While stress testing a DocQA pipe I uploaded 9 files in a single chat which caused the following issues:
The streaming was very slow after a certain point. The code used for streaming is just returning the streaming object like this which is handled by OWUI return self._chat_completion_openai(system_prompt, user_prompt).
After some slow token generation it shows the following thing on the browser:
When I refresh this page I see that the model doesn't go in the outlet which is there and event emitter is not closed. (This has happened before independent to this issue as well)
Originally created by @Baghla911 on GitHub (Mar 4, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/11134
While stress testing a DocQA pipe I uploaded 9 files in a single chat which caused the following issues:
1. The streaming was very slow after a certain point. The code used for streaming is just returning the streaming object like this which is handled by OWUI `return self._chat_completion_openai(system_prompt, user_prompt).`
2. After some slow token generation it shows the following thing on the browser:

3. When I refresh this page I see that the model doesn't go in the outlet which is there and event emitter is not closed. (This has happened before independent to this issue as well)

Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @Baghla911 on GitHub (Mar 4, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/11134
While stress testing a DocQA pipe I uploaded 9 files in a single chat which caused the following issues:
return self._chat_completion_openai(system_prompt, user_prompt).