docling

v2.111.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 18d RAG & Retrieval

✓ No known CVEs patched

✓ No known CVEs patched in this version

Topics

ai convert document-parser document-parsing documents docx

+9 more

html markdown pdf pdf-converter pdf-to-json pdf-to-text pptx tables xlsx

Affected surfaces

deps rce_ssrf

Summary

AI summary

Added BoxNote backend, msexcel native chart parsing, and JSONL chunk output format.

Full changelog

Guard against None _log in CodeFormulaVlmModel.del during interpreter shutdown (#3534) (52b8bdb)
Sanitize subprocess call in tesseract_ocr_cli_model.py (#3283) (dbaf9ff)
docx: Ignore heading numPr when numFmt is none (#3760) (dc4c0bb)
deps: Require python-docx>=1.2.0 for DOCX comment extraction (#3770) (63cb843)
Make DCLX naturally included page-images (#3765) (88b1a09)
Guard backend imports to prevent ImportError on slim installs (#3751) (2ec33bc)

deepseekocr: Fix parse_deepseekocr_markdown Args docstring (#3766) (d93579a)
Plan for DoclingDocument version compatibility (#3761) (fe72816)

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track docling

Get notified when new releases ship.

About docling

Get your documents ready for gen AI