docling

v2.103.0 Breaking

This release includes 1 breaking change for platform teams planning a safe upgrade.

Published 1mo 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

Summary

AI summary

Removed the legacy DoclingDocument API, requiring migration.

Full changelog

cli: Add docling service capability to CLI (#3622) (5897004)
Remove the legacy DoclingDocument (#3592) (147ac25)
service: Async service client facade (#3450) (947ab69)
html: Add description list support and optimize list handling (#3615) (a178bbb)

html: Collapse source newlines to spaces per HTML spec (#3630) (dfdac6b)
html: Ensure proper ListGroup parent for description list items (#3628) (42b1c01)
service: Allow DoclingServiceClient.convert to accept local filepaths as str (#3626) (0d3b641)
html: Correct list numbering and nested list processing (#3625) (6914bf4)
Retry transient remote VLM API failures (#3515) (419fc4c)
layout: Drop PICTURE cluster coinciding with a TABLE (#3523) (156d854)
ocr: Honor requested languages in RapidOCR model selection (#3586) (d9ceb41)
cli: Pass accelerator options to VLM pipeline (#3599) (846f81a)

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