[Feature Request]: Native support of Epub filetype

[justemu]

Is there an existing issue for the same feature request?

• [x] I have checked the existing issues.

Is your feature request related to a problem?

It's not a problem. But a large part of our local KB is epub files. We can unpack the epub files to folders of htmls. However, it would be better to have a native support of epub files directly.

Describe the feature you'd like

Native support of Epub filetype.

Describe implementation you've considered

The epub files are simply a bunch of packed htmls with clear structures. It would be easy to bridge the gap between epub and current processes of RAGFlow.

Documentation, adoption, use case

RAGFlow would have direct access to current storage of epubs, which is a high quality of information

Additional information

No response

[cogitech2]

Any movement on this request?

(Forgive me if this doesn’t comply with the etiquette. I claim ignorance. )

[B1tMaster]

would be great to have support for epub.. Many books come in epub format. How can this be prioritized ?

[which-W]

@B1tMaster @justemu @cogitech2 Thanks so much for your suggestion — and apologies for the late reply! 🕐

Support for EPUB is definitely a great idea 📚 and we're evaluating it for future development. In the meantime, you can upload the book as a PDF file — our built-in BOOK chunking strategy should make parsing and working with long-form content much easier! ✨

We really appreciate your thoughtful feedback — feel free to open more issues or suggestions anytime! 🚀

Thanks again! 🙏