docling-project / docling-project/docling
Poor PDF Processing Results on the Official Python Documentation
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
### Bug
Docling version 2.48.0 fails to properly extract content from official Python documentation PDFs, regardless of OCR settings.
### Steps to reproduce
pipeline_options = PdfPipelineOptions(
do_ocr=True,
)
converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
}
)
Then I used
result = converter.convert(str(pdf_file))
markdown = result.document.export_to_markdown()
### Docling version
2.48.0
### Python version
3.13
### Document source
Official Python 3.13 documentation PDFs from https://docs.python.org/3/download.html
I have attached an excel with comparison with the results.
[Docling python doc comparison.xlsx](https://github.com/user-attachments/files/22044414/Docling.python.doc.comparison.xlsx)
Contributor guide
Assessment
This issue has not been assessed yet.