{"adoption": {"forks": 351, "observed_at": "2026-08-28T04:08:57.249027+00:00", "stars": 4704}, "canonical_url": "https://ross.abutalabs.com/products/chonkie", "card": {"archived": false, "artifact_type": "library", "description": "🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines", "domain": ["large-language-models", "artificial-intelligence"], "enriched": true, "function": ["rag", "nlp", "etl", "machine-learning"], "health_score": 100, "homepage": "https://docs.chonkie.ai", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["feyninc/chonkie"], "name": "feyninc/chonkie", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-26T18:50:39+00:00", "repo": "feyninc/chonkie", "stars": 4704, "tags": ["chunking", "text-splitter", "ingestion", "vector-databases", "embeddings", "semantic-chunking", "retrieval-augmented-generation", "natural-language-processing"], "topics": ["rag", "chonkie", "chunker", "chunking-algorithm", "retrieval-systems", "semantic-chunker", "similarity-search", "text-splitter", "ai", "llms", "splitting-algorithms"], "urls": [], "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"], "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.", "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"], "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"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/chonkie", "repo": "feyninc/chonkie", "role": "main", "score": 84}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:19:11.788550+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a324fb472761a65f76a0b5f45e709d034732066bdd0d493755066986a4512af", "fetched_at": "2026-08-28T04:08:57.249027+00:00", "kind": "readme", "missing": false, "url": "https://github.com/feyninc/chonkie"}, {"content_hash": "be39a70be869bc599e28268f7dd2190a5e43565fe1da217e24288ed1cdc1491e", "fetched_at": "2026-08-29T09:03:09.017908+00:00", "kind": "homepage", "missing": false, "url": "https://docs.chonkie.ai"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:19:11.788550+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a324fb472761a65f76a0b5f45e709d034732066bdd0d493755066986a4512af", "fetched_at": "2026-08-28T04:08:57.249027+00:00", "kind": "readme", "missing": false, "url": "https://github.com/feyninc/chonkie"}, {"content_hash": "be39a70be869bc599e28268f7dd2190a5e43565fe1da217e24288ed1cdc1491e", "fetched_at": "2026-08-29T09:03:09.017908+00:00", "kind": "homepage", "missing": false, "url": "https://docs.chonkie.ai"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:19:11.788550+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a324fb472761a65f76a0b5f45e709d034732066bdd0d493755066986a4512af", "fetched_at": "2026-08-28T04:08:57.249027+00:00", "kind": "readme", "missing": false, "url": "https://github.com/feyninc/chonkie"}, {"content_hash": "be39a70be869bc599e28268f7dd2190a5e43565fe1da217e24288ed1cdc1491e", "fetched_at": "2026-08-29T09:03:09.017908+00:00", "kind": "homepage", "missing": false, "url": "https://docs.chonkie.ai"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:19:11.788550+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a324fb472761a65f76a0b5f45e709d034732066bdd0d493755066986a4512af", "fetched_at": "2026-08-28T04:08:57.249027+00:00", "kind": "readme", "missing": false, "url": "https://github.com/feyninc/chonkie"}, {"content_hash": "be39a70be869bc599e28268f7dd2190a5e43565fe1da217e24288ed1cdc1491e", "fetched_at": "2026-08-29T09:03:09.017908+00:00", "kind": "homepage", "missing": false, "url": "https://docs.chonkie.ai"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:19:11.788550+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a324fb472761a65f76a0b5f45e709d034732066bdd0d493755066986a4512af", "fetched_at": "2026-08-28T04:08:57.249027+00:00", "kind": "readme", "missing": false, "url": "https://github.com/feyninc/chonkie"}, {"content_hash": "be39a70be869bc599e28268f7dd2190a5e43565fe1da217e24288ed1cdc1491e", "fetched_at": "2026-08-29T09:03:09.017908+00:00", "kind": "homepage", "missing": false, "url": "https://docs.chonkie.ai"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:19:11.788550+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a324fb472761a65f76a0b5f45e709d034732066bdd0d493755066986a4512af", "fetched_at": "2026-08-28T04:08:57.249027+00:00", "kind": "readme", "missing": false, "url": "https://github.com/feyninc/chonkie"}, {"content_hash": "be39a70be869bc599e28268f7dd2190a5e43565fe1da217e24288ed1cdc1491e", "fetched_at": "2026-08-29T09:03:09.017908+00:00", "kind": "homepage", "missing": false, "url": "https://docs.chonkie.ai"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.249027+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:19:11.788550+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a324fb472761a65f76a0b5f45e709d034732066bdd0d493755066986a4512af", "fetched_at": "2026-08-28T04:08:57.249027+00:00", "kind": "readme", "missing": false, "url": "https://github.com/feyninc/chonkie"}, {"content_hash": "be39a70be869bc599e28268f7dd2190a5e43565fe1da217e24288ed1cdc1491e", "fetched_at": "2026-08-29T09:03:09.017908+00:00", "kind": "homepage", "missing": false, "url": "https://docs.chonkie.ai"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:19:11.788550+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a324fb472761a65f76a0b5f45e709d034732066bdd0d493755066986a4512af", "fetched_at": "2026-08-28T04:08:57.249027+00:00", "kind": "readme", "missing": false, "url": "https://github.com/feyninc/chonkie"}, {"content_hash": "be39a70be869bc599e28268f7dd2190a5e43565fe1da217e24288ed1cdc1491e", "fetched_at": "2026-08-29T09:03:09.017908+00:00", "kind": "homepage", "missing": false, "url": "https://docs.chonkie.ai"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:19:11.788550+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a324fb472761a65f76a0b5f45e709d034732066bdd0d493755066986a4512af", "fetched_at": "2026-08-28T04:08:57.249027+00:00", "kind": "readme", "missing": false, "url": "https://github.com/feyninc/chonkie"}, {"content_hash": "be39a70be869bc599e28268f7dd2190a5e43565fe1da217e24288ed1cdc1491e", "fetched_at": "2026-08-29T09:03:09.017908+00:00", "kind": "homepage", "missing": false, "url": "https://docs.chonkie.ai"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:19:11.788550+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a324fb472761a65f76a0b5f45e709d034732066bdd0d493755066986a4512af", "fetched_at": "2026-08-28T04:08:57.249027+00:00", "kind": "readme", "missing": false, "url": "https://github.com/feyninc/chonkie"}, {"content_hash": "be39a70be869bc599e28268f7dd2190a5e43565fe1da217e24288ed1cdc1491e", "fetched_at": "2026-08-29T09:03:09.017908+00:00", "kind": "homepage", "missing": false, "url": "https://docs.chonkie.ai"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 37, "rhythm": 92}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 522, "days_push": 7, "days_rel": 57, "gap_med": 11.0, "n_releases_24m": 37}, "score": 84, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}