{"adoption": {"forks": 673, "observed_at": "2026-08-28T04:09:41.710923+00:00", "stars": 6315}, "canonical_url": "https://ross.abutalabs.com/products/doctr", "card": {"archived": false, "artifact_type": "library", "description": "docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.", "domain": ["computer-vision", "image-processing", "deep-learning", "machine-learning"], "enriched": true, "function": ["ocr", "computer-vision", "deep-learning", "machine-learning", "image-processing"], "health_score": 99, "homepage": "https://mindee.github.io/doctr/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["mindee/doctr"], "name": "mindee/doctr", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-21T14:16:15+00:00", "repo": "mindee/doctr", "stars": 6315, "tags": ["text-detection", "text-recognition", "pytorch", "tensorflow", "document-parsing", "layout-analysis", "pretrained-models", "natural-language-processing", "gpu", "docker"], "topics": ["ocr", "deep-learning", "document-recognition", "tensorflow2", "text-detection-recognition", "text-detection", "text-recognition", "optical-character-recognition", "pytorch"], "urls": [], "use_cases": ["extract text from scanned documents", "run ocr on pdfs and images in python", "localize and recognize words in document images", "detect tables and layout regions in documents", "benchmark my own text recognition model against state-of-the-art ocr", "deploy an ocr api service", "convert receipts or invoices to text"], "what_it_is": "docTR is a Python OCR library that extracts text from documents and images using a two-stage deep learning approach: text detection followed by text recognition. It offers pretrained models in PyTorch and TensorFlow, layout analysis, and a simple 3-line API for end-to-end text extraction.", "when_to_avoid": ["you need handwriting transcription or full-page document understanding beyond text/layout", "you want a turnkey GUI application rather than a Python library", "you need OCR for non-Latin scripts not covered by the model zoo", "you prefer a cloud OCR API with zero model management"], "when_to_choose": ["you need high-accuracy OCR comparable to cloud services like AWS Textract but self-hosted", "you want a choice of detection and recognition architectures with pretrained weights", "you need both CPU and GPU inference with a lightweight dependency footprint", "you want layout analysis (tables, figures, headers) alongside text extraction"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/doctr", "repo": "mindee/doctr", "role": "main", "score": 90}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:46:12.294598+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2a1225f6159024b4bfef65923cac51a83a16bfb6b66d1ed576c231b4a6b664bc", "fetched_at": "2026-08-28T04:09:41.710923+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mindee/doctr"}, {"content_hash": "7e3ffab1342ce11c66f682966f6ccee731fbae5971ec610d0cccde488ec21a3e", "fetched_at": "2026-08-29T08:42:37.541026+00:00", "kind": "homepage", "missing": false, "url": "https://mindee.github.io/doctr/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:46:12.294598+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2a1225f6159024b4bfef65923cac51a83a16bfb6b66d1ed576c231b4a6b664bc", "fetched_at": "2026-08-28T04:09:41.710923+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mindee/doctr"}, {"content_hash": "7e3ffab1342ce11c66f682966f6ccee731fbae5971ec610d0cccde488ec21a3e", "fetched_at": "2026-08-29T08:42:37.541026+00:00", "kind": "homepage", "missing": false, "url": "https://mindee.github.io/doctr/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:46:12.294598+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2a1225f6159024b4bfef65923cac51a83a16bfb6b66d1ed576c231b4a6b664bc", "fetched_at": "2026-08-28T04:09:41.710923+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mindee/doctr"}, {"content_hash": "7e3ffab1342ce11c66f682966f6ccee731fbae5971ec610d0cccde488ec21a3e", "fetched_at": "2026-08-29T08:42:37.541026+00:00", "kind": "homepage", "missing": false, "url": "https://mindee.github.io/doctr/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:46:12.294598+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2a1225f6159024b4bfef65923cac51a83a16bfb6b66d1ed576c231b4a6b664bc", "fetched_at": "2026-08-28T04:09:41.710923+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mindee/doctr"}, {"content_hash": "7e3ffab1342ce11c66f682966f6ccee731fbae5971ec610d0cccde488ec21a3e", "fetched_at": "2026-08-29T08:42:37.541026+00:00", "kind": "homepage", "missing": false, "url": "https://mindee.github.io/doctr/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:46:12.294598+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2a1225f6159024b4bfef65923cac51a83a16bfb6b66d1ed576c231b4a6b664bc", "fetched_at": "2026-08-28T04:09:41.710923+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mindee/doctr"}, {"content_hash": "7e3ffab1342ce11c66f682966f6ccee731fbae5971ec610d0cccde488ec21a3e", "fetched_at": "2026-08-29T08:42:37.541026+00:00", "kind": "homepage", "missing": false, "url": "https://mindee.github.io/doctr/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:46:12.294598+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2a1225f6159024b4bfef65923cac51a83a16bfb6b66d1ed576c231b4a6b664bc", "fetched_at": "2026-08-28T04:09:41.710923+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mindee/doctr"}, {"content_hash": "7e3ffab1342ce11c66f682966f6ccee731fbae5971ec610d0cccde488ec21a3e", "fetched_at": "2026-08-29T08:42:37.541026+00:00", "kind": "homepage", "missing": false, "url": "https://mindee.github.io/doctr/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.710923+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:46:12.294598+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2a1225f6159024b4bfef65923cac51a83a16bfb6b66d1ed576c231b4a6b664bc", "fetched_at": "2026-08-28T04:09:41.710923+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mindee/doctr"}, {"content_hash": "7e3ffab1342ce11c66f682966f6ccee731fbae5971ec610d0cccde488ec21a3e", "fetched_at": "2026-08-29T08:42:37.541026+00:00", "kind": "homepage", "missing": false, "url": "https://mindee.github.io/doctr/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:46:12.294598+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2a1225f6159024b4bfef65923cac51a83a16bfb6b66d1ed576c231b4a6b664bc", "fetched_at": "2026-08-28T04:09:41.710923+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mindee/doctr"}, {"content_hash": "7e3ffab1342ce11c66f682966f6ccee731fbae5971ec610d0cccde488ec21a3e", "fetched_at": "2026-08-29T08:42:37.541026+00:00", "kind": "homepage", "missing": false, "url": "https://mindee.github.io/doctr/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:46:12.294598+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2a1225f6159024b4bfef65923cac51a83a16bfb6b66d1ed576c231b4a6b664bc", "fetched_at": "2026-08-28T04:09:41.710923+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mindee/doctr"}, {"content_hash": "7e3ffab1342ce11c66f682966f6ccee731fbae5971ec610d0cccde488ec21a3e", "fetched_at": "2026-08-29T08:42:37.541026+00:00", "kind": "homepage", "missing": false, "url": "https://mindee.github.io/doctr/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:46:12.294598+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2a1225f6159024b4bfef65923cac51a83a16bfb6b66d1ed576c231b4a6b664bc", "fetched_at": "2026-08-28T04:09:41.710923+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mindee/doctr"}, {"content_hash": "7e3ffab1342ce11c66f682966f6ccee731fbae5971ec610d0cccde488ec21a3e", "fetched_at": "2026-08-29T08:42:37.541026+00:00", "kind": "homepage", "missing": false, "url": "https://mindee.github.io/doctr/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 100, "rhythm": 74}, "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": 2063, "days_push": 12, "days_rel": 12, "gap_med": 140, "n_releases_24m": 6}, "score": 90, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}