GiovanniPasq/chunky

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

Transform and optimize your markdown documentation for Large Language Models (LLMs) and RAG systems. Generate llms.txt automatically.

Vision infrastructure to turn complex documents into LLM-ready data

🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

Full Rust port of Python docling

Docling core data types and transformations

Improved file parsing for LLM’s