setted the n_threads

main.py

@@ -33,7 +33,7 @@ async def send_response(query: SQLContext):
             prompt=query_text,
             max_tokens=512,
         )
-        response_text = output["choices"][0]["text"].split('###')[0].strip('"')
+        response_text = output["choices"][0]["text"].split('###')[0].strip().strip('"')
         return {"response": response_text}
     except Exception as e:
         logging.error(f"Error generating response: {e}")