Starstruk Logo MarkStarstruk

v2.126.0

Kedreamix/Linly-Talkerv2.126.0Sep 4, 2026by docling-ops[bot]

Upgrading?

What changed from v2.2.0 → v2.126.0?What's new in v31.4.4 after v2.126.0?

AI Summary

This release introduces a native PDF pipeline and enhances document processing capabilities for JATS and Apple Pages formats, alongside several parsing fixes.

Key Highlights

  • Addition of a native PDF pipeline for document processing
  • Preservation of external hyperlinks in JATS format
  • Completion of parsing for Apple Pages documents
  • Fix for preserving ordered list start numbers in Markdown conversion
  • Fix for preserving hard line breaks in Markdown

New Features

  • Native PDF pipeline
  • JATS hyperlink preservation
  • Apple Pages parsing completion
  • Markdown ordered list preservation
  • Markdown hard line break preservation

Full Release Notes

### Feature

* Add native pdf pipeline ([#3979](https://github.com/docling-project/docling/issues/3979)) ([`1c96dd3`](https://github.com/docling-project/docling/commit/1c96dd37ce9af206752f276f73030e5bf4d2fb69))
* **jats:** Preserve external hyperlinks ([#4029](https://github.com/docling-project/docling/issues/4029)) ([`cf38d90`](https://github.com/docling-project/docling/commit/cf38d9049cc5633c1736a1c2042dacd029e91c55))
* **iwork:** Complete the parsing of Apple Pages documents ([#4062](https://github.com/docling-project/docling/issues/4062)) ([`554b10a`](https://github.com/docling-project/docling/commit/554b10ac1c6a4252d9a193f4c02e3826df378e6a))

### Fix

* **markdown:** Preserve ordered list start numbers in conversion ([#4138](https://github.com/docling-project/docling/issues/4138)) ([`a4e9462`](https://github.com/docling-project/docling/commit/a4e94624ef2630641ed2a9e8f91b683f56898f41))
* **docx:** Inherit heading numId through the style basedOn chain (#3916) ([#3917](https://github.com/docling-project/docling/issues/3917)) ([`b2d333e`](https://github.com/docling-project/docling/commit/b2d333e12260fc9cb74d8e8748b0d45505afcabb))
* **ocr:** Apply the deprecated force_full_page_ocr flag on assignment (#4082) ([#4085](https://github.com/docling-project/docling/issues/4085)) ([`cb39dc1`](https://github.com/docling-project/docling/commit/cb39dc1f396a624df15812feafea93dd10634f09))
* **markdown:** Preserve hard line breaks ([#4019](https://github.com/docling-project/docling/issues/4019)) ([`1c2b794`](https://github.com/docling-project/docling/commit/1c2b794b00f45c16c33479f2b0e04cfceed19d94))
* **asciidoc:** Gate image loading ([#4156](https://github.com/docling-project/docling/issues/4156)) ([`63d1808`](https://github.com/docling-project/docling/commit/63d1808c7593b0add340394f485e12d7f0feda05))

Related Repositories

public-apis/public-apis★ 491,128

A collective list of free APIs

NousResearch/hermes-agent★ 255,901

The agent that grows with you

yt-dlp/yt-dlp★ 200,002

A feature-rich command-line audio/video downloader

microsoft/markitdown★ 191,481

Python tool for converting files and office documents to Markdown.

Significant-Gravitas/AutoGPT★ 187,700

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.