v1.6.3
π 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.
β¨ Features
- LanceDB Handshake : Introduced a new handshake mechanism for LanceDB integration by @chonk-lain in #546
- Metadata Enhancements : Added
filenameto metadata for better traceability by @chonk-lain in #554 - Markdown Support Improvements : Added
MarkdownDocumentsupport forCodeChunkerand fixed no-op behavior inTableChunkerby @chonknick in #563 - Table Utilities : Added a table-to-JSON converter by @anaslimem in #531
π§ Improvements
- Chunking Consistency : Deduplicated delimiter-based text splitting across chunkers by @anaslimem in #510
- Model Loading Robustness : Improved error handling for neural model and tokenizer loading by @chimchim89 in #472
- Refactor Handshake IDs : Moved
_generate_default_idintoBaseHandshakeby @chimchim89 in #455
π Fixes
- CJK Delimiter Handling : Fixed handling of single-character delimiters in
RecursiveChunker._split_textby @nightcityblade in #537
π Documentation
- JavaScript Docs : Added JavaScript documentation by @chonk-lain in #545
- Semantic Chunker Examples : Fixed embedding examples by @narumiruna in #544
- README Cleanup : Removed outdated full API documentation link by @narumiruna in #543
- General Docs Updates : Refactored and improved documentation by @chonk-lain in #542 and #557
- Contribution Guidelines : Added PR checklist to
CONTRIBUTING.mdby @swamy18 in #465
π§ Maintenance & Dependencies
- Test Coverage : Improved test coverage by @chonk-lain in #555
- Version Bump : Bumped library version by @chonk-lain in #564
π New Contributors
- @narumiruna made their first contribution in #544
- @nightcityblade made their first contribution in #537
- @swamy18 made their first contribution in #465
Full Changelog: v1.6.2...v1.6.3
