docling-project / docling-project/docling

Poor PDF Processing Results on the Official Python Documentation

Open
#2,164 2 comments 0 reactions 0 assignees View on GitHub
bug triage/close-stale
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.