semchunk has 4.6M monthly downloads and 656 GitHub stars. Version 4.1.1 supports Python 3.10+, first published in 2023.
It is actively maintained under a permissive license, last released in Jun 2026.
It is built on top of dill and tqdm. It is used by 19 tracked packages, including scrapegraphai, lumen and mtxai.
GitHub topics include chunking, nlp and splitting.
Package Insights
- Moderate bus factor: only 5 contributor(s) for this download volume
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100