{"adoption": {"forks": 407, "observed_at": "2026-08-28T04:09:51.621862+00:00", "stars": 6938}, "canonical_url": "https://ross.abutalabs.com/products/data-juicer", "card": {"archived": false, "artifact_type": "library", "description": "Data processing for and with foundation models!  🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷", "domain": ["large-language-models", "data-science", "artificial-intelligence"], "enriched": true, "function": ["etl", "data-science", "data-visualization", "machine-learning", "llm-training", "rag", "nlp"], "health_score": 100, "homepage": "https://datajuicer.github.io/data-juicer/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["datajuicer/data-juicer"], "name": "datajuicer/data-juicer", "platform": ["python", "cloud", "cross-platform"], "pushed_at": "2026-08-26T11:26:06+00:00", "repo": "datajuicer/data-juicer", "stars": 6938, "tags": ["data-processing", "foundation-models", "synthetic-data", "data-cleaning", "deduplication", "multimodal", "data-pipeline", "pre-training-data", "data-engineering", "docker"], "topics": ["data-analysis", "data-science", "large-language-models", "llm", "data-visualization", "llms", "instruction-tuning", "pre-training", "multi-modal", "synthetic-data", "data", "data-pipeline", "data-processing", "foundation-models"], "urls": [], "use_cases": ["clean and deduplicate web-scale pre-training corpora for LLMs", "filter and curate instruction-tuning datasets", "prepare domain-specific RAG index data", "synthesize training data for foundation models", "process multimodal datasets for AI training", "analyze and visualize dataset quality before training", "curate agent interaction traces for training"], "what_it_is": "Data-Juicer is a Python library and data processing system for cleaning, deduplicating, synthesizing, and analyzing data for foundation model training. It provides 200+ composable operators that scale from a laptop to thousand-node clusters.", "when_to_avoid": ["you need a simple one-off ETL job unrelated to AI/ML data", "you require a fully managed GUI data platform rather than a code-first library", "your data volumes are small and a few pandas scripts would suffice"], "when_to_choose": ["you need to clean, filter, or deduplicate large datasets for LLM pre-training or fine-tuning", "you want composable data processing operators with recipes for foundation model data", "you need data processing that scales from laptop to large clusters", "you are preparing multimodal or synthetic training data"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/data-juicer", "repo": "datajuicer/data-juicer", "role": "main", "score": 94}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:41:14.375656+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f27276109fe6faabaf846ed99e892e5ac1a22e539785cd85ee39c597abf99880", "fetched_at": "2026-08-28T04:09:51.621862+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datajuicer/data-juicer"}, {"content_hash": "fc6c7e5d5afd6199cb4f914857e37465352624e8c500317ecb507761952f4349", "fetched_at": "2026-08-29T08:37:07.465960+00:00", "kind": "homepage", "missing": false, "url": "https://datajuicer.github.io/data-juicer/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:41:14.375656+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f27276109fe6faabaf846ed99e892e5ac1a22e539785cd85ee39c597abf99880", "fetched_at": "2026-08-28T04:09:51.621862+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datajuicer/data-juicer"}, {"content_hash": "fc6c7e5d5afd6199cb4f914857e37465352624e8c500317ecb507761952f4349", "fetched_at": "2026-08-29T08:37:07.465960+00:00", "kind": "homepage", "missing": false, "url": "https://datajuicer.github.io/data-juicer/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:41:14.375656+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f27276109fe6faabaf846ed99e892e5ac1a22e539785cd85ee39c597abf99880", "fetched_at": "2026-08-28T04:09:51.621862+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datajuicer/data-juicer"}, {"content_hash": "fc6c7e5d5afd6199cb4f914857e37465352624e8c500317ecb507761952f4349", "fetched_at": "2026-08-29T08:37:07.465960+00:00", "kind": "homepage", "missing": false, "url": "https://datajuicer.github.io/data-juicer/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:41:14.375656+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f27276109fe6faabaf846ed99e892e5ac1a22e539785cd85ee39c597abf99880", "fetched_at": "2026-08-28T04:09:51.621862+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datajuicer/data-juicer"}, {"content_hash": "fc6c7e5d5afd6199cb4f914857e37465352624e8c500317ecb507761952f4349", "fetched_at": "2026-08-29T08:37:07.465960+00:00", "kind": "homepage", "missing": false, "url": "https://datajuicer.github.io/data-juicer/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:41:14.375656+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f27276109fe6faabaf846ed99e892e5ac1a22e539785cd85ee39c597abf99880", "fetched_at": "2026-08-28T04:09:51.621862+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datajuicer/data-juicer"}, {"content_hash": "fc6c7e5d5afd6199cb4f914857e37465352624e8c500317ecb507761952f4349", "fetched_at": "2026-08-29T08:37:07.465960+00:00", "kind": "homepage", "missing": false, "url": "https://datajuicer.github.io/data-juicer/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:41:14.375656+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f27276109fe6faabaf846ed99e892e5ac1a22e539785cd85ee39c597abf99880", "fetched_at": "2026-08-28T04:09:51.621862+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datajuicer/data-juicer"}, {"content_hash": "fc6c7e5d5afd6199cb4f914857e37465352624e8c500317ecb507761952f4349", "fetched_at": "2026-08-29T08:37:07.465960+00:00", "kind": "homepage", "missing": false, "url": "https://datajuicer.github.io/data-juicer/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.621862+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:41:14.375656+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f27276109fe6faabaf846ed99e892e5ac1a22e539785cd85ee39c597abf99880", "fetched_at": "2026-08-28T04:09:51.621862+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datajuicer/data-juicer"}, {"content_hash": "fc6c7e5d5afd6199cb4f914857e37465352624e8c500317ecb507761952f4349", "fetched_at": "2026-08-29T08:37:07.465960+00:00", "kind": "homepage", "missing": false, "url": "https://datajuicer.github.io/data-juicer/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:41:14.375656+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f27276109fe6faabaf846ed99e892e5ac1a22e539785cd85ee39c597abf99880", "fetched_at": "2026-08-28T04:09:51.621862+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datajuicer/data-juicer"}, {"content_hash": "fc6c7e5d5afd6199cb4f914857e37465352624e8c500317ecb507761952f4349", "fetched_at": "2026-08-29T08:37:07.465960+00:00", "kind": "homepage", "missing": false, "url": "https://datajuicer.github.io/data-juicer/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:41:14.375656+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f27276109fe6faabaf846ed99e892e5ac1a22e539785cd85ee39c597abf99880", "fetched_at": "2026-08-28T04:09:51.621862+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datajuicer/data-juicer"}, {"content_hash": "fc6c7e5d5afd6199cb4f914857e37465352624e8c500317ecb507761952f4349", "fetched_at": "2026-08-29T08:37:07.465960+00:00", "kind": "homepage", "missing": false, "url": "https://datajuicer.github.io/data-juicer/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:41:14.375656+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f27276109fe6faabaf846ed99e892e5ac1a22e539785cd85ee39c597abf99880", "fetched_at": "2026-08-28T04:09:51.621862+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datajuicer/data-juicer"}, {"content_hash": "fc6c7e5d5afd6199cb4f914857e37465352624e8c500317ecb507761952f4349", "fetched_at": "2026-08-29T08:37:07.465960+00:00", "kind": "homepage", "missing": false, "url": "https://datajuicer.github.io/data-juicer/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 80, "rhythm": 96}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1128, "days_push": 7, "days_rel": 26, "gap_med": 19.5, "n_releases_24m": 25}, "score": 94, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}