Update app.py

max_tokens=4096

app.py

@@ -27,7 +27,7 @@ def respond_to_question_llama(transcript, question):
 
     response = client.chat_completion(
         messages=[{"role": "user", "content": f"Transcript: {transcript}\n\nUser: {question}"}],
-        max_tokens=150,
+        max_tokens=4096,
     ).choices[0].message.content
 
     return response