[Feature Request]: Enabling layout recognition in chunk method "manual"
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
When the "general" method is selected as a chunk method in the Knowledge Base, the switch for layout recognition is available. However, the switch for layout recognition is not available at the chunk method "manual". That would be very helpful nonetheless. It's also very useful if this information could be passed along when uploading a file via API.
Describe implementation you've considered
No response
Documentation, adoption, use case
No response
Additional information
No response
@Nausoj Thanks a lot for your suggestion, and apologies for the late reply!
We've updated the relevant manual handling code to support selecting the chunking method, and the upload process now also returns the method used if the document is successfully processed 🧩📄
This should cover the need you mentioned — feel free to let us know if you run into any issues. If everything looks good, please help us close this feature when you get a chance. Otherwise, we're happy to keep the conversation going!
Appreciate your support and contributions — we're always open to more constructive ideas 💡🚀