[GH-ISSUE #7782] Can someone tell me why a question needs 4 requests to fullfill? #14888

Closed
opened 2026-04-19 21:08:41 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @houcheng on GitHub (Dec 11, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/7782

image

Here I asked two questions and for 2 models.
When asks QWEN model, it takes 4 requests to finished it. When asks SONNET, it uses 5 requests to finish.
I can understand that title, tags, and main question. But why 4-th and 5-th request ?
Can I selective turn some off? Or do we have a "weak" model configuration so that open-webui can asks him as that is very simple.

Thank you~

Originally created by @houcheng on GitHub (Dec 11, 2024). Original GitHub issue: https://github.com/open-webui/open-webui/issues/7782 ![image](https://github.com/user-attachments/assets/7e8b629f-d704-4f75-84f7-4fc6f5a9745c) Here I asked two questions and for 2 models. When asks QWEN model, it takes 4 requests to finished it. When asks SONNET, it uses 5 requests to finish. I can understand that title, tags, and main question. But why 4-th and 5-th request ? Can I selective turn some off? Or do we have a "weak" model configuration so that open-webui can asks him as that is very simple. Thank you~
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#14888