Update app.py

app.py

@@ -533,7 +533,7 @@ Your response should be detailed, informative, accurate, and directly relevant t
             response = groq_client.chat.completions.create(
                 messages=messages,
                 model="llama-3.1-8b-instant",
-                max_tokens=8192,
+                max_tokens=4192,
                 temperature=temperature,
                 top_p=0.9,
                 frequency_penalty=1.2,