Package inference

Interface GRPCInferenceServiceGrpc.AsyncService

All Known Implementing Classes:

GRPCInferenceServiceGrpc.GRPCInferenceServiceImplBase

Enclosing class:

GRPCInferenceServiceGrpc

public static interface GRPCInferenceServiceGrpc.AsyncService

 Inference Server GRPC endpoints.
 

Method Summary

Modifier and Type	Method	Description
default void	modelInfer(GrpcPredictV2.ModelInferRequest request, io.grpc.stub.StreamObserver<GrpcPredictV2.ModelInferResponse> responseObserver)	The ModelInfer API performs inference using the specified model.
default void	modelMetadata(GrpcPredictV2.ModelMetadataRequest request, io.grpc.stub.StreamObserver<GrpcPredictV2.ModelMetadataResponse> responseObserver)	The per-model metadata API provides information about a model.
default void	modelReady(GrpcPredictV2.ModelReadyRequest request, io.grpc.stub.StreamObserver<GrpcPredictV2.ModelReadyResponse> responseObserver)	The ModelReady API indicates if a specific model is ready for inferencing.
default void	serverLive(GrpcPredictV2.ServerLiveRequest request, io.grpc.stub.StreamObserver<GrpcPredictV2.ServerLiveResponse> responseObserver)	The ServerLive API indicates if the inference server is able to receive and respond to metadata and inference requests.
default void	serverMetadata(GrpcPredictV2.ServerMetadataRequest request, io.grpc.stub.StreamObserver<GrpcPredictV2.ServerMetadataResponse> responseObserver)	The ServerMetadata API provides information about the server.
default void	serverReady(GrpcPredictV2.ServerReadyRequest request, io.grpc.stub.StreamObserver<GrpcPredictV2.ServerReadyResponse> responseObserver)	The ServerReady API indicates if the server is ready for inferencing.

Method Details

serverLive

default void serverLive(GrpcPredictV2.ServerLiveRequest request,
 io.grpc.stub.StreamObserver<GrpcPredictV2.ServerLiveResponse> responseObserver)

 The ServerLive API indicates if the inference server is able to receive 
 and respond to metadata and inference requests.
 

serverReady

default void serverReady(GrpcPredictV2.ServerReadyRequest request,
 io.grpc.stub.StreamObserver<GrpcPredictV2.ServerReadyResponse> responseObserver)

 The ServerReady API indicates if the server is ready for inferencing.
 

modelReady

default void modelReady(GrpcPredictV2.ModelReadyRequest request,
 io.grpc.stub.StreamObserver<GrpcPredictV2.ModelReadyResponse> responseObserver)

 The ModelReady API indicates if a specific model is ready for inferencing.
 

serverMetadata

default void serverMetadata(GrpcPredictV2.ServerMetadataRequest request,
 io.grpc.stub.StreamObserver<GrpcPredictV2.ServerMetadataResponse> responseObserver)

 The ServerMetadata API provides information about the server. Errors are 
 indicated by the google.rpc.Status returned for the request. The OK code 
 indicates success and other codes indicate failure.
 

modelMetadata

default void modelMetadata(GrpcPredictV2.ModelMetadataRequest request,
 io.grpc.stub.StreamObserver<GrpcPredictV2.ModelMetadataResponse> responseObserver)

 The per-model metadata API provides information about a model. Errors are 
 indicated by the google.rpc.Status returned for the request. The OK code 
 indicates success and other codes indicate failure.
 

modelInfer

default void modelInfer(GrpcPredictV2.ModelInferRequest request,
 io.grpc.stub.StreamObserver<GrpcPredictV2.ModelInferResponse> responseObserver)

 The ModelInfer API performs inference using the specified model. Errors are
 indicated by the google.rpc.Status returned for the request. The OK code 
 indicates success and other codes indicate failure.