Update app.py

app.py

@@ -467,6 +467,7 @@ async def chat_endpoint(request: Request, _: None = Depends(verify_origin)):
                 temperature=temperature,  # Use same temperature for consistency
                 messages=messages,
                 max_tokens=2000
+                stream=True  # <<< KEY CHANGE: Enable streaming
             )
             final_chatbot_response = final_response.choices[0].message.content
         else: