v1.6.3

feyninc/chonkiev1.6.3Apr 20, 2026by chonk-lain

AI Summary

v1.6.3 introduces a LanceDB handshake mechanism, adds filename metadata, improves Markdown support, and adds a table-to-JSON converter.

Key Highlights

  • Introduced LanceDB handshake mechanism.
  • Added filename to metadata for better traceability.
  • Added MarkdownDocument support for CodeChunker.
  • Added table-to-JSON converter utility.

New Features

  • LanceDB handshake
  • Metadata filename enhancement
  • MarkdownDocument support
  • Table to JSON converter

Full Release Notes

<p align="center">
<img width="50%" alt="lancedb handshake" src="https://github.com/user-attachments/assets/3deca5d8-af13-4c01-b2c0-dc10afa300d2" />

</p>

# 🚀 Chonkie v1.6.3

> [!CAUTION]
> **Known Bug:** `import chonkie` fails with `ModuleNotFoundError: No module named 'pandas'` when installed without the `[table]` extra. This is caused by an unconditional top-level pandas import in `utils/table_converter.py`. **Please upgrade to v1.6.4** which fixes this issue.

## ✨ Features

- **LanceDB Handshake** : Introduced a new handshake mechanism for LanceDB integration by @chonk-lain in https://github.com/chonkie-inc/chonkie/pull/546
- **Metadata Enhancements** : Added `filename` to metadata for better traceability by @chonk-lain in https://github.com/chonkie-inc/chonkie/pull/554
- **Markdown Support Improvements** : Added `MarkdownDocument` support for `CodeChunker` and fixed no-op behavior in `TableChunker` by @chonknick in https://github.com/chonkie-inc/chonkie/pull/563
- **Table Utilities** : Added a table-to-JSON converter by @anaslimem in https://github.com/chonkie-inc/chonkie/pull/531

## 🧠 Improvements

- **Chunking Consistency** : Deduplicated delimiter-based text splitting across chunkers by @anaslimem in https://github.com/chonkie-inc/chonkie/pull/510
- **Model Loading Robustness** : Improved error handling for neural model and tokenizer loading by @chimchim89 in https://github.com/chonkie-inc/chonkie/pull/472
- **Refactor Handshake IDs** : Moved `_generate_default_id` into `BaseHandshake` by @chimchim89 in https://github.com/chonkie-inc/chonkie/pull/455

## 🐛 Fixes

- **CJK Delimiter Handling** : Fixed handling of single-character delimiters in `RecursiveChunker._split_text` by @nightcityblade in https://github.com/chonkie-inc/chonkie/pull/537

## 📚 Documentation

- **JavaScript Docs** : Added JavaScript documentation by @chonk-lain in https://github.com/chonkie-inc/chonkie/pull/545
- **Semantic Chunker Examples** : Fixed embedding examples by @narumiruna in https://github.com/chonkie-inc/chonkie/pull/544
- **README Cleanup** : Removed outdated full API documentation link by @narumiruna in https://github.com/chonkie-inc/chonkie/pull/543
- **General Docs Updates** : Refactored and improved documentation by @chonk-lain in https://github.com/chonkie-inc/chonkie/pull/542 and https://github.com/chonkie-inc/chonkie/pull/557
- **Contribution Guidelines** : Added PR checklist to `CONTRIBUTING.md` by @swamy18 in https://github.com/chonkie-inc/chonkie/pull/465

## 🔧 Maintenance & Dependencies

- **Test Coverage** : Improved test coverage by @chonk-lain in https://github.com/chonkie-inc/chonkie/pull/555
- **Version Bump** : Bumped library version by @chonk-lain in https://github.com/chonkie-inc/chonkie/pull/564

## 🙌 New Contributors
* @narumiruna made their first contribution in https://github.com/chonkie-inc/chonkie/pull/544 
* @nightcityblade made their first contribution in https://github.com/chonkie-inc/chonkie/pull/537 
* @swamy18 made their first contribution in https://github.com/chonkie-inc/chonkie/pull/465 


**Full Changelog**: https://github.com/chonkie-inc/chonkie/compare/v1.6.2...v1.6.3