{"adoption": {"forks": 3371, "observed_at": "2026-08-28T04:11:32.174613+00:00", "stars": 21870}, "canonical_url": "https://ross.abutalabs.com/products/datasets", "card": {"archived": false, "artifact_type": "library", "description": "🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools", "domain": ["machine-learning", "data-science", "computer-vision", "artificial-intelligence", "large-language-models"], "enriched": true, "function": ["etl", "data-science", "machine-learning", "deep-learning", "nlp", "computer-vision", "audio-processing", "sdk"], "health_score": 100, "homepage": "https://huggingface.co/docs/datasets", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["huggingface/datasets"], "name": "huggingface/datasets", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-26T12:48:03+00:00", "repo": "huggingface/datasets", "stars": 21870, "tags": ["huggingface", "datasets", "apache-arrow", "dataloader", "data-preprocessing", "pytorch", "tensorflow", "pandas", "streaming", "data-engineering", "natural-language-processing", "audio"], "topics": ["nlp", "datasets", "pytorch", "tensorflow", "pandas", "numpy", "natural-language-processing", "computer-vision", "machine-learning", "deep-learning", "speech", "ai", "artificial-intelligence", "llm", "dataset-hub", "huggingface"], "urls": [], "use_cases": ["load a public dataset for model training in one line of code", "preprocess and tokenize a text dataset for fine-tuning an LLM", "stream a huge dataset that doesn't fit on disk or memory", "convert local CSV, JSON, or Parquet files into an ML-ready dataset", "prepare image or audio datasets with transforms and resampling", "share a dataset with the community on the Hugging Face Hub"], "what_it_is": "Hugging Face Datasets is a Python library providing one-line access to hundreds of thousands of public datasets on the Hugging Face Hub across text, image, audio, and video modalities. It offers efficient, memory-mapped data loading and preprocessing built on Apache Arrow, with integrations for PyTorch, TensorFlow, JAX, Pandas, NumPy, and Polars.", "when_to_avoid": ["you need a general-purpose ETL tool for non-ML data pipelines", "your data lives in a SQL database and you only need simple queries", "you need distributed data processing beyond single-machine Arrow-based workflows"], "when_to_choose": ["you need fast, reproducible access to public ML datasets", "you work with large datasets and want memory-mapped, zero-copy loading", "you train models in PyTorch, TensorFlow, or JAX and need dataloader integration", "you want a unified API for text, image, and audio data preprocessing"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/datasets", "repo": "huggingface/datasets", "role": "main", "score": 98}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:57:46.403280+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3c6ff3c493d874dab50debe73fdef66867a2e57ed2f7d43da2012396e933f8ef", "fetched_at": "2026-08-28T04:11:32.174613+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datasets"}, {"content_hash": "619622f88451b947f041fd432ad0feaba602c93726c44cd4cf4b524741d0da8c", "fetched_at": "2026-08-29T07:56:13.857218+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/datasets"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T07:56:13.859846+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cd748fc8a545347486f911cce31292bef53a793b6274825a33814f7a5bbcde6e", "fetched_at": "2026-08-29T07:56:13.863982+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/quickstart"}, {"content_hash": "c711168832634aef9fc16289c5c4c08e6c1754fd231fbea9f192d965cd03e924", "fetched_at": "2026-08-29T07:56:13.866023+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/installation"}, {"content_hash": "84fe8fae3e6c8876dbe615f2d601c97e5d7d3c33a5f2d4e49b3c59eade67361d", "fetched_at": "2026-08-29T07:56:13.867804+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/tutorial"}, {"content_hash": "b2e149befada518daf73d73b77b748309cd75bac187fc901cfcd09fdc5c3aa20", "fetched_at": "2026-08-29T07:56:13.869572+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/load_hub"}, {"content_hash": "a4ded9ba5009f390fff0655050a40299c656ecf69948c1dc9db88c66dedb38e6", "fetched_at": "2026-08-29T07:56:13.871523+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/access"}, {"content_hash": "b052d61cc4583f0be6ab2e74f495280fae1eaf6ef1f08bcad4fdb8006d18b3da", "fetched_at": "2026-08-29T07:56:13.873376+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/use_dataset"}, {"content_hash": "9049903d19028d43f36303ef72a296180a611158e462f2bcfdb27f83f5a18633", "fetched_at": "2026-08-29T07:56:13.875116+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datasets/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:57:46.403280+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3c6ff3c493d874dab50debe73fdef66867a2e57ed2f7d43da2012396e933f8ef", "fetched_at": "2026-08-28T04:11:32.174613+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datasets"}, {"content_hash": "619622f88451b947f041fd432ad0feaba602c93726c44cd4cf4b524741d0da8c", "fetched_at": "2026-08-29T07:56:13.857218+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/datasets"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T07:56:13.859846+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cd748fc8a545347486f911cce31292bef53a793b6274825a33814f7a5bbcde6e", "fetched_at": "2026-08-29T07:56:13.863982+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/quickstart"}, {"content_hash": "c711168832634aef9fc16289c5c4c08e6c1754fd231fbea9f192d965cd03e924", "fetched_at": "2026-08-29T07:56:13.866023+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/installation"}, {"content_hash": "84fe8fae3e6c8876dbe615f2d601c97e5d7d3c33a5f2d4e49b3c59eade67361d", "fetched_at": "2026-08-29T07:56:13.867804+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/tutorial"}, {"content_hash": "b2e149befada518daf73d73b77b748309cd75bac187fc901cfcd09fdc5c3aa20", "fetched_at": "2026-08-29T07:56:13.869572+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/load_hub"}, {"content_hash": "a4ded9ba5009f390fff0655050a40299c656ecf69948c1dc9db88c66dedb38e6", "fetched_at": "2026-08-29T07:56:13.871523+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/access"}, {"content_hash": "b052d61cc4583f0be6ab2e74f495280fae1eaf6ef1f08bcad4fdb8006d18b3da", "fetched_at": "2026-08-29T07:56:13.873376+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/use_dataset"}, {"content_hash": "9049903d19028d43f36303ef72a296180a611158e462f2bcfdb27f83f5a18633", "fetched_at": "2026-08-29T07:56:13.875116+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datasets/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:57:46.403280+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3c6ff3c493d874dab50debe73fdef66867a2e57ed2f7d43da2012396e933f8ef", "fetched_at": "2026-08-28T04:11:32.174613+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datasets"}, {"content_hash": "619622f88451b947f041fd432ad0feaba602c93726c44cd4cf4b524741d0da8c", "fetched_at": "2026-08-29T07:56:13.857218+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/datasets"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T07:56:13.859846+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cd748fc8a545347486f911cce31292bef53a793b6274825a33814f7a5bbcde6e", "fetched_at": "2026-08-29T07:56:13.863982+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/quickstart"}, {"content_hash": "c711168832634aef9fc16289c5c4c08e6c1754fd231fbea9f192d965cd03e924", "fetched_at": "2026-08-29T07:56:13.866023+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/installation"}, {"content_hash": "84fe8fae3e6c8876dbe615f2d601c97e5d7d3c33a5f2d4e49b3c59eade67361d", "fetched_at": "2026-08-29T07:56:13.867804+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/tutorial"}, {"content_hash": "b2e149befada518daf73d73b77b748309cd75bac187fc901cfcd09fdc5c3aa20", "fetched_at": "2026-08-29T07:56:13.869572+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/load_hub"}, {"content_hash": "a4ded9ba5009f390fff0655050a40299c656ecf69948c1dc9db88c66dedb38e6", "fetched_at": "2026-08-29T07:56:13.871523+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/access"}, {"content_hash": "b052d61cc4583f0be6ab2e74f495280fae1eaf6ef1f08bcad4fdb8006d18b3da", "fetched_at": "2026-08-29T07:56:13.873376+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/use_dataset"}, {"content_hash": "9049903d19028d43f36303ef72a296180a611158e462f2bcfdb27f83f5a18633", "fetched_at": "2026-08-29T07:56:13.875116+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datasets/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:57:46.403280+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3c6ff3c493d874dab50debe73fdef66867a2e57ed2f7d43da2012396e933f8ef", "fetched_at": "2026-08-28T04:11:32.174613+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datasets"}, {"content_hash": "619622f88451b947f041fd432ad0feaba602c93726c44cd4cf4b524741d0da8c", "fetched_at": "2026-08-29T07:56:13.857218+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/datasets"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T07:56:13.859846+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cd748fc8a545347486f911cce31292bef53a793b6274825a33814f7a5bbcde6e", "fetched_at": "2026-08-29T07:56:13.863982+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/quickstart"}, {"content_hash": "c711168832634aef9fc16289c5c4c08e6c1754fd231fbea9f192d965cd03e924", "fetched_at": "2026-08-29T07:56:13.866023+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/installation"}, {"content_hash": "84fe8fae3e6c8876dbe615f2d601c97e5d7d3c33a5f2d4e49b3c59eade67361d", "fetched_at": "2026-08-29T07:56:13.867804+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/tutorial"}, {"content_hash": "b2e149befada518daf73d73b77b748309cd75bac187fc901cfcd09fdc5c3aa20", "fetched_at": "2026-08-29T07:56:13.869572+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/load_hub"}, {"content_hash": "a4ded9ba5009f390fff0655050a40299c656ecf69948c1dc9db88c66dedb38e6", "fetched_at": "2026-08-29T07:56:13.871523+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/access"}, {"content_hash": "b052d61cc4583f0be6ab2e74f495280fae1eaf6ef1f08bcad4fdb8006d18b3da", "fetched_at": "2026-08-29T07:56:13.873376+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/use_dataset"}, {"content_hash": "9049903d19028d43f36303ef72a296180a611158e462f2bcfdb27f83f5a18633", "fetched_at": "2026-08-29T07:56:13.875116+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datasets/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:57:46.403280+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3c6ff3c493d874dab50debe73fdef66867a2e57ed2f7d43da2012396e933f8ef", "fetched_at": "2026-08-28T04:11:32.174613+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datasets"}, {"content_hash": "619622f88451b947f041fd432ad0feaba602c93726c44cd4cf4b524741d0da8c", "fetched_at": "2026-08-29T07:56:13.857218+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/datasets"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T07:56:13.859846+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cd748fc8a545347486f911cce31292bef53a793b6274825a33814f7a5bbcde6e", "fetched_at": "2026-08-29T07:56:13.863982+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/quickstart"}, {"content_hash": "c711168832634aef9fc16289c5c4c08e6c1754fd231fbea9f192d965cd03e924", "fetched_at": "2026-08-29T07:56:13.866023+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/installation"}, {"content_hash": "84fe8fae3e6c8876dbe615f2d601c97e5d7d3c33a5f2d4e49b3c59eade67361d", "fetched_at": "2026-08-29T07:56:13.867804+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/tutorial"}, {"content_hash": "b2e149befada518daf73d73b77b748309cd75bac187fc901cfcd09fdc5c3aa20", "fetched_at": "2026-08-29T07:56:13.869572+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/load_hub"}, {"content_hash": "a4ded9ba5009f390fff0655050a40299c656ecf69948c1dc9db88c66dedb38e6", "fetched_at": "2026-08-29T07:56:13.871523+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/access"}, {"content_hash": "b052d61cc4583f0be6ab2e74f495280fae1eaf6ef1f08bcad4fdb8006d18b3da", "fetched_at": "2026-08-29T07:56:13.873376+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/use_dataset"}, {"content_hash": "9049903d19028d43f36303ef72a296180a611158e462f2bcfdb27f83f5a18633", "fetched_at": "2026-08-29T07:56:13.875116+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datasets/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:57:46.403280+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3c6ff3c493d874dab50debe73fdef66867a2e57ed2f7d43da2012396e933f8ef", "fetched_at": "2026-08-28T04:11:32.174613+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datasets"}, {"content_hash": "619622f88451b947f041fd432ad0feaba602c93726c44cd4cf4b524741d0da8c", "fetched_at": "2026-08-29T07:56:13.857218+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/datasets"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T07:56:13.859846+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cd748fc8a545347486f911cce31292bef53a793b6274825a33814f7a5bbcde6e", "fetched_at": "2026-08-29T07:56:13.863982+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/quickstart"}, {"content_hash": "c711168832634aef9fc16289c5c4c08e6c1754fd231fbea9f192d965cd03e924", "fetched_at": "2026-08-29T07:56:13.866023+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/installation"}, {"content_hash": "84fe8fae3e6c8876dbe615f2d601c97e5d7d3c33a5f2d4e49b3c59eade67361d", "fetched_at": "2026-08-29T07:56:13.867804+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/tutorial"}, {"content_hash": "b2e149befada518daf73d73b77b748309cd75bac187fc901cfcd09fdc5c3aa20", "fetched_at": "2026-08-29T07:56:13.869572+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/load_hub"}, {"content_hash": "a4ded9ba5009f390fff0655050a40299c656ecf69948c1dc9db88c66dedb38e6", "fetched_at": "2026-08-29T07:56:13.871523+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/access"}, {"content_hash": "b052d61cc4583f0be6ab2e74f495280fae1eaf6ef1f08bcad4fdb8006d18b3da", "fetched_at": "2026-08-29T07:56:13.873376+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/use_dataset"}, {"content_hash": "9049903d19028d43f36303ef72a296180a611158e462f2bcfdb27f83f5a18633", "fetched_at": "2026-08-29T07:56:13.875116+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datasets/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.174613+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:57:46.403280+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3c6ff3c493d874dab50debe73fdef66867a2e57ed2f7d43da2012396e933f8ef", "fetched_at": "2026-08-28T04:11:32.174613+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datasets"}, {"content_hash": "619622f88451b947f041fd432ad0feaba602c93726c44cd4cf4b524741d0da8c", "fetched_at": "2026-08-29T07:56:13.857218+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/datasets"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T07:56:13.859846+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cd748fc8a545347486f911cce31292bef53a793b6274825a33814f7a5bbcde6e", "fetched_at": "2026-08-29T07:56:13.863982+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/quickstart"}, {"content_hash": "c711168832634aef9fc16289c5c4c08e6c1754fd231fbea9f192d965cd03e924", "fetched_at": "2026-08-29T07:56:13.866023+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/installation"}, {"content_hash": "84fe8fae3e6c8876dbe615f2d601c97e5d7d3c33a5f2d4e49b3c59eade67361d", "fetched_at": "2026-08-29T07:56:13.867804+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/tutorial"}, {"content_hash": "b2e149befada518daf73d73b77b748309cd75bac187fc901cfcd09fdc5c3aa20", "fetched_at": "2026-08-29T07:56:13.869572+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/load_hub"}, {"content_hash": "a4ded9ba5009f390fff0655050a40299c656ecf69948c1dc9db88c66dedb38e6", "fetched_at": "2026-08-29T07:56:13.871523+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/access"}, {"content_hash": "b052d61cc4583f0be6ab2e74f495280fae1eaf6ef1f08bcad4fdb8006d18b3da", "fetched_at": "2026-08-29T07:56:13.873376+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/use_dataset"}, {"content_hash": "9049903d19028d43f36303ef72a296180a611158e462f2bcfdb27f83f5a18633", "fetched_at": "2026-08-29T07:56:13.875116+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datasets/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:57:46.403280+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3c6ff3c493d874dab50debe73fdef66867a2e57ed2f7d43da2012396e933f8ef", "fetched_at": "2026-08-28T04:11:32.174613+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datasets"}, {"content_hash": "619622f88451b947f041fd432ad0feaba602c93726c44cd4cf4b524741d0da8c", "fetched_at": "2026-08-29T07:56:13.857218+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/datasets"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T07:56:13.859846+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cd748fc8a545347486f911cce31292bef53a793b6274825a33814f7a5bbcde6e", "fetched_at": "2026-08-29T07:56:13.863982+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/quickstart"}, {"content_hash": "c711168832634aef9fc16289c5c4c08e6c1754fd231fbea9f192d965cd03e924", "fetched_at": "2026-08-29T07:56:13.866023+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/installation"}, {"content_hash": "84fe8fae3e6c8876dbe615f2d601c97e5d7d3c33a5f2d4e49b3c59eade67361d", "fetched_at": "2026-08-29T07:56:13.867804+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/tutorial"}, {"content_hash": "b2e149befada518daf73d73b77b748309cd75bac187fc901cfcd09fdc5c3aa20", "fetched_at": "2026-08-29T07:56:13.869572+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/load_hub"}, {"content_hash": "a4ded9ba5009f390fff0655050a40299c656ecf69948c1dc9db88c66dedb38e6", "fetched_at": "2026-08-29T07:56:13.871523+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/access"}, {"content_hash": "b052d61cc4583f0be6ab2e74f495280fae1eaf6ef1f08bcad4fdb8006d18b3da", "fetched_at": "2026-08-29T07:56:13.873376+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/use_dataset"}, {"content_hash": "9049903d19028d43f36303ef72a296180a611158e462f2bcfdb27f83f5a18633", "fetched_at": "2026-08-29T07:56:13.875116+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datasets/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:57:46.403280+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3c6ff3c493d874dab50debe73fdef66867a2e57ed2f7d43da2012396e933f8ef", "fetched_at": "2026-08-28T04:11:32.174613+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datasets"}, {"content_hash": "619622f88451b947f041fd432ad0feaba602c93726c44cd4cf4b524741d0da8c", "fetched_at": "2026-08-29T07:56:13.857218+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/datasets"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T07:56:13.859846+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cd748fc8a545347486f911cce31292bef53a793b6274825a33814f7a5bbcde6e", "fetched_at": "2026-08-29T07:56:13.863982+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/quickstart"}, {"content_hash": "c711168832634aef9fc16289c5c4c08e6c1754fd231fbea9f192d965cd03e924", "fetched_at": "2026-08-29T07:56:13.866023+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/installation"}, {"content_hash": "84fe8fae3e6c8876dbe615f2d601c97e5d7d3c33a5f2d4e49b3c59eade67361d", "fetched_at": "2026-08-29T07:56:13.867804+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/tutorial"}, {"content_hash": "b2e149befada518daf73d73b77b748309cd75bac187fc901cfcd09fdc5c3aa20", "fetched_at": "2026-08-29T07:56:13.869572+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/load_hub"}, {"content_hash": "a4ded9ba5009f390fff0655050a40299c656ecf69948c1dc9db88c66dedb38e6", "fetched_at": "2026-08-29T07:56:13.871523+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/access"}, {"content_hash": "b052d61cc4583f0be6ab2e74f495280fae1eaf6ef1f08bcad4fdb8006d18b3da", "fetched_at": "2026-08-29T07:56:13.873376+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/use_dataset"}, {"content_hash": "9049903d19028d43f36303ef72a296180a611158e462f2bcfdb27f83f5a18633", "fetched_at": "2026-08-29T07:56:13.875116+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datasets/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:57:46.403280+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3c6ff3c493d874dab50debe73fdef66867a2e57ed2f7d43da2012396e933f8ef", "fetched_at": "2026-08-28T04:11:32.174613+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/datasets"}, {"content_hash": "619622f88451b947f041fd432ad0feaba602c93726c44cd4cf4b524741d0da8c", "fetched_at": "2026-08-29T07:56:13.857218+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/datasets"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T07:56:13.859846+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cd748fc8a545347486f911cce31292bef53a793b6274825a33814f7a5bbcde6e", "fetched_at": "2026-08-29T07:56:13.863982+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/quickstart"}, {"content_hash": "c711168832634aef9fc16289c5c4c08e6c1754fd231fbea9f192d965cd03e924", "fetched_at": "2026-08-29T07:56:13.866023+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/installation"}, {"content_hash": "84fe8fae3e6c8876dbe615f2d601c97e5d7d3c33a5f2d4e49b3c59eade67361d", "fetched_at": "2026-08-29T07:56:13.867804+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/tutorial"}, {"content_hash": "b2e149befada518daf73d73b77b748309cd75bac187fc901cfcd09fdc5c3aa20", "fetched_at": "2026-08-29T07:56:13.869572+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/load_hub"}, {"content_hash": "a4ded9ba5009f390fff0655050a40299c656ecf69948c1dc9db88c66dedb38e6", "fetched_at": "2026-08-29T07:56:13.871523+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/access"}, {"content_hash": "b052d61cc4583f0be6ab2e74f495280fae1eaf6ef1f08bcad4fdb8006d18b3da", "fetched_at": "2026-08-29T07:56:13.873376+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/datasets/use_dataset"}, {"content_hash": "9049903d19028d43f36303ef72a296180a611158e462f2bcfdb27f83f5a18633", "fetched_at": "2026-08-29T07:56:13.875116+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datasets/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 95}, "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": 2351, "days_push": 7, "days_rel": 36, "gap_med": 12.5, "n_releases_24m": 33}, "score": 98, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}