I have searched the existing issues and discussions.
Problem Description
Currently, Open WebUI does not support dots.ocr, which is a tool for extracting text from images efficiently.
Desired Solution you'd like
there will be an option to use dots.ocr as an ocr instead the tika or docling options
Alternatives Considered
Docling and Tika are not as effective as Dots.OCR, particularly for languages other than English.
Additional Context
No response
Originally created by @liorzilka on GitHub (Sep 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17846
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
### Problem Description
Currently, Open WebUI does not support dots.ocr, which is a tool for extracting text from images efficiently.
### Desired Solution you'd like
there will be an option to use [dots.ocr](https://github.com/rednote-hilab/dots.ocr) as an ocr instead the tika or docling options
### Alternatives Considered
Docling and Tika are not as [effective](https://github.com/rednote-hilab/dots.ocr?tab=readme-ov-file#performance-comparison-dotsocr-vs-competing-models) as Dots.OCR, particularly for languages other than English.
### Additional Context
_No response_
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 @liorzilka on GitHub (Sep 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17846
Check Existing Issues
Problem Description
Currently, Open WebUI does not support dots.ocr, which is a tool for extracting text from images efficiently.
Desired Solution you'd like
there will be an option to use dots.ocr as an ocr instead the tika or docling options
Alternatives Considered
Docling and Tika are not as effective as Dots.OCR, particularly for languages other than English.
Additional Context
No response
@tjbck commented on GitHub (Sep 28, 2025):
PR welcome.