diff --git a/model_server/app/function_calling/model_utils.py b/model_server/app/function_calling/model_utils.py index c790e0ae..4c55816c 100644 --- a/model_server/app/function_calling/model_utils.py +++ b/model_server/app/function_calling/model_utils.py @@ -79,7 +79,7 @@ async def chat_completion(req: ChatMessage, res: Response): resp = const.arch_function_client.chat.completions.create( messages=messages, model=client_model_name, - stream=False, + stream=True, extra_body=const.arch_function_generation_params, ) except Exception as e: