Update app.py

app.py

@@ -3,11 +3,9 @@ from pydantic import BaseModel
 from llama_cpp import Llama
 from concurrent.futures import ThreadPoolExecutor, as_completed
 import uvicorn
-import huggingface_hub
 import re
 from dotenv import load_dotenv
 import spaces
-from spaces import *
 
 load_dotenv()
 
@@ -115,10 +113,10 @@ def remove_repetitive_responses(responses):
 
 @spaces.GPU(duration=0)
 def generate_chat_response(request, model_data):
+    model = model_data['model']
     try:
         user_input = normalize_input(request.message)
-        llm = model_data['model']
-        response = llm(user_input, top_k=request.top_k, top_p=request.top_p, temperature=request.temperature)
+        response = model(user_input, top_k=request.top_k, top_p=request.top_p, temperature=request.temperature)
         return {"model": model_data['name'], "response": response}
     except Exception:
         pass
@@ -149,5 +147,12 @@ async def generate(request: ChatRequest):
     except Exception:
         pass
 
+@app.api_route("/{method_name}", methods=["GET", "POST", "PUT", "DELETE", "PATCH"])
+async def handle_request(method_name: str):
+    try:
+        return {"message": "Request handled successfully"}
+    except Exception:
+        raise HTTPException(status_code=500, detail="Error: Internal Server Error")
+
 if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=7860)