chonkie

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

🦛 CHONK your texts with Chonkie ✨ Type-friendly, light-weight, fast and super-simple chunking library

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

From data to vector database effortlessly

agent-skills for chonkie's ecosystem

An opinionated, local-first, asynchronous document ingestion pipeline for RAG workflows.

Step-by-step guide to building a local RAG system from scratch. Learn hybrid search, reranking, HyDE, and evaluation... 100% free, no cloud required.

chonkie-example

ChunkLab is an open-source Streamlit app for learning, comparing, and benchmarking Retrieval-Augmented Generation (RAG) engineering techniques — chunking, embeddings, retrieval, reranking, and evaluation — side by side, with real metrics instead of vibes.

Chat with document

Tutorials on using LlamaIndex for modern RAG applications