Add support outlines

Signed-off-by: GitHub <[email protected]>

extra/grpc/backend_outlines/Makefile

@@ -0,0 +1,11 @@
+.PONY: outlines
+outlines:
+	@echo "Creating virtual environment..."
+	@conda env create --name outlines --file outlines.yml
+	@echo "Virtual environment created."
+
+.PONY: run
+run:
+	@echo "Running outlines..."
+	bash run.sh
+	@echo "outlines run."

extra/grpc/backend_outlines/README.md

@@ -0,0 +1,5 @@
+# Creating a separate environment for the outlines project
+
+```
+make outlines
+```

extra/grpc/backend_outlines/backend_outlines.py

@@ -0,0 +1,82 @@
+"""
+This is the extra gRPC server for outlines of LocalAI
+"""
+from concurrent import futures
+import argparse
+import os
+import signal
+import sys
+import time
+
+import backend_pb2
+import backend_pb2_grpc
+
+import grpc
+
+import outlines.text.generate as generate
+import outlines.models as models
+
+_ONE_DAY_IN_SECONDS = 60 * 60 * 24
+
+# If MAX_WORKERS are specified in the environment use it, otherwise default to 1
+MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
+
+# Implement the BackendServicer class with the service methods
+class BackendServicer(backend_pb2_grpc.BackendServicer):
+    """
+    BackendServicer is the class that implements the gRPC service
+    """
+    def Health(self, request, context):
+        return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
+
+    def LoadModel(self, request, context):
+        try:
+            # TODO: Need to make sure request.Model is a model name or path
+            if request.Model == "":
+                return backend_pb2.Result(success=False, message="Model name is empty")
+            # TODO: It is download model from huggingface.co, this should be optimized. The internal of this funciton is used transformers
+            # Maybe we can only load the model from local
+            self.model = models.transformers(request.Model)
+        except Exception as err:
+            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
+        return backend_pb2.Result(message="Model loaded successfully", success=True)
+
+    def Predict(self, request, context):
+        try:
+            #TODO: stop=["."] is a hard code, we need to make it configurable
+            output=generate.continuation(self.model, stop=["."])(self.prompt)
+        except Exception as err:
+            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
+        return backend_pb2.Result(message=bytes(output, encoding='utf-8'))
+
+def serve(address):
+    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
+    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)