{"adoption": {"forks": 2543, "observed_at": "2026-08-28T04:11:37.172142+00:00", "stars": 24569}, "canonical_url": "https://ross.abutalabs.com/products/unlimited-ocr", "card": {"archived": false, "artifact_type": "library", "description": "Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.", "domain": ["computer-vision", "deep-learning", "pdf"], "enriched": true, "function": ["ocr", "machine-learning", "llm-inference", "pdf"], "health_score": 77, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["baidu/Unlimited-OCR"], "name": "baidu/Unlimited-OCR", "platform": ["python"], "pushed_at": "2026-07-29T04:37:03+00:00", "repo": "baidu/Unlimited-OCR", "stars": 24569, "tags": ["vision-language-model", "document-parsing", "long-context", "huggingface", "vllm", "natural-language-processing", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["extract text from long pdf documents", "parse scanned documents with a vision-language model", "run ocr on gpu with vllm", "convert document images to structured text", "batch document parsing for rag pipelines"], "what_it_is": "Baidu's Unlimited-OCR is an open vision-language OCR model for one-shot long-horizon document parsing, extending DeepSeek-OCR. It provides inference via Hugging Face Transformers and vLLM on NVIDIA GPUs, with weights on Hugging Face and ModelScope.", "when_to_avoid": ["you need lightweight cpu-only ocr like tesseract", "you need a hosted ocr api without gpu infrastructure", "you need handwriting or niche-language recognition without evaluation"], "when_to_choose": ["you need ocr over very long or multi-page documents in one pass", "you want an open model deployable with transformers or vllm", "you need document parsing as input for downstream llm workflows"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/unlimited-ocr", "repo": "baidu/Unlimited-OCR", "role": "main", "score": 56}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:56:12.105119+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5f77b9450d4965dfb9f0e82aa9a019c7f9776e97e4be5631ff7d503764535868", "fetched_at": "2026-08-28T04:11:37.172142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/baidu/Unlimited-OCR"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:56:12.105119+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5f77b9450d4965dfb9f0e82aa9a019c7f9776e97e4be5631ff7d503764535868", "fetched_at": "2026-08-28T04:11:37.172142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/baidu/Unlimited-OCR"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:56:12.105119+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5f77b9450d4965dfb9f0e82aa9a019c7f9776e97e4be5631ff7d503764535868", "fetched_at": "2026-08-28T04:11:37.172142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/baidu/Unlimited-OCR"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:56:12.105119+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5f77b9450d4965dfb9f0e82aa9a019c7f9776e97e4be5631ff7d503764535868", "fetched_at": "2026-08-28T04:11:37.172142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/baidu/Unlimited-OCR"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:56:12.105119+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5f77b9450d4965dfb9f0e82aa9a019c7f9776e97e4be5631ff7d503764535868", "fetched_at": "2026-08-28T04:11:37.172142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/baidu/Unlimited-OCR"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:56:12.105119+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5f77b9450d4965dfb9f0e82aa9a019c7f9776e97e4be5631ff7d503764535868", "fetched_at": "2026-08-28T04:11:37.172142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/baidu/Unlimited-OCR"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:37.172142+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:56:12.105119+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5f77b9450d4965dfb9f0e82aa9a019c7f9776e97e4be5631ff7d503764535868", "fetched_at": "2026-08-28T04:11:37.172142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/baidu/Unlimited-OCR"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:56:12.105119+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5f77b9450d4965dfb9f0e82aa9a019c7f9776e97e4be5631ff7d503764535868", "fetched_at": "2026-08-28T04:11:37.172142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/baidu/Unlimited-OCR"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:56:12.105119+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5f77b9450d4965dfb9f0e82aa9a019c7f9776e97e4be5631ff7d503764535868", "fetched_at": "2026-08-28T04:11:37.172142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/baidu/Unlimited-OCR"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:56:12.105119+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5f77b9450d4965dfb9f0e82aa9a019c7f9776e97e4be5631ff7d503764535868", "fetched_at": "2026-08-28T04:11:37.172142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/baidu/Unlimited-OCR"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 95, "longevity": 5, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 76, "days_push": 35, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 56, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}