LocalAI/extra/grpc/huggingface/huggingface.py

#!/usr/bin/env python3
import grpc
from concurrent import futures
import time
import backend_pb2
import backend_pb2_grpc
import argparse
import signal
import sys
import os
from sentence_transformers import SentenceTransformer

_ONE_DAY_IN_SECONDS = 60 * 60 * 24

# Implement the BackendServicer class with the service methods
class BackendServicer(backend_pb2_grpc.BackendServicer):
    def Health(self, request, context):
        return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
    def LoadModel(self, request, context):
        model_name = request.Model
        try:
            self.model = SentenceTransformer(model_name)
        except Exception as err:
            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
        # Implement your logic here for the LoadModel service
        # Replace this with your desired response
        return backend_pb2.Result(message="Model loaded successfully", success=True)
    def Embedding(self, request, context):
        # Implement your logic here for the Embedding service
        # Replace this with your desired response
        print("Calculated embeddings for: " + request.Embeddings, file=sys.stderr)
        sentence_embeddings = self.model.encode(request.Embeddings)
        return backend_pb2.EmbeddingResult(embeddings=sentence_embeddings)


def serve(address):
    server = grpc.server(futures.ThreadPoolExecutor(max_workers=1))
    backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
    server.add_insecure_port(address)
    server.start()
    print("Server started. Listening on: " + address, file=sys.stderr)

    # Define the signal handler function
    def signal_handler(sig, frame):
        print("Received termination signal. Shutting down...")
        server.stop(0)
        sys.exit(0)

    # Set the signal handlers for SIGINT and SIGTERM
    signal.signal(signal.SIGINT, signal_handler)
    signal.signal(signal.SIGTERM, signal_handler)

    try:
        while True:
            time.sleep(_ONE_DAY_IN_SECONDS)
    except KeyboardInterrupt:
        server.stop(0)

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Run the gRPC server.")
    parser.add_argument(
        "--addr", default="localhost:50051", help="The address to bind the server to."
    )
    args = parser.parse_args()

    serve(args.addr)