public static final class PredictionServiceGrpc.PredictionServiceBlockingStub extends AbstractBlockingStub<PredictionServiceGrpc.PredictionServiceBlockingStub>
Uno stub per consentire ai client di effettuare chiamate RPC sincrone al servizio PredictionService.
Un servizio per previsioni e spiegazioni online.
Ereditarietà
java.lang.Object >
io.grpc.stub.AbstractStub >
io.grpc.stub.AbstractBlockStub >
PredictionServiceGrpc.PredictionServiceBlockStub
Membri ereditati
io.grpc.stub.AbstractBlockingStub.<T>newStub(io.grpc.stub.AbstractStub.StubFactory<T>,io.grpc.Channel)
io.grpc.stub.AbstractBlockingStub.<T>newStub(io.grpc.stub.AbstractStub.StubFactory<T>,io.grpc.Channel,io.grpc.CallOptions)
io.grpc.stub.AbstractStub.<T>withOption(io.grpc.CallOptions.Key<T>,T)
io.grpc.stub.AbstractStub.build(io.grpc.Channel,io.grpc.CallOptions)
io.grpc.stub.AbstractStub.getCallOptions()
io.grpc.stub.AbstractStub.getChannel()
io.grpc.stub.AbstractStub.withCallCredentials(io.grpc.CallCredentials)
io.grpc.stub.AbstractStub.withChannel(io.grpc.Channel)
io.grpc.stub.AbstractStub.withCompression(java.lang.String)
io.grpc.stub.AbstractStub.withDeadline(io.grpc.Deadline)
io.grpc.stub.AbstractStub.withDeadlineAfter(long,java.util.concurrent.TimeUnit)
io.grpc.stub.AbstractStub.withExecutor(java.util.concurrent.Executor)
io.grpc.stub.AbstractStub.withInterceptors(io.grpc.ClientInterceptor...)
io.grpc.stub.AbstractStub.withMaxInboundMessageSize(int)
io.grpc.stub.AbstractStub.withMaxOutboundMessageSize(int)
io.grpc.stub.AbstractStub.withWaitForReady()
Metodi
build(Canale canale, CallOptions callOptions)
protected PredictionServiceGrpc.PredictionServiceBlockingStub build(Channel channel, CallOptions callOptions)
Parametri |
Nome |
Description |
channel |
io.grpc.Channel
|
callOptions |
io.grpc.CallOptions
|
Sostituzioni
io.grpc.stub.AbstractStub.build(io.grpc.Channel,io.grpc.CallOptions)
countTokens(CountTokensRequest request)
public CountTokensResponse countTokens(CountTokensRequest request)
Esegui un conteggio di token.
directPredict(DirectPredictRequest request)
public DirectPredictResponse directPredict(DirectPredictRequest request)
Esegui una richiesta di previsione online unaaria per i prodotti e i framework proprietari di Vertex.
directRawPredict(DirectRawPredictRequest request)
public DirectRawPredictResponse directRawPredict(DirectRawPredictRequest request)
Eseguire una richiesta di previsione online tramite gRPC.
spiegare(richiesta ExplainRequest)
public ExplainResponse explain(ExplainRequest request)
Eseguire una spiegazione online.
Se viene specificato deployed_model_id, per il modello DeployModel corrispondente deve essere compilato
explanation_spec. Se deployed_model_id non è specificato, per tutti i DeployedModel deve essere compilato
explanation_spec.
predicted(richiesta PredictRequest)
public PredictResponse predict(PredictRequest request)
Eseguire una previsione online.
rawPredict(RawPredictRequest request)
public HttpBody rawPredict(RawPredictRequest request)
Eseguire una previsione online con un payload HTTP arbitrario.
La risposta include le seguenti intestazioni HTTP:
X-Vertex-AI-Endpoint-Id
: ID dell'endpoint che ha fornito questa previsione.
X-Vertex-AI-Deployed-Model-Id
: ID del modello DeployedModel dell'endpoint che ha fornito questa previsione.
Restituisce |
Tipo |
Description |
com.google.api.HttpBody |
|
serverStreamingPredict(StreamingPredictRequest request)
public Iterator<StreamingPredictResponse> serverStreamingPredict(StreamingPredictRequest request)
Esegui una richiesta di previsione online di streaming lato server per i flussi di dati Vertex LLM.
streamGenerateContent(GenerateContentRequest request)
public Iterator<GenerateContentResponse> streamGenerateContent(GenerateContentRequest request)
Genera contenuti con input multimodali con supporto per lo streaming.