResponse>

streamRawPredict(StreamRawPredictRequest request)

public BlockingClientCall<?,HttpBody> streamRawPredict(StreamRawPredictRequest request)

Perform a streaming online prediction with an arbitrary HTTP payload.

Parameter
Name Description
request StreamRawPredictRequest
Returns
Type Description
io.grpc.stub.BlockingClientCall<?,com.google.api.HttpBody>

streamingPredict()

public BlockingClientCall<StreamingPredictRequest,StreamingPredictResponse> streamingPredict()

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

Returns
Type Description
io.grpc.stub.BlockingClientCall<StreamingPredictRequest,StreamingPredictResponse>

streamingRawPredict()

public BlockingClientCall<StreamingRawPredictRequest,StreamingRawPredictResponse> streamingRawPredict()

Perform a streaming online prediction request through gRPC.

Returns
Type Description
io.grpc.stub.BlockingClientCall<StreamingRawPredictRequest,StreamingRawPredictResponse>