{"adoption": {"forks": 1524, "observed_at": "2026-08-28T04:11:07.759456+00:00", "stars": 14833}, "canonical_url": "https://ross.abutalabs.com/products/easy-dataset", "card": {"archived": false, "artifact_type": "application", "description": "A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval", "domain": ["large-language-models", "machine-learning", "data-science", "artificial-intelligence"], "enriched": true, "function": ["data-generation", "etl", "rag", "llm-training", "prompt-engineering", "pdf", "nlp"], "health_score": 86, "homepage": "https://docs.easy-dataset.com", "language": "JavaScript", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["ConardLi/easy-dataset"], "name": "ConardLi/easy-dataset", "platform": ["self-hosted", "cross-platform"], "pushed_at": "2026-05-01T15:03:32+00:00", "repo": "ConardLi/easy-dataset", "stars": 14833, "tags": ["fine-tuning-datasets", "dataset-creation", "document-parsing", "text-chunking", "qa-generation", "model-evaluation", "data-labeling", "agpl", "retrieval-augmented-generation", "web-server", "docker", "nodejs"], "topics": ["dataset", "javascript", "llm", "fine-tuning", "rag"], "urls": [], "use_cases": ["create fine-tuning datasets from domain documents", "generate QA pairs from PDFs for LLM training", "build evaluation test sets for vertical domain models", "convert datasets between fine-tuning formats", "manage and label large batches of generated questions", "evaluate RAG recall and post-fine-tune model performance", "construct COT reasoning data for fine-tuning"], "what_it_is": "Easy Dataset is a self-hosted web application for building high-quality structured datasets for LLM fine-tuning, RAG, and model evaluation. It converts domain documents (PDF, Markdown, DOCX, EPUB, etc.) into question-answer datasets via intelligent segmentation, AI-assisted generation, labeling, export, and evaluation workflows.", "when_to_avoid": ["you only need a small one-off script to transform existing JSONL data", "you require a fully automated headless data pipeline without a UI", "you need a permissively licensed library to embed in closed-source products (AGPL-3.0)"], "when_to_choose": ["you need to turn domain documents into structured training or eval datasets", "you want a GUI-driven pipeline covering parsing, chunking, generation, labeling, and export", "you need dataset formats for common fine-tuning frameworks and RAG evaluation"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/easy-dataset", "repo": "ConardLi/easy-dataset", "role": "main", "score": 71}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:07:08.315287+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05d9dce95684cce715f77f986b76cdbffd4f7b54c84def9f4cf0f6c89cd9c250", "fetched_at": "2026-08-28T04:11:07.759456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ConardLi/easy-dataset"}, {"content_hash": "c2233544658eeb516dc16d50ea2d267927edc4d38bc878ff4a277f98c4fe7442", "fetched_at": "2026-08-29T08:05:33.413295+00:00", "kind": "homepage", "missing": false, "url": "https://docs.easy-dataset.com"}, {"content_hash": "50d8514d9283f88d1301af046258a3c456c30700b4982df674bfbd1b9dd5ebb4", "fetched_at": "2026-08-29T08:05:33.423294+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/quickstart"}, {"content_hash": "78585e972f97e3c49e6e3d145dae56301594eb6a6f9e9dbda9243d118c52c328", "fetched_at": "2026-08-29T08:05:33.425168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/publish-your-docs"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:07:08.315287+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05d9dce95684cce715f77f986b76cdbffd4f7b54c84def9f4cf0f6c89cd9c250", "fetched_at": "2026-08-28T04:11:07.759456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ConardLi/easy-dataset"}, {"content_hash": "c2233544658eeb516dc16d50ea2d267927edc4d38bc878ff4a277f98c4fe7442", "fetched_at": "2026-08-29T08:05:33.413295+00:00", "kind": "homepage", "missing": false, "url": "https://docs.easy-dataset.com"}, {"content_hash": "50d8514d9283f88d1301af046258a3c456c30700b4982df674bfbd1b9dd5ebb4", "fetched_at": "2026-08-29T08:05:33.423294+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/quickstart"}, {"content_hash": "78585e972f97e3c49e6e3d145dae56301594eb6a6f9e9dbda9243d118c52c328", "fetched_at": "2026-08-29T08:05:33.425168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/publish-your-docs"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:07:08.315287+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05d9dce95684cce715f77f986b76cdbffd4f7b54c84def9f4cf0f6c89cd9c250", "fetched_at": "2026-08-28T04:11:07.759456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ConardLi/easy-dataset"}, {"content_hash": "c2233544658eeb516dc16d50ea2d267927edc4d38bc878ff4a277f98c4fe7442", "fetched_at": "2026-08-29T08:05:33.413295+00:00", "kind": "homepage", "missing": false, "url": "https://docs.easy-dataset.com"}, {"content_hash": "50d8514d9283f88d1301af046258a3c456c30700b4982df674bfbd1b9dd5ebb4", "fetched_at": "2026-08-29T08:05:33.423294+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/quickstart"}, {"content_hash": "78585e972f97e3c49e6e3d145dae56301594eb6a6f9e9dbda9243d118c52c328", "fetched_at": "2026-08-29T08:05:33.425168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/publish-your-docs"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:07:08.315287+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05d9dce95684cce715f77f986b76cdbffd4f7b54c84def9f4cf0f6c89cd9c250", "fetched_at": "2026-08-28T04:11:07.759456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ConardLi/easy-dataset"}, {"content_hash": "c2233544658eeb516dc16d50ea2d267927edc4d38bc878ff4a277f98c4fe7442", "fetched_at": "2026-08-29T08:05:33.413295+00:00", "kind": "homepage", "missing": false, "url": "https://docs.easy-dataset.com"}, {"content_hash": "50d8514d9283f88d1301af046258a3c456c30700b4982df674bfbd1b9dd5ebb4", "fetched_at": "2026-08-29T08:05:33.423294+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/quickstart"}, {"content_hash": "78585e972f97e3c49e6e3d145dae56301594eb6a6f9e9dbda9243d118c52c328", "fetched_at": "2026-08-29T08:05:33.425168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/publish-your-docs"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:07:08.315287+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05d9dce95684cce715f77f986b76cdbffd4f7b54c84def9f4cf0f6c89cd9c250", "fetched_at": "2026-08-28T04:11:07.759456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ConardLi/easy-dataset"}, {"content_hash": "c2233544658eeb516dc16d50ea2d267927edc4d38bc878ff4a277f98c4fe7442", "fetched_at": "2026-08-29T08:05:33.413295+00:00", "kind": "homepage", "missing": false, "url": "https://docs.easy-dataset.com"}, {"content_hash": "50d8514d9283f88d1301af046258a3c456c30700b4982df674bfbd1b9dd5ebb4", "fetched_at": "2026-08-29T08:05:33.423294+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/quickstart"}, {"content_hash": "78585e972f97e3c49e6e3d145dae56301594eb6a6f9e9dbda9243d118c52c328", "fetched_at": "2026-08-29T08:05:33.425168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/publish-your-docs"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:07:08.315287+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05d9dce95684cce715f77f986b76cdbffd4f7b54c84def9f4cf0f6c89cd9c250", "fetched_at": "2026-08-28T04:11:07.759456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ConardLi/easy-dataset"}, {"content_hash": "c2233544658eeb516dc16d50ea2d267927edc4d38bc878ff4a277f98c4fe7442", "fetched_at": "2026-08-29T08:05:33.413295+00:00", "kind": "homepage", "missing": false, "url": "https://docs.easy-dataset.com"}, {"content_hash": "50d8514d9283f88d1301af046258a3c456c30700b4982df674bfbd1b9dd5ebb4", "fetched_at": "2026-08-29T08:05:33.423294+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/quickstart"}, {"content_hash": "78585e972f97e3c49e6e3d145dae56301594eb6a6f9e9dbda9243d118c52c328", "fetched_at": "2026-08-29T08:05:33.425168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/publish-your-docs"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.759456+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:07:08.315287+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05d9dce95684cce715f77f986b76cdbffd4f7b54c84def9f4cf0f6c89cd9c250", "fetched_at": "2026-08-28T04:11:07.759456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ConardLi/easy-dataset"}, {"content_hash": "c2233544658eeb516dc16d50ea2d267927edc4d38bc878ff4a277f98c4fe7442", "fetched_at": "2026-08-29T08:05:33.413295+00:00", "kind": "homepage", "missing": false, "url": "https://docs.easy-dataset.com"}, {"content_hash": "50d8514d9283f88d1301af046258a3c456c30700b4982df674bfbd1b9dd5ebb4", "fetched_at": "2026-08-29T08:05:33.423294+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/quickstart"}, {"content_hash": "78585e972f97e3c49e6e3d145dae56301594eb6a6f9e9dbda9243d118c52c328", "fetched_at": "2026-08-29T08:05:33.425168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/publish-your-docs"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:07:08.315287+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05d9dce95684cce715f77f986b76cdbffd4f7b54c84def9f4cf0f6c89cd9c250", "fetched_at": "2026-08-28T04:11:07.759456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ConardLi/easy-dataset"}, {"content_hash": "c2233544658eeb516dc16d50ea2d267927edc4d38bc878ff4a277f98c4fe7442", "fetched_at": "2026-08-29T08:05:33.413295+00:00", "kind": "homepage", "missing": false, "url": "https://docs.easy-dataset.com"}, {"content_hash": "50d8514d9283f88d1301af046258a3c456c30700b4982df674bfbd1b9dd5ebb4", "fetched_at": "2026-08-29T08:05:33.423294+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/quickstart"}, {"content_hash": "78585e972f97e3c49e6e3d145dae56301594eb6a6f9e9dbda9243d118c52c328", "fetched_at": "2026-08-29T08:05:33.425168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/publish-your-docs"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:07:08.315287+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05d9dce95684cce715f77f986b76cdbffd4f7b54c84def9f4cf0f6c89cd9c250", "fetched_at": "2026-08-28T04:11:07.759456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ConardLi/easy-dataset"}, {"content_hash": "c2233544658eeb516dc16d50ea2d267927edc4d38bc878ff4a277f98c4fe7442", "fetched_at": "2026-08-29T08:05:33.413295+00:00", "kind": "homepage", "missing": false, "url": "https://docs.easy-dataset.com"}, {"content_hash": "50d8514d9283f88d1301af046258a3c456c30700b4982df674bfbd1b9dd5ebb4", "fetched_at": "2026-08-29T08:05:33.423294+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/quickstart"}, {"content_hash": "78585e972f97e3c49e6e3d145dae56301594eb6a6f9e9dbda9243d118c52c328", "fetched_at": "2026-08-29T08:05:33.425168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/publish-your-docs"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:07:08.315287+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05d9dce95684cce715f77f986b76cdbffd4f7b54c84def9f4cf0f6c89cd9c250", "fetched_at": "2026-08-28T04:11:07.759456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ConardLi/easy-dataset"}, {"content_hash": "c2233544658eeb516dc16d50ea2d267927edc4d38bc878ff4a277f98c4fe7442", "fetched_at": "2026-08-29T08:05:33.413295+00:00", "kind": "homepage", "missing": false, "url": "https://docs.easy-dataset.com"}, {"content_hash": "50d8514d9283f88d1301af046258a3c456c30700b4982df674bfbd1b9dd5ebb4", "fetched_at": "2026-08-29T08:05:33.423294+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/quickstart"}, {"content_hash": "78585e972f97e3c49e6e3d145dae56301594eb6a6f9e9dbda9243d118c52c328", "fetched_at": "2026-08-29T08:05:33.425168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.easy-dataset.com/ji-chu-gong-neng/publish-your-docs"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 80, "longevity": 39, "rhythm": 78}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 547, "days_push": 124, "days_rel": 146, "gap_med": 8.5, "n_releases_24m": 31}, "score": 71, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}