{"adoption": {"forks": 292, "observed_at": "2026-08-28T04:07:55.913681+00:00", "stars": 3308}, "canonical_url": "https://ross.abutalabs.com/products/datatrove", "card": {"archived": false, "artifact_type": "library", "description": "Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.", "domain": ["machine-learning", "large-language-models"], "enriched": true, "function": ["etl", "data-science", "nlp", "llm-training", "streaming"], "health_score": 98, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["huggingface/datatrove"], "name": "huggingface/datatrove", "platform": ["python", "cli"], "pushed_at": "2026-08-13T16:04:51+00:00", "repo": "huggingface/datatrove", "stars": 3308, "tags": ["data-pipelines", "text-processing", "deduplication", "slurm", "web-crawl-processing", "fsspec", "data-engineering", "natural-language-processing", "linux", "docker"], "topics": [], "urls": [], "use_cases": ["filter and deduplicate large text datasets for LLM training", "process common crawl web data at scale", "extract text from warc/arc/wet files", "run data processing pipelines on a slurm cluster", "build custom data processing pipeline blocks", "generate synthetic training data with LLM inference"], "what_it_is": "DataTrove is a Python library from Hugging Face for processing, filtering, and deduplicating large-scale text data through customizable pipeline blocks. Pipelines are platform-agnostic, running locally, on Slurm, or on Ray, making it well suited for preparing LLM training data.", "when_to_avoid": ["you only need small-scale data wrangling that pandas handles fine", "you need a GUI or no-code ETL tool", "your data is not text-based"], "when_to_choose": ["you need to clean, filter, or deduplicate massive text corpora", "you want platform-agnostic pipelines that run locally or on Slurm/Ray", "you are preparing pretraining data for large language models", "you need to read web archive formats like warc, arc, or wet"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/datatrove", "repo": "huggingface/datatrove", "role": "main", "score": 86}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:42:37.640794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6e3f95a7ea0fb5de8b91561d79fc7ab41efc0fbff208e13b4520b21b1eb19162", "fetched_at": "2026-08-28T04:07:55.913681+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datatrove"}, {"content_hash": "2b852b80d34af95326212a56ea77599ecbea246bc1dc1538dde222b2afb379ad", "fetched_at": "2026-08-29T09:35:13.688200+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datatrove/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:42:37.640794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6e3f95a7ea0fb5de8b91561d79fc7ab41efc0fbff208e13b4520b21b1eb19162", "fetched_at": "2026-08-28T04:07:55.913681+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datatrove"}, {"content_hash": "2b852b80d34af95326212a56ea77599ecbea246bc1dc1538dde222b2afb379ad", "fetched_at": "2026-08-29T09:35:13.688200+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datatrove/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:42:37.640794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6e3f95a7ea0fb5de8b91561d79fc7ab41efc0fbff208e13b4520b21b1eb19162", "fetched_at": "2026-08-28T04:07:55.913681+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datatrove"}, {"content_hash": "2b852b80d34af95326212a56ea77599ecbea246bc1dc1538dde222b2afb379ad", "fetched_at": "2026-08-29T09:35:13.688200+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datatrove/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:42:37.640794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6e3f95a7ea0fb5de8b91561d79fc7ab41efc0fbff208e13b4520b21b1eb19162", "fetched_at": "2026-08-28T04:07:55.913681+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datatrove"}, {"content_hash": "2b852b80d34af95326212a56ea77599ecbea246bc1dc1538dde222b2afb379ad", "fetched_at": "2026-08-29T09:35:13.688200+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datatrove/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:42:37.640794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6e3f95a7ea0fb5de8b91561d79fc7ab41efc0fbff208e13b4520b21b1eb19162", "fetched_at": "2026-08-28T04:07:55.913681+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datatrove"}, {"content_hash": "2b852b80d34af95326212a56ea77599ecbea246bc1dc1538dde222b2afb379ad", "fetched_at": "2026-08-29T09:35:13.688200+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datatrove/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:42:37.640794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6e3f95a7ea0fb5de8b91561d79fc7ab41efc0fbff208e13b4520b21b1eb19162", "fetched_at": "2026-08-28T04:07:55.913681+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datatrove"}, {"content_hash": "2b852b80d34af95326212a56ea77599ecbea246bc1dc1538dde222b2afb379ad", "fetched_at": "2026-08-29T09:35:13.688200+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datatrove/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:55.913681+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:42:37.640794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6e3f95a7ea0fb5de8b91561d79fc7ab41efc0fbff208e13b4520b21b1eb19162", "fetched_at": "2026-08-28T04:07:55.913681+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datatrove"}, {"content_hash": "2b852b80d34af95326212a56ea77599ecbea246bc1dc1538dde222b2afb379ad", "fetched_at": "2026-08-29T09:35:13.688200+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datatrove/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:42:37.640794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6e3f95a7ea0fb5de8b91561d79fc7ab41efc0fbff208e13b4520b21b1eb19162", "fetched_at": "2026-08-28T04:07:55.913681+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datatrove"}, {"content_hash": "2b852b80d34af95326212a56ea77599ecbea246bc1dc1538dde222b2afb379ad", "fetched_at": "2026-08-29T09:35:13.688200+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datatrove/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:42:37.640794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6e3f95a7ea0fb5de8b91561d79fc7ab41efc0fbff208e13b4520b21b1eb19162", "fetched_at": "2026-08-28T04:07:55.913681+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datatrove"}, {"content_hash": "2b852b80d34af95326212a56ea77599ecbea246bc1dc1538dde222b2afb379ad", "fetched_at": "2026-08-29T09:35:13.688200+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datatrove/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:42:37.640794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6e3f95a7ea0fb5de8b91561d79fc7ab41efc0fbff208e13b4520b21b1eb19162", "fetched_at": "2026-08-28T04:07:55.913681+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datatrove"}, {"content_hash": "2b852b80d34af95326212a56ea77599ecbea246bc1dc1538dde222b2afb379ad", "fetched_at": "2026-08-29T09:35:13.688200+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datatrove/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 97, "longevity": 84, "rhythm": 73}, "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": 1176, "days_push": 20, "days_rel": 20, "gap_med": 121.5, "n_releases_24m": 7}, "score": 86, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}