{"adoption": {"forks": 6604, "observed_at": "2026-08-28T04:12:21.669896+00:00", "stars": 78560}, "canonical_url": "https://ross.abutalabs.com/products/mineru", "card": {"archived": false, "artifact_type": "library", "description": "Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.", "domain": ["pdf", "large-language-models", "developer-tools"], "enriched": true, "function": ["ocr", "parser", "pdf", "nlp", "rag", "machine-learning"], "health_score": 100, "homepage": "https://opendatalab.github.io/MinerU/", "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["opendatalab/MinerU"], "name": "opendatalab/MinerU", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-08-25T20:03:39+00:00", "repo": "opendatalab/MinerU", "stars": 78560, "tags": ["document-parsing", "pdf-to-markdown", "layout-analysis", "llm-ready", "document-understanding", "formula-recognition", "table-extraction", "natural-language-processing", "data-engineering", "web-server", "gpu"], "topics": ["extract-data", "layout-analysis", "ocr", "parser", "pdf", "pdf-converter", "python", "document-analysis", "pdf-parser", "pdf-extractor-llm", "pdf-extractor-pretrain", "pdf-extractor-rag", "ai4science", "docx", "pptx", "xlsx"], "urls": [], "use_cases": ["convert pdfs to markdown for llm training", "extract text and tables from scanned pdfs", "prepare documents for rag pipelines", "parse research papers with formulas into latex", "convert docx and pptx files to", "ocr documents in multiple languages", "extract structured data from complex pdf layouts"], "what_it_is": "MinerU is a document parsing tool that converts PDFs, images, DOCX, PPTX, and XLSX files into machine-readable Markdown and JSON. It handles layout analysis, OCR in 109 languages, formula-to-LaTeX conversion, and table extraction, making documents ready for LLM and RAG pipelines.", "when_to_avoid": ["you only need simple text extraction from plain digital PDFs", "you need pixel-perfect visual fidelity of the original document", "you cannot run GPU-accelerated models locally and need lightweight processing"], "when_to_choose": ["you need LLM-ready markdown or JSON from complex documents", "documents contain formulas, tables, or multi-column layouts", "you need OCR for scanned or garbled PDFs", "you want a CLI, API, or WebUI for batch document conversion"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/mineru", "repo": "opendatalab/MinerU", "role": "main", "score": 88}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:14:11.374000+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "653cb63df358910c0dc2488bfb23049c53bd96033b49c169eb0c1b31526e5764", "fetched_at": "2026-08-28T04:12:21.669896+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/MinerU"}, {"content_hash": "4c1da043420781fdd4698a6cd09a6bfaea4c153defd8d7e10a7bb361cdcd8090", "fetched_at": "2026-08-28T17:42:27.073580+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.github.io/MinerU/"}, {"content_hash": "872683b6a78487fe2ca682bbfee4aa5de32a7e1b3ce033524cfbe59a6d0f9c4a", "fetched_at": "2026-08-28T17:42:27.082561+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mineru/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:14:11.374000+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "653cb63df358910c0dc2488bfb23049c53bd96033b49c169eb0c1b31526e5764", "fetched_at": "2026-08-28T04:12:21.669896+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/MinerU"}, {"content_hash": "4c1da043420781fdd4698a6cd09a6bfaea4c153defd8d7e10a7bb361cdcd8090", "fetched_at": "2026-08-28T17:42:27.073580+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.github.io/MinerU/"}, {"content_hash": "872683b6a78487fe2ca682bbfee4aa5de32a7e1b3ce033524cfbe59a6d0f9c4a", "fetched_at": "2026-08-28T17:42:27.082561+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mineru/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:14:11.374000+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "653cb63df358910c0dc2488bfb23049c53bd96033b49c169eb0c1b31526e5764", "fetched_at": "2026-08-28T04:12:21.669896+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/MinerU"}, {"content_hash": "4c1da043420781fdd4698a6cd09a6bfaea4c153defd8d7e10a7bb361cdcd8090", "fetched_at": "2026-08-28T17:42:27.073580+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.github.io/MinerU/"}, {"content_hash": "872683b6a78487fe2ca682bbfee4aa5de32a7e1b3ce033524cfbe59a6d0f9c4a", "fetched_at": "2026-08-28T17:42:27.082561+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mineru/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:14:11.374000+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "653cb63df358910c0dc2488bfb23049c53bd96033b49c169eb0c1b31526e5764", "fetched_at": "2026-08-28T04:12:21.669896+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/MinerU"}, {"content_hash": "4c1da043420781fdd4698a6cd09a6bfaea4c153defd8d7e10a7bb361cdcd8090", "fetched_at": "2026-08-28T17:42:27.073580+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.github.io/MinerU/"}, {"content_hash": "872683b6a78487fe2ca682bbfee4aa5de32a7e1b3ce033524cfbe59a6d0f9c4a", "fetched_at": "2026-08-28T17:42:27.082561+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mineru/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:14:11.374000+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "653cb63df358910c0dc2488bfb23049c53bd96033b49c169eb0c1b31526e5764", "fetched_at": "2026-08-28T04:12:21.669896+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/MinerU"}, {"content_hash": "4c1da043420781fdd4698a6cd09a6bfaea4c153defd8d7e10a7bb361cdcd8090", "fetched_at": "2026-08-28T17:42:27.073580+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.github.io/MinerU/"}, {"content_hash": "872683b6a78487fe2ca682bbfee4aa5de32a7e1b3ce033524cfbe59a6d0f9c4a", "fetched_at": "2026-08-28T17:42:27.082561+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mineru/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:14:11.374000+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "653cb63df358910c0dc2488bfb23049c53bd96033b49c169eb0c1b31526e5764", "fetched_at": "2026-08-28T04:12:21.669896+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/MinerU"}, {"content_hash": "4c1da043420781fdd4698a6cd09a6bfaea4c153defd8d7e10a7bb361cdcd8090", "fetched_at": "2026-08-28T17:42:27.073580+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.github.io/MinerU/"}, {"content_hash": "872683b6a78487fe2ca682bbfee4aa5de32a7e1b3ce033524cfbe59a6d0f9c4a", "fetched_at": "2026-08-28T17:42:27.082561+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mineru/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:21.669896+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:14:11.374000+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "653cb63df358910c0dc2488bfb23049c53bd96033b49c169eb0c1b31526e5764", "fetched_at": "2026-08-28T04:12:21.669896+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/MinerU"}, {"content_hash": "4c1da043420781fdd4698a6cd09a6bfaea4c153defd8d7e10a7bb361cdcd8090", "fetched_at": "2026-08-28T17:42:27.073580+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.github.io/MinerU/"}, {"content_hash": "872683b6a78487fe2ca682bbfee4aa5de32a7e1b3ce033524cfbe59a6d0f9c4a", "fetched_at": "2026-08-28T17:42:27.082561+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mineru/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:14:11.374000+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "653cb63df358910c0dc2488bfb23049c53bd96033b49c169eb0c1b31526e5764", "fetched_at": "2026-08-28T04:12:21.669896+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/MinerU"}, {"content_hash": "4c1da043420781fdd4698a6cd09a6bfaea4c153defd8d7e10a7bb361cdcd8090", "fetched_at": "2026-08-28T17:42:27.073580+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.github.io/MinerU/"}, {"content_hash": "872683b6a78487fe2ca682bbfee4aa5de32a7e1b3ce033524cfbe59a6d0f9c4a", "fetched_at": "2026-08-28T17:42:27.082561+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mineru/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:14:11.374000+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "653cb63df358910c0dc2488bfb23049c53bd96033b49c169eb0c1b31526e5764", "fetched_at": "2026-08-28T04:12:21.669896+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/MinerU"}, {"content_hash": "4c1da043420781fdd4698a6cd09a6bfaea4c153defd8d7e10a7bb361cdcd8090", "fetched_at": "2026-08-28T17:42:27.073580+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.github.io/MinerU/"}, {"content_hash": "872683b6a78487fe2ca682bbfee4aa5de32a7e1b3ce033524cfbe59a6d0f9c4a", "fetched_at": "2026-08-28T17:42:27.082561+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mineru/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:14:11.374000+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "653cb63df358910c0dc2488bfb23049c53bd96033b49c169eb0c1b31526e5764", "fetched_at": "2026-08-28T04:12:21.669896+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/MinerU"}, {"content_hash": "4c1da043420781fdd4698a6cd09a6bfaea4c153defd8d7e10a7bb361cdcd8090", "fetched_at": "2026-08-28T17:42:27.073580+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.github.io/MinerU/"}, {"content_hash": "872683b6a78487fe2ca682bbfee4aa5de32a7e1b3ce033524cfbe59a6d0f9c4a", "fetched_at": "2026-08-28T17:42:27.082561+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/mineru/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 65, "rhythm": 86}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 916, "days_push": 8, "days_rel": 19, "gap_med": 2.0, "n_releases_24m": 105}, "score": 88, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}