{"id":"hugging-face-datasets--huggingface-co","name":"Hugging Face Datasets","url":"https://huggingface.co/docs/datasets","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/hugging-face-datasets--huggingface-co","family":"models-ops","section":"Training infrastructure","sections":["Training infrastructure"],"tier":1,"last_verified_at":"2026-10-27","lifecycle":{"status":"active","severity":0,"note":null},"taxonomy":null,"cells":{"type":{"value":"Dataset library + Hub","citation":"https://huggingface.co/docs/datasets","status":"real-data","tier":"T2","source_class":"vendor"},"desc":{"value":"Library for accessing and processing 100k+ public datasets on the Hub. Apache Arrow-backed; default dataset layer for the open ML ecosystem.","citation":"https://huggingface.co/docs/datasets","status":"real-data","tier":"T2","source_class":"vendor"},"claims":{"value":"100k+ datasets on Hub; standard dataset library across OSS NLP/CV.","citation":"https://huggingface.co/docs/datasets","status":"real-data","tier":"T2","source_class":"vendor"},"modalities":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"created":{"value":"2020","citation":"https://huggingface.co/docs/datasets","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"vendor"},"latest-release":{"value":"v5.1.0 (2026-10-05)","citation":"https://pypi.org/project/datasets/","status":"real-data","tier":"T2","last_verified_at":"2026-10-27","source_class":"registry"},"license":{"value":"Apache-2.0","citation":"https://huggingface.co/docs/datasets","status":"real-data","tier":"T2","source_class":"vendor"},"gh":{"value":"huggingface/datasets — ~22.1k stars, last commit 2026-10","citation":"https://github.com/huggingface/datasets","status":"real-data","tier":"T1","last_verified_at":"2026-10-27","source_class":"repo"},"mindshare":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","last_verified_at":"2026-05-12","source_class":"vendor"},"citations":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","last_verified_at":"2026-05-12","source_class":"vendor"},"funding":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","last_verified_at":"2026-05-12","source_class":"vendor"},"customers":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"pricing":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"compliance":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"data-handling":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"deployment":{"value":"Self-hosted only — library","citation":"https://pypi.org/project/datasets/","status":"real-data","tier":"T2","source_class":"registry"},"hq":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"founders":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"volume":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"perf":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"repro":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"code-release":{"value":"Active — last commit 2026-05 · 21,512★","citation":"https://github.com/huggingface/datasets","status":"real-data","tier":"T1","source_class":"repo"},"api-surface":{"value":"Python library (datasets)","citation":"https://github.com/huggingface/datasets","status":"real-data","tier":"T1","source_class":"repo"},"latency":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"throughput":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"backend-storage":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"multi-tenancy":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"encryption":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"sso-rbac":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"embedding-model":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"consistency":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"versioning":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"tombstoning":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"schema-evolution":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"namespace":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"contradiction":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"forgetting":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"mcp-support":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"a2a-support":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"otel":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"webhooks":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"import-export":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"integration-count":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"orchestration":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"programmatic-control":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"vendor-benchmarks":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","last_verified_at":"2026-05-12","source_class":"vendor"},"pricing-specifics":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"agent-abstraction":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"memory-primitives":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"llm-lock":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"runtimes":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"session-handling":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"validated-verticals":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"time-to-running":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"anti-fit":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"optimised-for":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"adjacent-infrastructure":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"pros":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cons":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"links":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"obs-langsmith":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-opentelemetry":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-datadog":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-helicone":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-weave":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-langfuse":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-arize":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-custom":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-token-budget":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-prompt-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-semantic-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-batching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-model-routing":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-streaming-only":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-observability-cost-attribution":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-langsmith-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-braintrust":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-weights-and-biases-agent":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-helicone-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-custom-test-harness":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-human-loop":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-production-traffic-replay":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"commit-trajectory":{"value":"not applicable — no GitHub repo","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"citation-trajectory":{"value":"not applicable — non-paper row","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"download-trajectory":{"value":"not applicable — not published as a package","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"cost-input-usd-per-mtok":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-output-usd-per-mtok":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-tier":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-pricing-model":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-last-verified":{"value":"searched not found","citation":"https://huggingface.co/docs/datasets","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"capability-composite-score":{"value":"not applicable — dataset library / Hub, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-band":{"value":"not applicable — dataset library / Hub, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-benchmark-sources":{"value":"not applicable — dataset library / Hub, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-last-verified":{"value":"not applicable — dataset library / Hub, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-tags":{"value":"not applicable — dataset library + Hub, not a deployable agent/memory use case","citation":null,"status":"not-applicable","tier":"T3"},"use-case-anti-tags":{"value":"not applicable — training-data infrastructure, no inference-time use case to flag against","citation":null,"status":"not-applicable","tier":"T3"},"adoption-accelerator":{"value":"betaworks-camp-2016","citation":"https://www.betaworks.com/camp/botcamp","status":"real-data","tier":"T2","source_class":"third-party"},"architecture-deployment-locus":{"value":"local","citation":"https://huggingface.co/docs/datasets/index","status":"real-data","tier":"T2","source_class":"vendor"},"licensing-bucket":{"value":"open-source","citation":"https://huggingface.co/docs/datasets","status":"real-data","tier":"T2","source_class":"vendor"},"positioning-platform-vs-product":{"value":"platform","citation":"https://huggingface.co/docs/datasets/index","status":"real-data","tier":"T2","source_class":"vendor"},"taxonomy-three-layer-rollup":{"value":"model-infra","citation":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/docs/schema/section-to-three-layer-rollup.json","status":"real-data","tier":"T1","source_class":"repo"},"developer-activity-opendigger":{"value":"{\"activity\":237.77,\"as_of\":\"2026-09\",\"openrank_12mo\":27.29,\"openrank_current\":21.7,\"participants\":107}","citation":"https://oss.open-digger.cn/github/huggingface/datasets/openrank.json","status":"real-data","tier":"T2","last_verified_at":"2026-10-28","source_class":"third-party"},"freshness-date":{"value":"2026-10-27","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/hugging-face-datasets--huggingface-co","status":"real-data","tier":"T2","source_class":"catalog"},"compliance-certifications":{"value":"","citation":null,"status":"no-data","tier":"T3"},"sdk-languages":{"value":"","citation":null,"status":"no-data","tier":"T3"},"protocol-support":{"value":"","citation":null,"status":"no-data","tier":"T3"},"maturity":{"value":"","citation":null,"status":"no-data","tier":"T3"}},"corroboration":{"cited_cells":16,"third_party_cells":2},"edges":{"outgoing":[],"incoming":[{"source":"comet-ml--comet-com","target":"hugging-face-datasets--huggingface-co","type":"integrates-with","evidence":"Comet's Opik docs have a Hugging Face Datasets integration page.","citation":"https://www.comet.com/docs/opik/integrations/huggingface-datasets","verified_at":"2026-10-29"}]},"history":[{"date":"2026-10-27","commit":"9482a0953d","pr":271,"kind":"update","changes":[{"field":"latest-release","label":"Latest release","from":"","to":"v5.1.0 (2026-10-05)","first":true,"source":"https://pypi.org/project/datasets/"},{"field":"deployment","label":"Deployment","from":"","to":"Self-hosted only — library","first":true,"source":"https://pypi.org/project/datasets/"}]}],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}