{"adoption": {"forks": 1236, "observed_at": "2026-08-28T04:10:51.908902+00:00", "stars": 12171}, "canonical_url": "https://ross.abutalabs.com/products/chandra", "card": {"archived": false, "artifact_type": "library", "description": "OCR model that handles complex tables, forms, handwriting with full layout.", "domain": ["artificial-intelligence", "computer-vision", "pdf"], "enriched": true, "function": ["ocr", "machine-learning", "pdf", "nlp"], "health_score": 92, "homepage": "https://www.datalab.to", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["datalab-to/chandra"], "name": "datalab-to/chandra", "platform": ["python", "cli"], "pushed_at": "2026-06-26T10:26:47+00:00", "repo": "datalab-to/chandra", "stars": 12171, "tags": ["document-intelligence", "layout-preservation", "handwriting-recognition", "table-extraction", "multilingual", "vllm", "markdown-conversion", "natural-language-processing", "gpu", "docker"], "topics": ["ai", "ocr"], "urls": [], "use_cases": ["convert scanned pdfs to markdown", "extract tables from document images", "transcribe handwritten notes", "digitize forms with checkboxes", "ocr documents in multiple languages", "convert documents to structured  with layout", "extract math equations from images"], "what_it_is": "Chandra OCR 2 is a state-of-the-art open-weight OCR model from Datalab that converts images and PDFs into structured HTML, Markdown, or JSON while preserving full layout information. It supports 90+ languages and excels at complex tables, forms, math, and handwriting, with local (HuggingFace) and remote (vLLM server) inference modes.", "when_to_avoid": ["you need only plain text extraction from simple documents", "commercial self-hosting without licensing arrangements", "you lack GPU resources for local inference and don't want a remote API"], "when_to_choose": ["you need layout-aware OCR output in HTML/Markdown/JSON", "documents contain complex tables, forms, math, or handwriting", "you need multilingual OCR across 90+ languages", "you want to self-host an open-weight OCR model with vLLM"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/chandra", "repo": "datalab-to/chandra", "role": "main", "score": 71}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:14:52.755030+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db05f20a20674638824c01f7c5dde6a8923605aab0873c783b83420a9b7efd24", "fetched_at": "2026-08-28T04:10:51.908902+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/chandra"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T08:12:00.014835+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:14:52.755030+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db05f20a20674638824c01f7c5dde6a8923605aab0873c783b83420a9b7efd24", "fetched_at": "2026-08-28T04:10:51.908902+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/chandra"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T08:12:00.014835+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": "2026-08-29T17:14:52.755030+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db05f20a20674638824c01f7c5dde6a8923605aab0873c783b83420a9b7efd24", "fetched_at": "2026-08-28T04:10:51.908902+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/chandra"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T08:12:00.014835+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": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:14:52.755030+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db05f20a20674638824c01f7c5dde6a8923605aab0873c783b83420a9b7efd24", "fetched_at": "2026-08-28T04:10:51.908902+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/chandra"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T08:12:00.014835+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:14:52.755030+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db05f20a20674638824c01f7c5dde6a8923605aab0873c783b83420a9b7efd24", "fetched_at": "2026-08-28T04:10:51.908902+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/chandra"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T08:12:00.014835+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:14:52.755030+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db05f20a20674638824c01f7c5dde6a8923605aab0873c783b83420a9b7efd24", "fetched_at": "2026-08-28T04:10:51.908902+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/chandra"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T08:12:00.014835+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:51.908902+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:14:52.755030+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db05f20a20674638824c01f7c5dde6a8923605aab0873c783b83420a9b7efd24", "fetched_at": "2026-08-28T04:10:51.908902+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/chandra"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T08:12:00.014835+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:14:52.755030+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db05f20a20674638824c01f7c5dde6a8923605aab0873c783b83420a9b7efd24", "fetched_at": "2026-08-28T04:10:51.908902+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/chandra"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T08:12:00.014835+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:14:52.755030+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db05f20a20674638824c01f7c5dde6a8923605aab0873c783b83420a9b7efd24", "fetched_at": "2026-08-28T04:10:51.908902+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/chandra"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T08:12:00.014835+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:14:52.755030+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db05f20a20674638824c01f7c5dde6a8923605aab0873c783b83420a9b7efd24", "fetched_at": "2026-08-28T04:10:51.908902+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datalab-to/chandra"}, {"content_hash": "2bbd3c9c83e2e88f31e8119b77b73d5cf9114357cc7e7fc3c7c9b4e95dfda551", "fetched_at": "2026-08-29T08:12:00.014835+00:00", "kind": "homepage", "missing": false, "url": "https://www.datalab.to"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 89, "longevity": 23, "rhythm": 75}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 329, "days_push": 68, "days_rel": 168, "gap_med": 0, "n_releases_24m": 8}, "score": 71, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}