v1.6.7

facebookresearch/sam-audiov1.6.7May 19, 2026by chonk-lain

AI Summary

This release introduces MistralOCR integration for extracting text from images and includes a fix for initial CodeChunker language downloads.

Key Highlights

MistralOCR support for text extraction from images
Fixed initial CodeChunker languages download
Added justified method for the overlap option

New Features

MistralOCR integration
Justified method for overlap option

Full Release Notes

# Chonkie v1.6.7 ✨ 
<img width="1360" height="768" alt="image" src="https://github.com/user-attachments/assets/638b6049-51c1-4b96-ae91-7b1061e6b93f" />


## MistralOCR support 
Extract text from images with the new MistralOCR integration:
```python
from chonkie import MistralOCR
ocr = MistralOCR()
out = ocr("image.jpg")
print(out.content)
```

## What's Changed
* chore(deps): bump langsmith from 0.7.31 to 0.8.0 by @dependabot[bot] in https://github.com/chonkie-inc/chonkie/pull/590
* Fix: initial CodeChunker languages downloaded by @chonk-lain in https://github.com/chonkie-inc/chonkie/pull/591
* Add justified method for the overlap option by @anaslimem in https://github.com/chonkie-inc/chonkie/pull/562
* feat: add MistralOCR by @chonk-lain in https://github.com/chonkie-inc/chonkie/pull/593
* chore: bump version by @chonk-lain in https://github.com/chonkie-inc/chonkie/pull/594


**Full Changelog**: https://github.com/chonkie-inc/chonkie/compare/v1.6.6...v1.6.7