v1.0.9
feyninc/chonkiev1.0.9Jun 4, 2025by chonknick
AI Summary
Performance optimizations via Cython and the addition of support for PostgreSQL vector databases.
Key Highlights
- Added Cython functions for `split` and `merge` operations for performance boosts.
- Added `PsycopgHandshake` for initial support of `pgvector`.
- Added `experimental.CodeChunker` for improved code chunking.
New Features
- Cython optimization for basic ops.
- PostgreSQL (pgvector) support.
- Experimental code chunker.
- Gemini embeddings support.
Full Release Notes
## What's Changed * Fix pickling issue in BaseTokenizer by @chonknick in https://github.com/chonkie-inc/chonkie/pull/153 * Improve test coverage for OverlapRefinery by @chonknick in https://github.com/chonkie-inc/chonkie/pull/154 * Feat: Enhance the tests for `OverlapRefinery`, `Tokenizers` and `SlumberChunker` by @chonknick in https://github.com/chonkie-inc/chonkie/pull/155 * Feat: Enhance the tests for `SPDMChunker`, `SemanticChunker`, `NeuralChunker` and `Visualizer` by @chonknick in https://github.com/chonkie-inc/chonkie/pull/156 * Feat: Add cloud `CodeChunker` + tests by @chonknick in https://github.com/chonkie-inc/chonkie/pull/157 * Fix: `CodeChunker` fails multiprocessing due to pickling issues; Run it sequentially by @chonknick in https://github.com/chonkie-inc/chonkie/pull/158 * Add GeminiEmbeddings Support by @chonknick in https://github.com/chonkie-inc/chonkie/pull/159 * Fix: OverlapRefinery with `mode="recursive"` fails with level gets too low by @chonknick in https://github.com/chonkie-inc/chonkie/pull/161 * Fix: `OverlapRefinery` is caching too much; revert `context_size` calculation caching by @chonknick in https://github.com/chonkie-inc/chonkie/pull/162 * Feat: Create Cython functions for `split` and `merge` basic ops for chunking! by @chonknick in https://github.com/chonkie-inc/chonkie/pull/163 * Feat: Add CPython optimized methods for `split` and `merge` ops for performance boosts! by @chonknick in https://github.com/chonkie-inc/chonkie/pull/164 * Migrate Docs from `chonkie-docs` repo to `chonkie` for easier management + maintainance by @chonknick in https://github.com/chonkie-inc/chonkie/pull/149 * Migrate DOCS.md by @chonknick in https://github.com/chonkie-inc/chonkie/pull/165 * Update DOCS by @chonknick in https://github.com/chonkie-inc/chonkie/pull/166 * Update DOCS.md + Add example for `JSONPorter` by @chonknick in https://github.com/chonkie-inc/chonkie/pull/167 * Feat: Add support for `PsycopgHandshake` by @chonknick in https://github.com/chonkie-inc/chonkie/pull/171 * Feat: Add `PsycopgHandshake` for initial support of `pgvector` by @chonknick in https://github.com/chonkie-inc/chonkie/pull/172 * Update semantic.py to fix check if any of the split token counts are greater than the max chunk size by @geosmart in https://github.com/chonkie-inc/chonkie/pull/175 * Fix: Refactor `PyscopgHandshake` to `PgvectorHandshake` via `vecs` by @chonknick in https://github.com/chonkie-inc/chonkie/pull/174 * Update DOCS.md + Fix `SemanticChunker` bug for `all` comparison by @chonknick in https://github.com/chonkie-inc/chonkie/pull/176 * Update version to 1.0.9 in pyproject.toml for the next release. by @chonknick in https://github.com/chonkie-inc/chonkie/pull/177 * Feat: Add initial support for `experimental.CodeChunker` — improved code chunking for few languages by @chonknick in https://github.com/chonkie-inc/chonkie/pull/178 * Fix: `cython` module build failing during CD — Add `cython` build info to `pyproject.toml` by @chonknick in https://github.com/chonkie-inc/chonkie/pull/180 * Fix: Use `cibuildwheel` to build and publish wheels to PyPI by @chonknick in https://github.com/chonkie-inc/chonkie/pull/182 * Fix: Update the CD script to use `uv` instead in the hopes of finally publishing the `v1.0.9` by @chonknick in https://github.com/chonkie-inc/chonkie/pull/183 ## New Contributors * @geosmart made their first contribution in https://github.com/chonkie-inc/chonkie/pull/175 **Full Changelog**: https://github.com/chonkie-inc/chonkie/compare/v1.0.8...v1.0.9