change max tokens

app.py

@@ -15,7 +15,8 @@ async def generate_response(user_input):
     response = client.chat.completions.create(
         model= 'nvidia/Llama-3.1-Nemotron-70B-Instruct-HF',
         messages=messages, 
-        max_tokens= 500,
+        max_tokens=16384,
+        max_completion_tokens=16384
     )
 
     return response.choices[0].message.content