messkan/rag-chunk

A Python CLI to test, benchmark, and find the best RAG chunking strategy for your Markdown documents.

39
/ 100
Emerging

Implements six chunking strategies including header-aware and embedding-based semantic splitting, with token-accurate chunking via tiktoken for specific LLM models (GPT-3.5, GPT-4, etc.). Evaluates chunk quality through precision, recall, and F1-score metrics, and supports embedding-based semantic retrieval using sentence-transformers as an alternative to lexical matching. Exports results to JSON/CSV and integrates optional LangChain components for recursive character splitting.

104 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 13 / 25
Community 7 / 25

How are scores calculated?

Stars

104

Forks

5

Language

Python

License

MIT

Last pushed

Jan 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/messkan/rag-chunk"

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