I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Git Clone
Open WebUI Version
v0.5.20
Ollama Version (if applicable)
No response
Operating System
Windows 10
Browser (if applicable)
Edge
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 included the browser console logs.
I have included the Docker container logs.
I have listed steps to reproduce the bug in detail.
Expected Behavior
Markdown is parsed normally, and information similar to "(\angle BAC)" and "(\triangle ABD)" will not appear. It should be converted to information similar to "∠BAC" and "△ABD".
Actual Behavior
Markdown parsing is slightly abnormal when the model is output in Chinese, but it is parsed normally when it is output in English.
Steps to Reproduce
Use Chinese to talk to the model
The model outputs Chinese, but a small amount of markdown is not parsed properly
Logs & Screenshots
Additional Information
No response
Originally created by @huanyan434 on GitHub (Mar 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/12151
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Git Clone
### Open WebUI Version
v0.5.20
### Ollama Version (if applicable)
_No response_
### Operating System
Windows 10
### Browser (if applicable)
Edge
### 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 included the browser console logs.
- [x] I have included the Docker container logs.
- [x] I have listed steps to reproduce the bug in detail.
### Expected Behavior
Markdown is parsed normally, and information similar to "(\angle BAC)" and "(\triangle ABD)" will not appear. It should be converted to information similar to "∠BAC" and "△ABD".
### Actual Behavior
Markdown parsing is slightly abnormal when the model is output in Chinese, but it is parsed normally when it is output in English.
### Steps to Reproduce
1. Use Chinese to talk to the model
2. The model outputs Chinese, but a small amount of markdown is not parsed properly
### Logs & Screenshots
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-05-05 17:13:45 -05:00
OK, but after testing, the same content can be parsed using English output? Maybe it's a space problem?
<!-- gh-comment-id:2763003781 -->
@huanyan434 commented on GitHub (Mar 29, 2025):
OK, but after testing, the same content can be parsed using English output? Maybe it's a space problem?
could you copy paste a sample text (chinesse plus expresions) to do some test with diferents markdown converters libs?
(same as screenshot img but in text)
<!-- gh-comment-id:2763010840 -->
@rgaricano commented on GitHub (Mar 29, 2025):
could you copy paste a sample text (chinesse plus expresions) to do some test with diferents markdown converters libs?
(same as screenshot img but in text)
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 @huanyan434 on GitHub (Mar 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/12151
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
v0.5.20
Ollama Version (if applicable)
No response
Operating System
Windows 10
Browser (if applicable)
Edge
Confirmation
README.md.Expected Behavior
Markdown is parsed normally, and information similar to "(\angle BAC)" and "(\triangle ABD)" will not appear. It should be converted to information similar to "∠BAC" and "△ABD".
Actual Behavior
Markdown parsing is slightly abnormal when the model is output in Chinese, but it is parsed normally when it is output in English.
Steps to Reproduce
Logs & Screenshots
Additional Information
No response
@tjbck commented on GitHub (Mar 28, 2025):
Is not a valid latex format.
@huanyan434 commented on GitHub (Mar 29, 2025):
OK, but after testing, the same content can be parsed using English output? Maybe it's a space problem?
@huanyan434 commented on GitHub (Mar 29, 2025):
So can LaTex be optimized for Chinese environment?
@rgaricano commented on GitHub (Mar 29, 2025):
could you copy paste a sample text (chinesse plus expresions) to do some test with diferents markdown converters libs?
(same as screenshot img but in text)