docling-project / docling-project/docling
Elimination of Document Header and Footers
Open
enhancement
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
### Requested Feature
I am working on a document extraction problem, and it seems that Docling keeps treating some headers and footers as sections due to their format. Is there any possibility of providing a set of known headers or footers to automatically exclude them from the extracted text?
### Alternatives
I am currently removing them manually, but it seems that Docling should at least be able to detect potential headers and footers, as most official documents follow a specific structure. In my case, I am identifying headers and footers in a separate process using an external library.
Contributor guide
Assessment
This issue has not been assessed yet.