Home Projects chunky
chunky

chunky

by GiovanniPasq · GitHub

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.

# chonkie# chunk-validation# chunking# chunking-algorithm
View on GitHub
⭐ Stars
149
🍴 Forks
13
📜 License
MIT
Commercial use OK
📅 Created
2026
🔄 Last commit
13 days ago
🏷️ Category
chonkie
💻 Language
You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
chunky — GitHub preview card
📈 Star history
150149
2026-07-202026-07-21
📄 About

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.

Frequently asked questions

What is chunky?

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.

Is chunky open source?

chunky is an open-source project. It is released under the MIT license.

Is chunky free?

Yes. chunky is free and open source — you can use, modify and self-host it.

🏅 Maintainer of this project?
OpenSourceAI badge — chunky

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![OpenSourceAI](https://opensourceai.tech/badge.php?tool=giovannipasq-chunky)](https://opensourceai.tech/project/giovannipasq-chunky.html)
More badge options →
🧬 Related projects🧬 View the DNA map →