Update app.py

app.py

@@ -36,7 +36,7 @@ def predict(question_choice, audio):
         model='gpt-3.5-turbo',
         messages=conversation,
         temperature=0.6,
-        max_tokens=600,  # Limiting the response to 500 tokens
+        max_tokens=100,  # Limiting the response to 500 tokens
         stream=True
     )