{"adoption": {"forks": 442, "observed_at": "2026-08-28T04:09:40.721655+00:00", "stars": 6226}, "canonical_url": "https://ross.abutalabs.com/products/pdf-craft", "card": {"archived": false, "artifact_type": "library", "description": "PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.", "domain": ["pdf", "files", "developer-tools"], "enriched": true, "function": ["ocr", "pdf", "parser", "nlp", "llm-inference"], "health_score": 100, "homepage": "https://inkora.oomol.com/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["oomol-lab/pdf-craft"], "name": "oomol-lab/pdf-craft", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-25T11:56:57+00:00", "repo": "oomol-lab/pdf-craft", "stars": 6226, "tags": ["pdf-conversion", "epub", "markdown", "scanned-books", "document-processing", "translation", "natural-language-processing", "gpu"], "topics": ["document", "ocr", "pdf", "deepseek-ocr"], "urls": [], "use_cases": ["convert scanned book pdfs to markdown", "turn pdf into epub", "make scanned documents searchable", "ocr a scanned pdf book", "translate a pdf and write translation back into it", "extract tables and formulas from scanned pdfs"], "what_it_is": "pdf-craft is a Python library that converts PDF files into Markdown or EPUB, with a focus on scanned books and documents. It uses OCR (locally on GPU or via a remote vendor service) and an LLM for translation, handling tables of contents, footnotes, tables, formulas, and images.", "when_to_avoid": ["you only need simple text extraction from digitally-born (non-scanned) PDFs", "you need a GUI-only tool with no programming", "you lack a GPU and cannot use a remote OCR service"], "when_to_choose": ["you need to convert scanned books or academic documents into editable formats like Markdown or EPUB", "you want a Python library with both local GPU OCR and remote OCR service options", "you need PDF translation integrated into the conversion pipeline"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdf-craft", "repo": "oomol-lab/pdf-craft", "role": "main", "score": 87}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:47:13.866316+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b4a03cbe62af265b3f3ede8944dd1435dbb654ebc4d9287e2518e3e8494a3185", "fetched_at": "2026-08-28T04:09:40.721655+00:00", "kind": "readme", "missing": false, "url": "https://github.com/oomol-lab/pdf-craft"}, {"content_hash": "2b06242a38e5c860fca06bd2cacd041d5450f4e5be14b7774f006b86ca7665bb", "fetched_at": "2026-08-29T08:43:31.009076+00:00", "kind": "homepage", "missing": false, "url": "https://inkora.oomol.com/"}, {"content_hash": "f6edb921dfd10c2563d3c17e0e6245753a2593aaec0b073589b15198b586e7ed", "fetched_at": "2026-08-29T08:43:31.019048+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdf-craft/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:47:13.866316+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b4a03cbe62af265b3f3ede8944dd1435dbb654ebc4d9287e2518e3e8494a3185", "fetched_at": "2026-08-28T04:09:40.721655+00:00", "kind": "readme", "missing": false, "url": "https://github.com/oomol-lab/pdf-craft"}, {"content_hash": "2b06242a38e5c860fca06bd2cacd041d5450f4e5be14b7774f006b86ca7665bb", "fetched_at": "2026-08-29T08:43:31.009076+00:00", "kind": "homepage", "missing": false, "url": "https://inkora.oomol.com/"}, {"content_hash": "f6edb921dfd10c2563d3c17e0e6245753a2593aaec0b073589b15198b586e7ed", "fetched_at": "2026-08-29T08:43:31.019048+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdf-craft/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:47:13.866316+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b4a03cbe62af265b3f3ede8944dd1435dbb654ebc4d9287e2518e3e8494a3185", "fetched_at": "2026-08-28T04:09:40.721655+00:00", "kind": "readme", "missing": false, "url": "https://github.com/oomol-lab/pdf-craft"}, {"content_hash": "2b06242a38e5c860fca06bd2cacd041d5450f4e5be14b7774f006b86ca7665bb", "fetched_at": "2026-08-29T08:43:31.009076+00:00", "kind": "homepage", "missing": false, "url": "https://inkora.oomol.com/"}, {"content_hash": "f6edb921dfd10c2563d3c17e0e6245753a2593aaec0b073589b15198b586e7ed", "fetched_at": "2026-08-29T08:43:31.019048+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdf-craft/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:47:13.866316+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b4a03cbe62af265b3f3ede8944dd1435dbb654ebc4d9287e2518e3e8494a3185", "fetched_at": "2026-08-28T04:09:40.721655+00:00", "kind": "readme", "missing": false, "url": "https://github.com/oomol-lab/pdf-craft"}, {"content_hash": "2b06242a38e5c860fca06bd2cacd041d5450f4e5be14b7774f006b86ca7665bb", "fetched_at": "2026-08-29T08:43:31.009076+00:00", "kind": "homepage", "missing": false, "url": "https://inkora.oomol.com/"}, {"content_hash": "f6edb921dfd10c2563d3c17e0e6245753a2593aaec0b073589b15198b586e7ed", "fetched_at": "2026-08-29T08:43:31.019048+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdf-craft/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:47:13.866316+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b4a03cbe62af265b3f3ede8944dd1435dbb654ebc4d9287e2518e3e8494a3185", "fetched_at": "2026-08-28T04:09:40.721655+00:00", "kind": "readme", "missing": false, "url": "https://github.com/oomol-lab/pdf-craft"}, {"content_hash": "2b06242a38e5c860fca06bd2cacd041d5450f4e5be14b7774f006b86ca7665bb", "fetched_at": "2026-08-29T08:43:31.009076+00:00", "kind": "homepage", "missing": false, "url": "https://inkora.oomol.com/"}, {"content_hash": "f6edb921dfd10c2563d3c17e0e6245753a2593aaec0b073589b15198b586e7ed", "fetched_at": "2026-08-29T08:43:31.019048+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdf-craft/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:47:13.866316+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b4a03cbe62af265b3f3ede8944dd1435dbb654ebc4d9287e2518e3e8494a3185", "fetched_at": "2026-08-28T04:09:40.721655+00:00", "kind": "readme", "missing": false, "url": "https://github.com/oomol-lab/pdf-craft"}, {"content_hash": "2b06242a38e5c860fca06bd2cacd041d5450f4e5be14b7774f006b86ca7665bb", "fetched_at": "2026-08-29T08:43:31.009076+00:00", "kind": "homepage", "missing": false, "url": "https://inkora.oomol.com/"}, {"content_hash": "f6edb921dfd10c2563d3c17e0e6245753a2593aaec0b073589b15198b586e7ed", "fetched_at": "2026-08-29T08:43:31.019048+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdf-craft/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.721655+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:47:13.866316+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b4a03cbe62af265b3f3ede8944dd1435dbb654ebc4d9287e2518e3e8494a3185", "fetched_at": "2026-08-28T04:09:40.721655+00:00", "kind": "readme", "missing": false, "url": "https://github.com/oomol-lab/pdf-craft"}, {"content_hash": "2b06242a38e5c860fca06bd2cacd041d5450f4e5be14b7774f006b86ca7665bb", "fetched_at": "2026-08-29T08:43:31.009076+00:00", "kind": "homepage", "missing": false, "url": "https://inkora.oomol.com/"}, {"content_hash": "f6edb921dfd10c2563d3c17e0e6245753a2593aaec0b073589b15198b586e7ed", "fetched_at": "2026-08-29T08:43:31.019048+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdf-craft/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:47:13.866316+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b4a03cbe62af265b3f3ede8944dd1435dbb654ebc4d9287e2518e3e8494a3185", "fetched_at": "2026-08-28T04:09:40.721655+00:00", "kind": "readme", "missing": false, "url": "https://github.com/oomol-lab/pdf-craft"}, {"content_hash": "2b06242a38e5c860fca06bd2cacd041d5450f4e5be14b7774f006b86ca7665bb", "fetched_at": "2026-08-29T08:43:31.009076+00:00", "kind": "homepage", "missing": false, "url": "https://inkora.oomol.com/"}, {"content_hash": "f6edb921dfd10c2563d3c17e0e6245753a2593aaec0b073589b15198b586e7ed", "fetched_at": "2026-08-29T08:43:31.019048+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdf-craft/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:47:13.866316+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b4a03cbe62af265b3f3ede8944dd1435dbb654ebc4d9287e2518e3e8494a3185", "fetched_at": "2026-08-28T04:09:40.721655+00:00", "kind": "readme", "missing": false, "url": "https://github.com/oomol-lab/pdf-craft"}, {"content_hash": "2b06242a38e5c860fca06bd2cacd041d5450f4e5be14b7774f006b86ca7665bb", "fetched_at": "2026-08-29T08:43:31.009076+00:00", "kind": "homepage", "missing": false, "url": "https://inkora.oomol.com/"}, {"content_hash": "f6edb921dfd10c2563d3c17e0e6245753a2593aaec0b073589b15198b586e7ed", "fetched_at": "2026-08-29T08:43:31.019048+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdf-craft/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:47:13.866316+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b4a03cbe62af265b3f3ede8944dd1435dbb654ebc4d9287e2518e3e8494a3185", "fetched_at": "2026-08-28T04:09:40.721655+00:00", "kind": "readme", "missing": false, "url": "https://github.com/oomol-lab/pdf-craft"}, {"content_hash": "2b06242a38e5c860fca06bd2cacd041d5450f4e5be14b7774f006b86ca7665bb", "fetched_at": "2026-08-29T08:43:31.009076+00:00", "kind": "homepage", "missing": false, "url": "https://inkora.oomol.com/"}, {"content_hash": "f6edb921dfd10c2563d3c17e0e6245753a2593aaec0b073589b15198b586e7ed", "fetched_at": "2026-08-29T08:43:31.019048+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdf-craft/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 40, "rhythm": 99}, "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": 567, "days_push": 8, "days_rel": 6, "gap_med": 7, "n_releases_24m": 22}, "score": 87, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}