docling-project / docling-project/docling
Chunker not returning chunks on pdf's with only header sections.
Open
bug
chunker
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
### Bug
When a pdf is so simple that it seemingly only contains two headers the hybrid chunker is not returning any chunks.
Even so the export_to_markdown function returns a result.
### Steps to reproduce
https://colab.research.google.com/drive/15yDYj501f-W3ro55Nv1UfP_R-P5TrIxU?usp=sharing
### Docling version
Version: 2.52.0
### Python version
3.12.11 (main, Jun 4 2025, 08:56:18) [GCC 11.4.0]
The pdf in question. Also included in the colab.
[broken_pdf.pdf](https://github.com/user-attachments/files/22297499/broken_pdf.pdf)
Contributor guide
Assessment
This issue has not been assessed yet.