# feyninc/chonkie

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

Repository: https://github.com/feyninc/chonkie
Canonical: https://ross.abutalabs.com/products/chonkie
Homepage: https://docs.chonkie.ai
Language: Python
License: MIT
License Family: permissive
Topics: rag, chonkie, chunker, chunking-algorithm, retrieval-systems, semantic-chunker, similarity-search, text-splitter, ai, llms, splitting-algorithms
Last push: 2026-08-26T18:50:39+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 92, longevity 37
- inputs: {"age_days": 522, "days_push": 7, "days_rel": 57, "gap_med": 11.0, "n_releases_24m": 37}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4704, forks 351 (observed 2026-08-28T04:08:57.249027+00:00)

## What it is
Chonkie is a lightweight Python library for chunking text in RAG pipelines, offering multiple chunking algorithms, embeddings, and integrations with vector databases. It handles the ingestion step of retrieval-augmented generation: fetch, chunk, refine, embed, and store text.

## Use cases
- split documents into chunks for a RAG pipeline
- chunk text semantically before embedding
- prepare documents for a vector database
- replace a custom text splitter with a maintained library
- build a fast lightweight document ingestion pipeline
- chunk multilingual text for retrieval

## When to choose
- you need efficient, fast text chunking for RAG without heavy dependencies
- you want built-in integrations with tokenizers, embedders, and vector DBs
- you need multilingual chunking support out of the box

## When to avoid
- you need a full RAG framework with retrieval and generation, not just ingestion
- your project is not Python-based and you cannot use the JS SDK or API

## Facets
- artifact type: library
- maturity: active
- function: rag, nlp, etl, machine-learning
- domain: large-language-models, artificial-intelligence
- platform: python, cross-platform
- tags: chunking, text-splitter, ingestion, vector-databases, embeddings, semantic-chunking, retrieval-augmented-generation, natural-language-processing

## Member repositories
- feyninc/chonkie (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:57.249027+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:19:11.788550+00:00, confidence not recorded.
  - readme: https://github.com/feyninc/chonkie (fetched 2026-08-28T04:08:57.249027+00:00, sha 6a324fb47276)
  - homepage: https://docs.chonkie.ai (fetched 2026-08-29T09:03:09.017908+00:00, sha be39a70be869)
- Data as of 2026-08-30T08:39:29.467469+00:00.