hongbo-miao/hongbomiao.com

// https://github.com/pytorch/serve/tree/master/frontend/server/src/main/resources/proto

syntax = "proto3";

package org.pytorch.serve.grpc.inference;
import "google/protobuf/empty.proto";
option go_package="./api/graphql_server/proto/torchserve/v1";

message PredictionsRequest {
    // Name of model.
    string model_name = 1; //required

    // Version of model to run prediction on.
    string model_version = 2; //optional

    // input data for model prediction
    map<string, bytes> input = 3; //required
}

message PredictionResponse {
    // TorchServe health
    bytes prediction = 1;
}

message TorchServeHealthResponse {
    // TorchServe health
    string health = 1;
}

service InferenceAPIsService {
    rpc Ping(google.protobuf.Empty) returns (TorchServeHealthResponse) {}

    // Predictions entry point to get inference using default model version.
    rpc Predictions(PredictionsRequest) returns (PredictionResponse) {}
}