inference.proto

syntax = "proto3";

package org.pytorch.serve.grpc.inference;

import "google/protobuf/empty.proto";
import "google/rpc/status.proto";

option java_multiple_files = true;

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

    // SequenceId is required for StreamPredictions2 API.
    optional string sequence_id = 4; //optional
}

message PredictionResponse {
    // Response content for prediction
    bytes prediction = 1;

    // SequenceId is required for StreamPredictions2 API.
    optional string sequence_id = 2; //optional

    // Error information for StreamPredictions2 API.
    optional google.rpc.Status status = 3; //optional
}

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

service InferenceAPIsService {
    // Check health status of the TorchServe server.
    rpc Ping(google.protobuf.Empty) returns (TorchServeHealthResponse) {}

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

    // Streaming response for an inference request.
    rpc StreamPredictions(PredictionsRequest) returns (stream PredictionResponse) {}

    // Bi-direction streaming inference and response.
    rpc StreamPredictions2(stream PredictionsRequest) returns (stream PredictionResponse) {}
}