{"adoption": {"forks": 196, "observed_at": "2026-08-28T04:07:51.830095+00:00", "stars": 3248}, "canonical_url": "https://ross.abutalabs.com/products/deepdoctection", "card": {"archived": false, "artifact_type": "library", "description": "A Repo For Document AI", "domain": ["artificial-intelligence", "computer-vision", "pdf", "deep-learning"], "enriched": true, "function": ["ocr", "pdf", "machine-learning", "computer-vision", "nlp", "image-processing", "parser"], "health_score": 99, "homepage": "https://deepdoctection.readthedocs.io/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["deepdoctection/deepdoctection"], "name": "deepdoctection/deepdoctection", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-16T14:54:56+00:00", "repo": "deepdoctection/deepdoctection", "stars": 3248, "tags": ["document-ai", "document-layout-analysis", "table-recognition", "document-understanding", "layoutlm", "detectron2", "pdf-parsing", "natural-language-processing"], "topics": ["document-parser", "document-image-analysis", "table-recognition", "ocr", "document-ai", "document-understanding", "python", "document-layout-analysis", "table-detection", "pytorch", "tensorflow", "publaynet", "pubtabnet", "layoutlm", "nlp"], "urls": [], "use_cases": ["extract text and tables from scanned PDFs", "run OCR on document images", "detect document layout and tables", "classify documents with LayoutLM", "fine-tune document understanding models", "parse native PDF text"], "what_it_is": "deepdoctection is a Python library for Document AI that orchestrates document layout analysis, table recognition, OCR, and document/token classification into configurable pipelines. It supports fine-tuning and inference with models like LayoutLM, LiLT, and Detectron2-based detectors, and integrates OCR backends such as Tesseract, DocTr, and AWS Textract.", "when_to_avoid": ["need a simple one-line PDF text extractor without ML models", "working outside Python or without GPU/deep learning dependencies", "need a ready-made end-user application rather than a library"], "when_to_choose": ["building document extraction pipelines with layout analysis and OCR", "need table detection and recognition in documents", "want to fine-tune or use LayoutLM-family models", "processing scanned or PDF documents at scale in Python"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deepdoctection", "repo": "deepdoctection/deepdoctection", "role": "main", "score": 98}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.134299+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8236f9d9a7c0f1d5a047c1eb51fef0fd6f6042346f46f281950389b478f1a8f9", "fetched_at": "2026-08-28T04:07:51.830095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepdoctection/deepdoctection"}, {"content_hash": "5a5c104d2682be0f77ae0fda7d3677ba4d614a64ec1becb33ff5bd279dda6c90", "fetched_at": "2026-08-29T09:37:37.935693+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepdoctection/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.134299+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8236f9d9a7c0f1d5a047c1eb51fef0fd6f6042346f46f281950389b478f1a8f9", "fetched_at": "2026-08-28T04:07:51.830095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepdoctection/deepdoctection"}, {"content_hash": "5a5c104d2682be0f77ae0fda7d3677ba4d614a64ec1becb33ff5bd279dda6c90", "fetched_at": "2026-08-29T09:37:37.935693+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepdoctection/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.134299+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8236f9d9a7c0f1d5a047c1eb51fef0fd6f6042346f46f281950389b478f1a8f9", "fetched_at": "2026-08-28T04:07:51.830095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepdoctection/deepdoctection"}, {"content_hash": "5a5c104d2682be0f77ae0fda7d3677ba4d614a64ec1becb33ff5bd279dda6c90", "fetched_at": "2026-08-29T09:37:37.935693+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepdoctection/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.134299+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8236f9d9a7c0f1d5a047c1eb51fef0fd6f6042346f46f281950389b478f1a8f9", "fetched_at": "2026-08-28T04:07:51.830095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepdoctection/deepdoctection"}, {"content_hash": "5a5c104d2682be0f77ae0fda7d3677ba4d614a64ec1becb33ff5bd279dda6c90", "fetched_at": "2026-08-29T09:37:37.935693+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepdoctection/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.134299+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8236f9d9a7c0f1d5a047c1eb51fef0fd6f6042346f46f281950389b478f1a8f9", "fetched_at": "2026-08-28T04:07:51.830095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepdoctection/deepdoctection"}, {"content_hash": "5a5c104d2682be0f77ae0fda7d3677ba4d614a64ec1becb33ff5bd279dda6c90", "fetched_at": "2026-08-29T09:37:37.935693+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepdoctection/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.134299+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8236f9d9a7c0f1d5a047c1eb51fef0fd6f6042346f46f281950389b478f1a8f9", "fetched_at": "2026-08-28T04:07:51.830095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepdoctection/deepdoctection"}, {"content_hash": "5a5c104d2682be0f77ae0fda7d3677ba4d614a64ec1becb33ff5bd279dda6c90", "fetched_at": "2026-08-29T09:37:37.935693+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepdoctection/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:51.830095+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.134299+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8236f9d9a7c0f1d5a047c1eb51fef0fd6f6042346f46f281950389b478f1a8f9", "fetched_at": "2026-08-28T04:07:51.830095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepdoctection/deepdoctection"}, {"content_hash": "5a5c104d2682be0f77ae0fda7d3677ba4d614a64ec1becb33ff5bd279dda6c90", "fetched_at": "2026-08-29T09:37:37.935693+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepdoctection/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.134299+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8236f9d9a7c0f1d5a047c1eb51fef0fd6f6042346f46f281950389b478f1a8f9", "fetched_at": "2026-08-28T04:07:51.830095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepdoctection/deepdoctection"}, {"content_hash": "5a5c104d2682be0f77ae0fda7d3677ba4d614a64ec1becb33ff5bd279dda6c90", "fetched_at": "2026-08-29T09:37:37.935693+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepdoctection/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.134299+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8236f9d9a7c0f1d5a047c1eb51fef0fd6f6042346f46f281950389b478f1a8f9", "fetched_at": "2026-08-28T04:07:51.830095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepdoctection/deepdoctection"}, {"content_hash": "5a5c104d2682be0f77ae0fda7d3677ba4d614a64ec1becb33ff5bd279dda6c90", "fetched_at": "2026-08-29T09:37:37.935693+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepdoctection/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.134299+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8236f9d9a7c0f1d5a047c1eb51fef0fd6f6042346f46f281950389b478f1a8f9", "fetched_at": "2026-08-28T04:07:51.830095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepdoctection/deepdoctection"}, {"content_hash": "5a5c104d2682be0f77ae0fda7d3677ba4d614a64ec1becb33ff5bd279dda6c90", "fetched_at": "2026-08-29T09:37:37.935693+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepdoctection/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 100, "rhythm": 98}, "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": 1728, "days_push": 17, "days_rel": 17, "gap_med": 7, "n_releases_24m": 58}, "score": 98, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}