Package profile
semchunk
- Summary: A Python library for splitting text into smaller chunks while preserving as much local semantic context as possible.
- Author: Isaacus <hello@isaacus.com>, Umar Butler <umar@isaacus.com>
- License: MIT License
- Homepage: https://github.com/isaacus-dev/semchunk
- Documentation: https://github.com/isaacus-dev/semchunk/blob/main/README.md
- Source: https://github.com/isaacus-dev/semchunk
- Number of releases: 36
- First release: 0.1.0 on 2023-11-05
- Latest release: 4.1.1 on 2026-06-13
- Latest release size: 18.3 KB (pure Python wheel)
Dependencies
Semchunk has 2 dependencies, 0 of which optional.Dependent packages
| Package | Optional | Group |
|---|---|---|
| docling-core | true | chunking |
Similar packages
- langchain-text-splittersLangChain text splitting utilities
- mistletoeA fast, extensible Markdown parser in pure Python.
- textfsmPython module for parsing semi-structured text into python tables.
- lkmlA speedy LookML parser implemented in pure Python.
- readability-lxmlfast html to text parser (article readability tool) with python 3 support
- filesplitPython module that is capable of splitting files and merging it back.
- python-multipartA streaming multipart parser for Python