jparkerweb/semantic-chunking

🍱 semantic-chunking ⇢ semantically create chunks from large document for passing to LLM workflows

59
/ 100
Established

When preparing long documents for AI models, it's crucial to break them into smaller, meaningful pieces. This tool takes your raw text documents and automatically splits them into semantically coherent chunks, making the input more digestible and effective for large language models. This is ideal for anyone working with AI applications that process extensive text, like researchers analyzing scientific papers or content strategists summarizing articles.

134 stars. Used by 1 other package. Available on npm.

Use this if you need to intelligently divide large text documents into smaller, related sections for better performance in AI models.

Not ideal if your primary goal is simple, fixed-length text splitting without considering the meaning or context of sentences.

AI-content-preparation document-preprocessing text-analysis large-language-models knowledge-management
Maintenance 10 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 13 / 25

How are scores calculated?

Stars

134

Forks

14

Language

JavaScript

License

MIT

Last pushed

Feb 03, 2026

Commits (30d)

0

Dependencies

5

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/jparkerweb/semantic-chunking"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.