Update app.py

app.py

@@ -41,6 +41,7 @@ def retrieve_context_faiss(query, top_k=3):
     return "\n".join([menu_chunks[i] for i in indices[0]])
 
 # === Generate LLM Response ===
+@GPU
 def generate_response(message, history, system_message, max_tokens, temperature, top_p):
     context = retrieve_context_faiss(message)
     messages = [{"role": "system", "content": system_message}]