Increase max_output_tokens to 4096 to prevent response truncation

app.py

@@ -514,7 +514,7 @@ def generate_response(user_message: str, history: List[Dict], context: Dict) ->
             prompt,
             generation_config=genai.types.GenerationConfig(
                 temperature=0.7,
-                max_output_tokens=2048,
+                max_output_tokens=4096,
             )
         )