package org.pytorch.serve.grpc.inference

Get desktop application:
View/edit binary Protocol Buffers messages

• rpc Ping (google.protobuf.Empty, TorchServeHealthResponse)

  torchserve_inference.proto:34

  Check health status of the TorchServe server.

  message TorchServeHealthResponse

  torchserve_inference.proto:27

  • string health = 1

    TorchServe health

• rpc Predictions (PredictionsRequest, PredictionResponse)

  torchserve_inference.proto:37

  Predictions entry point to get inference using default model version.

  message PredictionsRequest

  torchserve_inference.proto:11

  • string model_name = 1

    Name of model.

    required

  • string model_version = 2

    Version of model to run prediction on.

    optional

  • map<string, bytes> input = 3

    Input data for model prediction

    required

  message PredictionResponse

  torchserve_inference.proto:22

  • bytes prediction = 1

    Response content for prediction