v0.1.6

roboflow/supervisionv0.1.6May 26, 2026by afourney

AI Summary

The Microsoft markitdown library adds OCR capabilities and improves PDF handling performance. New converters for Azure Content Understanding are also introduced to enhance document processing.

Key Highlights

New OCR layer service for embedded images and PDF scans
Fix for O(n) memory growth in PDF conversion
Azure Content Understanding converter added
Fix for deeply nested HTML RecursionError

New Features

Azure Content Understanding integration
PDF memory optimization
Improved HTML parsing stability

Full Release Notes

## What's Changed
* [MS] Add OCR layer service for embedded images and PDF scans by @lesyk in https://github.com/microsoft/markitdown/pull/1541
* Fix O(n) memory growth in PDF conversion by calling page.close() afte… by @lesyk in https://github.com/microsoft/markitdown/pull/1612
* Updated warning about binding to non-local interfaces. by @afourney in https://github.com/microsoft/markitdown/pull/1653
* fix: handle deeply nested HTML that triggers RecursionError by @jigangz in https://github.com/microsoft/markitdown/pull/1644
* Clarify security posture in READMEs by @afourney in https://github.com/microsoft/markitdown/pull/1807
* feat: Add Azure Content Understanding converter by @chienyuanchang in https://github.com/microsoft/markitdown/pull/1865
* Bump version to 0.1.6 by @afourney in https://github.com/microsoft/markitdown/pull/1914

## New Contributors
* @jigangz made their first contribution in https://github.com/microsoft/markitdown/pull/1644
* @chienyuanchang made their first contribution in https://github.com/microsoft/markitdown/pull/1865

**Full Changelog**: https://github.com/microsoft/markitdown/compare/v0.1.5...v0.1.6