{"adoption": {"forks": 11237, "observed_at": "2026-08-28T04:12:23.085696+00:00", "stars": 88312}, "canonical_url": "https://ross.abutalabs.com/products/paddleocr", "card": {"archived": false, "artifact_type": "library", "description": "Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.", "domain": ["computer-vision", "pdf", "artificial-intelligence"], "enriched": true, "function": ["ocr", "pdf", "machine-learning", "rag", "nlp", "image-processing"], "health_score": 95, "homepage": "https://www.paddleocr.com", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["PaddlePaddle/PaddleOCR"], "name": "PaddlePaddle/PaddleOCR", "platform": ["python", "windows", "cross-platform"], "pushed_at": "2026-07-22T11:59:34+00:00", "repo": "PaddlePaddle/PaddleOCR", "stars": 88312, "tags": ["document-parsing", "text-recognition", "text-detection", "multilingual", "paddlepaddle", "pdf-to-markdown", "key-information-extraction", "document-ai", "natural-language-processing", "retrieval-augmented-generation", "linux", "macos", "gpu"], "topics": ["ocr", "chineseocr", "pdf2markdown", "pp-ocr", "pp-structure", "document-parsing", "document-translation", "kie", "ai4science", "pdf-extractor-rag", "pdf-parser", "rag", "paddleocr-vl"], "urls": [], "use_cases": ["extract text from images and scanned pdfs", "convert pdf documents to markdown for llm ingestion", "build a rag pipeline over document collections", "recognize chinese and other multilingual text in photos", "parse invoices and forms to extract key fields", "ocr tables and document layout into structured data"], "what_it_is": "PaddleOCR is a multilingual OCR and document parsing toolkit built on PaddlePaddle that converts images and PDFs into structured data like Markdown. It supports 100+ languages, text detection/recognition, layout analysis, and key information extraction, and is designed to feed documents into LLM and RAG pipelines.", "when_to_avoid": ["you need a lightweight pure-inference solution without a deep learning framework dependency", "your project is built on pytorch or tensorflow and you don't want paddlepaddle", "you only need simple tesseract-level ocr without document structure parsing"], "when_to_choose": ["you need high-accuracy multilingual ocr, especially for chinese text", "you want to turn pdfs or images into structured input for llms or rag", "you need document parsing with layout, table, and key-information extraction", "you want a mature, actively maintained toolkit with cpu and gpu support"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/paddleocr", "repo": "PaddlePaddle/PaddleOCR", "role": "main", "score": 93}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:13:52.999194+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e37865b4d7d5e8513dcb21771511809dfc6dd5bdb05889d2d3703c2b52dfec62", "fetched_at": "2026-08-28T04:12:23.085696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PaddlePaddle/PaddleOCR"}, {"content_hash": "e962d88d556886b0f50c7a8eaedea2819cb76e33b9f98b3769a2c4203946df72", "fetched_at": "2026-08-28T17:38:44.604727+00:00", "kind": "homepage", "missing": false, "url": "https://www.paddleocr.com"}, {"content_hash": "405135b3572da49d3bc88f1c95f13b9294fafb9df4aaba675ac256a06a614fe2", "fetched_at": "2026-08-28T17:38:44.613238+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/paddleocr/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:13:52.999194+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e37865b4d7d5e8513dcb21771511809dfc6dd5bdb05889d2d3703c2b52dfec62", "fetched_at": "2026-08-28T04:12:23.085696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PaddlePaddle/PaddleOCR"}, {"content_hash": "e962d88d556886b0f50c7a8eaedea2819cb76e33b9f98b3769a2c4203946df72", "fetched_at": "2026-08-28T17:38:44.604727+00:00", "kind": "homepage", "missing": false, "url": "https://www.paddleocr.com"}, {"content_hash": "405135b3572da49d3bc88f1c95f13b9294fafb9df4aaba675ac256a06a614fe2", "fetched_at": "2026-08-28T17:38:44.613238+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/paddleocr/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:13:52.999194+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e37865b4d7d5e8513dcb21771511809dfc6dd5bdb05889d2d3703c2b52dfec62", "fetched_at": "2026-08-28T04:12:23.085696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PaddlePaddle/PaddleOCR"}, {"content_hash": "e962d88d556886b0f50c7a8eaedea2819cb76e33b9f98b3769a2c4203946df72", "fetched_at": "2026-08-28T17:38:44.604727+00:00", "kind": "homepage", "missing": false, "url": "https://www.paddleocr.com"}, {"content_hash": "405135b3572da49d3bc88f1c95f13b9294fafb9df4aaba675ac256a06a614fe2", "fetched_at": "2026-08-28T17:38:44.613238+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/paddleocr/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:13:52.999194+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e37865b4d7d5e8513dcb21771511809dfc6dd5bdb05889d2d3703c2b52dfec62", "fetched_at": "2026-08-28T04:12:23.085696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PaddlePaddle/PaddleOCR"}, {"content_hash": "e962d88d556886b0f50c7a8eaedea2819cb76e33b9f98b3769a2c4203946df72", "fetched_at": "2026-08-28T17:38:44.604727+00:00", "kind": "homepage", "missing": false, "url": "https://www.paddleocr.com"}, {"content_hash": "405135b3572da49d3bc88f1c95f13b9294fafb9df4aaba675ac256a06a614fe2", "fetched_at": "2026-08-28T17:38:44.613238+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/paddleocr/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:13:52.999194+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e37865b4d7d5e8513dcb21771511809dfc6dd5bdb05889d2d3703c2b52dfec62", "fetched_at": "2026-08-28T04:12:23.085696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PaddlePaddle/PaddleOCR"}, {"content_hash": "e962d88d556886b0f50c7a8eaedea2819cb76e33b9f98b3769a2c4203946df72", "fetched_at": "2026-08-28T17:38:44.604727+00:00", "kind": "homepage", "missing": false, "url": "https://www.paddleocr.com"}, {"content_hash": "405135b3572da49d3bc88f1c95f13b9294fafb9df4aaba675ac256a06a614fe2", "fetched_at": "2026-08-28T17:38:44.613238+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/paddleocr/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:13:52.999194+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e37865b4d7d5e8513dcb21771511809dfc6dd5bdb05889d2d3703c2b52dfec62", "fetched_at": "2026-08-28T04:12:23.085696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PaddlePaddle/PaddleOCR"}, {"content_hash": "e962d88d556886b0f50c7a8eaedea2819cb76e33b9f98b3769a2c4203946df72", "fetched_at": "2026-08-28T17:38:44.604727+00:00", "kind": "homepage", "missing": false, "url": "https://www.paddleocr.com"}, {"content_hash": "405135b3572da49d3bc88f1c95f13b9294fafb9df4aaba675ac256a06a614fe2", "fetched_at": "2026-08-28T17:38:44.613238+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/paddleocr/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:23.085696+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:13:52.999194+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e37865b4d7d5e8513dcb21771511809dfc6dd5bdb05889d2d3703c2b52dfec62", "fetched_at": "2026-08-28T04:12:23.085696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PaddlePaddle/PaddleOCR"}, {"content_hash": "e962d88d556886b0f50c7a8eaedea2819cb76e33b9f98b3769a2c4203946df72", "fetched_at": "2026-08-28T17:38:44.604727+00:00", "kind": "homepage", "missing": false, "url": "https://www.paddleocr.com"}, {"content_hash": "405135b3572da49d3bc88f1c95f13b9294fafb9df4aaba675ac256a06a614fe2", "fetched_at": "2026-08-28T17:38:44.613238+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/paddleocr/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:13:52.999194+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e37865b4d7d5e8513dcb21771511809dfc6dd5bdb05889d2d3703c2b52dfec62", "fetched_at": "2026-08-28T04:12:23.085696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PaddlePaddle/PaddleOCR"}, {"content_hash": "e962d88d556886b0f50c7a8eaedea2819cb76e33b9f98b3769a2c4203946df72", "fetched_at": "2026-08-28T17:38:44.604727+00:00", "kind": "homepage", "missing": false, "url": "https://www.paddleocr.com"}, {"content_hash": "405135b3572da49d3bc88f1c95f13b9294fafb9df4aaba675ac256a06a614fe2", "fetched_at": "2026-08-28T17:38:44.613238+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/paddleocr/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:13:52.999194+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e37865b4d7d5e8513dcb21771511809dfc6dd5bdb05889d2d3703c2b52dfec62", "fetched_at": "2026-08-28T04:12:23.085696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PaddlePaddle/PaddleOCR"}, {"content_hash": "e962d88d556886b0f50c7a8eaedea2819cb76e33b9f98b3769a2c4203946df72", "fetched_at": "2026-08-28T17:38:44.604727+00:00", "kind": "homepage", "missing": false, "url": "https://www.paddleocr.com"}, {"content_hash": "405135b3572da49d3bc88f1c95f13b9294fafb9df4aaba675ac256a06a614fe2", "fetched_at": "2026-08-28T17:38:44.613238+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/paddleocr/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:13:52.999194+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e37865b4d7d5e8513dcb21771511809dfc6dd5bdb05889d2d3703c2b52dfec62", "fetched_at": "2026-08-28T04:12:23.085696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PaddlePaddle/PaddleOCR"}, {"content_hash": "e962d88d556886b0f50c7a8eaedea2819cb76e33b9f98b3769a2c4203946df72", "fetched_at": "2026-08-28T17:38:44.604727+00:00", "kind": "homepage", "missing": false, "url": "https://www.paddleocr.com"}, {"content_hash": "405135b3572da49d3bc88f1c95f13b9294fafb9df4aaba675ac256a06a614fe2", "fetched_at": "2026-08-28T17:38:44.613238+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/paddleocr/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 93, "longevity": 100, "rhythm": 88}, "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": 2308, "days_push": 42, "days_rel": 83, "gap_med": 14.5, "n_releases_24m": 19}, "score": 93, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}