infiniflow
[Feature Request]: Divide the text into chunks based on the chapter directory in the Word document and retain the pictures in the text.
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?
No response
Describe the feature you'd like
A large number of Word documents in an enterprise have a chapter directory structure, but ragflow does not seem to use this information. Can we directly divide the document into blocks based on the chapter directory and retain the tree structure for retrieval?
Describe implementation you've considered
No response
Documentation, adoption, use case
No response
Additional information
No response
@chenhanbiao 👋 Thanks for your suggestion, and sorry for the delayed response!
It may be helpful to take another look at our current chunking methods, especially the Manual mode — this approach could be a good fit for your use case 📚🧩
If you're still running into issues, feel free to share more details so we can assist further! Appreciate your continued interest in the project — and we'd love to hear more ideas or feedback you might have 💡
Stay tuned for updates! 🚀
