add main.py & end point

app.py

@@ -77,6 +77,3 @@ def chat(req: ChatRequest):
     reply = output["choices"][0]["text"].split("<|im_end|>")[0].strip()
     req.history.append([req.message, reply])
     return ChatResponse(response=reply, updated_history=req.history)
-
-if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=7860)