v1.6.8
Gentleman-Programming/engramv1.6.8Jun 1, 2026by chonk-lain
Upgrading?
Release notes summary
Chonkie v1.6.8 adds support for Gemini embedding dimensions in the Catsu wrappers and introduces PyEmscripten wheels for broader platform compatibility. It also fixes JSON export so non-ASCII text is written as-is rather than using \uXXXX escapes, plus routine dependency updates.
Key Highlights
- Gemini embedding dimensions now supported in Catsu wrappers
- Added PyEmscripten wheels for expanded distribution targets
- JSON export now writes non-ASCII text as-is instead of escaped sequences
- Dependency updates including idna and uv
- First-time contributor @zzhdbw credited for the JSON export fix
New Features
- Gemini embedding dimension support in Catsu wrappers
- PyEmscripten wheel builds
- Improved non-ASCII handling in JSON export
Full Release Notes
<p align="center"> <img width="50%" alt="lancedb handshake" src="https://github.com/user-attachments/assets/7c6ef4c1-2c4c-4cfa-8def-332767159343" /> </p> ## What's Changed * Support Gemini embedding dimensions in Catsu wrappers by @hannibal-lee in https://github.com/chonkie-inc/chonkie/pull/571 * chore(deps): bump idna from 3.11 to 3.15 by @dependabot[bot] in https://github.com/chonkie-inc/chonkie/pull/595 * feat: add PyEmscripten wheels by @chonk-lain in https://github.com/chonkie-inc/chonkie/pull/597 * fix: write non-ASCII text as-is in JSON export instead of \uXXXX escapes by @zzhdbw in https://github.com/chonkie-inc/chonkie/pull/596 * chore(deps): bump uv from 0.11.6 to 0.11.15 by @dependabot[bot] in https://github.com/chonkie-inc/chonkie/pull/598 * chore: bump library by @chonk-lain in https://github.com/chonkie-inc/chonkie/pull/599 ## New Contributors * @zzhdbw made their first contribution in https://github.com/chonkie-inc/chonkie/pull/596 **Full Changelog**: https://github.com/chonkie-inc/chonkie/compare/v1.6.7...v1.6.8
Related Repositories
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
The world’s fastest framework for building websites.
:cherry_blossom: A command-line fuzzy finder