github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-06 19:08:59 -05:00
Code Issues 1.3k Packages Projects Releases 126 Wiki Activity

[GH-ISSUE #11284] issue: Cannot correctly handle the think tag of qwq model #16171

New Issue
Closed
opened 2026-04-19 22:10:59 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-19 22:10:59 -05:00
Owner
Copy Link

Originally created by @qhjqhj on GitHub (Mar 6, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/11284

Check Existing Issues

  • I have searched the existing issues and discussions.

Installation Method

Git Clone

Open WebUI Version

0.5.20

Ollama Version (if applicable)

0.5.13

Operating System

windows 11

Browser (if applicable)

No response

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have checked the browser console logs.
  • I have checked the Docker container logs.
  • I have listed steps to reproduce the bug in detail.

Expected Behavior

Separate thinking from formal output

Actual Behavior

The content of thinking and the content of formal output cannot be distinguished, and the formal content cannot be output

Steps to Reproduce

  1. run ollama serve
  2. run open-webui serve
  3. Open the browser and select the qwq model
  4. Ask a code-related question, such as "Write the code for the Viterbi algorithm using Python"
    When running the qwq:latest model of Ollama on the backend, the content in the tag is output as normal content, and part of the code output seems to be lost

Logs & Screenshots

Image
Image

Additional Information

No response

Originally created by @qhjqhj on GitHub (Mar 6, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/11284 ### Check Existing Issues - [x] I have searched the existing issues and discussions. ### Installation Method Git Clone ### Open WebUI Version 0.5.20 ### Ollama Version (if applicable) 0.5.13 ### Operating System windows 11 ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have checked the browser console logs. - [x] I have checked the Docker container logs. - [x] I have listed steps to reproduce the bug in detail. ### Expected Behavior Separate thinking from formal output ### Actual Behavior The content of thinking and the content of formal output cannot be distinguished, and the formal content cannot be output ### Steps to Reproduce 1. run ollama serve 2. run open-webui serve 3. Open the browser and select the qwq model 4. Ask a code-related question, such as "Write the code for the Viterbi algorithm using Python" When running the qwq:latest model of Ollama on the backend, the content in the <think> tag is output as normal content, and part of the code output seems to be lost ### Logs & Screenshots ![Image](https://github.com/user-attachments/assets/1a074a36-554e-4737-8d0f-f2dcbddfff82) ![Image](https://github.com/user-attachments/assets/81fe239d-ad85-4ba4-931c-4d4cdc8d2ee6) ### Additional Information _No response_
GiteaMirror added the bug label 2026-04-19 22:10:59 -05:00
GiteaMirror commented 2026-04-19 22:11:01 -05:00
Author
Owner
Copy Link

@Eidenz commented on GitHub (Mar 6, 2025):

Adding to this, it doesn't even seem to have its normal output in the thinking tag.

On my end, everything in the thinking tag seems to indeed be the thought process, but once it's done it outputs no answer, and openwebui acts as if the model was still thinking.

<!-- gh-comment-id:2703421332 --> @Eidenz commented on GitHub (Mar 6, 2025): Adding to this, it doesn't even seem to have its normal output in the thinking tag. On my end, everything in the thinking tag seems to indeed be the thought process, but once it's done it outputs no answer, and openwebui acts as if the model was still thinking.
GiteaMirror commented 2026-04-19 22:11:02 -05:00
Author
Owner
Copy Link

@mihkhub commented on GitHub (Mar 6, 2025):

QwQ-32b thinking tag pair "

<!-- gh-comment-id:2703769661 --> @mihkhub commented on GitHub (Mar 6, 2025): QwQ-32b thinking tag pair "<think> </think>
GiteaMirror commented 2026-04-19 22:11:02 -05:00
Author
Owner
Copy Link

@EntropyYue commented on GitHub (Mar 6, 2025):

It seems that the model's thinking output has been stopped before it has finished, please try increasing nun_ctx and num_predict

<!-- gh-comment-id:2703983192 --> @EntropyYue commented on GitHub (Mar 6, 2025): It seems that the model's thinking output has been stopped before it has finished, please try increasing `nun_ctx` and `num_predict`
GiteaMirror commented 2026-04-19 22:11:03 -05:00
Author
Owner
Copy Link

@Duxon commented on GitHub (Mar 6, 2025):

How to increase num_ctx (to 131072) in the Open-WebUI settings? I can't find that seeting.

<!-- gh-comment-id:2704088783 --> @Duxon commented on GitHub (Mar 6, 2025): How to increase `num_ctx` (to 131072) in the Open-WebUI settings? I can't find that seeting.
GiteaMirror commented 2026-04-19 22:11:04 -05:00
Author
Owner
Copy Link

@EntropyYue commented on GitHub (Mar 6, 2025):

If you are using en-US, it will display as Context Length

<!-- gh-comment-id:2704099849 --> @EntropyYue commented on GitHub (Mar 6, 2025): If you are using en-US, it will display as `Context Length`
GiteaMirror commented 2026-04-19 22:11:04 -05:00
Author
Owner
Copy Link

@qhjqhj commented on GitHub (Mar 6, 2025):

It seems that the model's thinking output has been stopped before it has finished, please try increasing nun_ctx and num_predict

I tried it several times, and the total number of tokens generated was different. It seems that the issue is not caused by the maximum length limit.

<!-- gh-comment-id:2704202626 --> @qhjqhj commented on GitHub (Mar 6, 2025): > It seems that the model's thinking output has been stopped before it has finished, please try increasing `nun_ctx` and `num_predict` I tried it several times, and the total number of tokens generated was different. It seems that the issue is not caused by the maximum length limit.
GiteaMirror commented 2026-04-19 22:11:05 -05:00
Author
Owner
Copy Link

@bjj commented on GitHub (Mar 6, 2025):

See #11259

<!-- gh-comment-id:2704469701 --> @bjj commented on GitHub (Mar 6, 2025): See #11259
GiteaMirror commented 2026-04-19 22:11:06 -05:00
Author
Owner
Copy Link

@EntropyYue commented on GitHub (Mar 6, 2025):

Please provide screenshots of other situations, which will help us better solve the problem

<!-- gh-comment-id:2704599809 --> @EntropyYue commented on GitHub (Mar 6, 2025): Please provide screenshots of other situations, which will help us better solve the problem
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#16171
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?