{"adoption": {"forks": 1533, "observed_at": "2026-08-28T04:11:31.583882+00:00", "stars": 21318}, "canonical_url": "https://ross.abutalabs.com/products/surya", "card": {"archived": false, "artifact_type": "library", "description": "OCR, layout analysis, reading order, table recognition in 90+ languages", "domain": ["computer-vision", "pdf", "machine-learning", "files"], "enriched": true, "function": ["ocr", "image-processing", "machine-learning", "deep-learning", "pdf"], "health_score": 99, "homepage": "https://www.datalab.to", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["datalab-to/surya"], "name": "datalab-to/surya", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-21T10:00:59+00:00", "repo": "datalab-to/surya", "stars": 21318, "tags": ["document-intelligence", "layout-analysis", "table-recognition", "reading-order", "multilingual", "text-detection", "natural-language-processing", "gpu"], "topics": [], "urls": [], "use_cases": ["extract text from scanned pdfs", "ocr documents in multiple languages", "detect layout regions and reading order in documents", "recognize tables from images", "convert scanned documents to markdown", "run ocr on gpu at high throughput"], "what_it_is": "Surya is a 650M parameter OCR toolkit from Datalab providing state-of-the-art text recognition, layout analysis, reading order detection, and table recognition in 90+ languages. It ships as a Python library with GPU acceleration and is part of Datalab's document intelligence model suite.", "when_to_avoid": ["you only need simple English-only ocr with a lightweight dependency", "you have no gpu and need very fast batch processing", "you need a fully managed api without running models yourself", "your models must be under a permissive license without usage restrictions (weights use OpenRAIL-M)"], "when_to_choose": ["you need multilingual ocr across 90+ languages", "you need layout analysis and table recognition alongside text extraction", "you want a self-hosted, Apache-2.0 licensed ocr pipeline with gpu speed", "you are building document processing or rag ingestion pipelines"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/surya", "repo": "datalab-to/surya", "role": "main", "score": 86}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:58:24.914009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "69b053d2917ab2d001a9737b7d051bfcfcd23a896750ac5b6d784e21a1ba88d7", "fetched_at": "2026-08-28T04:11:31.583882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/surya"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:56:49.830598+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:58:24.914009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "69b053d2917ab2d001a9737b7d051bfcfcd23a896750ac5b6d784e21a1ba88d7", "fetched_at": "2026-08-28T04:11:31.583882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/surya"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:56:49.830598+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:58:24.914009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "69b053d2917ab2d001a9737b7d051bfcfcd23a896750ac5b6d784e21a1ba88d7", "fetched_at": "2026-08-28T04:11:31.583882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/surya"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:56:49.830598+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:58:24.914009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "69b053d2917ab2d001a9737b7d051bfcfcd23a896750ac5b6d784e21a1ba88d7", "fetched_at": "2026-08-28T04:11:31.583882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/surya"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:56:49.830598+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:58:24.914009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "69b053d2917ab2d001a9737b7d051bfcfcd23a896750ac5b6d784e21a1ba88d7", "fetched_at": "2026-08-28T04:11:31.583882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/surya"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:56:49.830598+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:58:24.914009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "69b053d2917ab2d001a9737b7d051bfcfcd23a896750ac5b6d784e21a1ba88d7", "fetched_at": "2026-08-28T04:11:31.583882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/surya"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:56:49.830598+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:31.583882+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:58:24.914009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "69b053d2917ab2d001a9737b7d051bfcfcd23a896750ac5b6d784e21a1ba88d7", "fetched_at": "2026-08-28T04:11:31.583882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/surya"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:56:49.830598+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:58:24.914009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "69b053d2917ab2d001a9737b7d051bfcfcd23a896750ac5b6d784e21a1ba88d7", "fetched_at": "2026-08-28T04:11:31.583882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/surya"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:56:49.830598+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:58:24.914009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "69b053d2917ab2d001a9737b7d051bfcfcd23a896750ac5b6d784e21a1ba88d7", "fetched_at": "2026-08-28T04:11:31.583882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/surya"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:56:49.830598+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:58:24.914009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "69b053d2917ab2d001a9737b7d051bfcfcd23a896750ac5b6d784e21a1ba88d7", "fetched_at": "2026-08-28T04:11:31.583882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/surya"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T07:56:49.830598+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 69, "rhythm": 81}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 966, "days_push": 12, "days_rel": 44, "gap_med": 3, "n_releases_24m": 62}, "score": 86, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}