feat: add backend

main.py

@@ -77,11 +77,11 @@ handlerToken = MyCustomSyncHandler()
 
 LLM = load_model(device_type=DEVICE_TYPE, model_id=MODEL_ID, model_basename=MODEL_BASENAME, stream=True, callbacks=[handlerToken])
 
-template = """you are a helpful, respectful and honest assistant. You should only use the source documents provided to answer the questions.
+template = """You are a helpful, respectful and honest assistant. You should only use the documents provided in the context to answer the questions.
 You should only respond only topics that contains in documents use to training. Use the following pieces of context to answer the question at the end.
 Always answer in the most helpful and safe way possible.
-If you don't know the answer to a question, just say that you don't know, don't try to make up an answer, don't share false information.
-Use 15 sentences maximum. Keep the answer as concise as possible. Always say "thanks for asking!" at the end of the answer.
+If you don't know the answer to a question, just say that you "I don't know", never try to make up an answer and don't share false information.
+Use 15 sentences maximum. The answer must be as concise as possible. Always say "thanks for asking!" at the end of the answer.
 Context: {context}
 Question: {question}
 """
@@ -259,6 +259,8 @@ async def websocket_endpoint(websocket: WebSocket):
         while finish == False:
             finish = handlerToken.end
             token = handlerToken.token
+            print(token)
+            print(finish)
             await websocket.send_text(f"result: {token}")