Higher limit

app.py

@@ -201,7 +201,7 @@ async def stream_response_gemini(query, history):
                 system_instruction=system_prompt,
                 temperature=0.3,
                 top_p=0.7,
-                max_output_tokens=512,
+                max_output_tokens=1024,
                 response_mime_type="text/plain",
             )
         )