docling-project / docling-project/docling

Section Header does not include any children after parsing PDF file

Open
#2,774 3 comments 0 reactions 0 assignees View on GitHub
question triage/close-fixed
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

### Question
I am trying to use the Docling Package to extract the content of a pdf file.
In the documentation for docling document, it says that section headers will include their sections text in their children attribute.
However, if my text includes a section header and following text belonging to that section, the output from docling sets the parent of both elements to "#/body". The section headers children are empty.
Is this feature not available for PDF parsing? Or is there a setting in the Pipeline options that I am missing?

This is the basic PDF file I am using for the parsing. I am using the standard configuration for the PDF pipeline.
[header_test.pdf](https://github.com/user-attachments/files/24098685/header_test.pdf)

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.