{"slug":"surya","name":"surya","category":"rag-docs","categoryName":"Document parsing & web scraping","audience":["for-ai"],"primary":"for-ai","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"yes","officialUrl":"https://www.datalab.to","repo":"https://github.com/datalab-to/surya","latestVersion":"v0.22.1","latestRelease":"2026-07-20","stars":21517,"starsAsOf":"2026-10-22","description":"OCR, layout analysis, reading order, table recognition in 90+ languages","descriptionZh":"多语种 OCR 与版面分析","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":[],"language":"Python","lastPush":"2026-09-11","formerly":null,"packages":[],"recentVersions":[{"version":"v0.22.1","date":"2026-07-20","prerelease":false,"url":"https://github.com/datalab-to/surya/releases/tag/v0.22.1","source":"GitHub Release"},{"version":"v0.22.0","date":"2026-07-17","prerelease":false,"url":"https://github.com/datalab-to/surya/releases/tag/v0.22.0","source":"GitHub Release"},{"version":"v0.21.2","date":"2026-07-15","prerelease":false,"url":"https://github.com/datalab-to/surya/releases/tag/v0.21.2","source":"GitHub Release"},{"version":"v0.21.1","date":"2026-07-08","prerelease":false,"url":"https://github.com/datalab-to/surya/releases/tag/v0.21.1","source":"GitHub Release"},{"version":"v0.21.0","date":"2026-07-08","prerelease":false,"url":"https://github.com/datalab-to/surya/releases/tag/v0.21.0","source":"GitHub Release"}],"alternatives":["firecrawl","markitdown","ragflow","paddleocr","crawl4ai","mineru","docling","pandoc"],"stacks":[],"scenarios":["rag-and-documents"],"problems":[],"reasonZh":"开源大库收录：多语种 OCR 与版面分析","sources":["oss","github-pool"],"record":"https://aimap.page/api/v1/software/surya.json","pages":{"en":"https://aimap.page/en/software/surya/","zh-hans":"https://aimap.page/zh-hans/software/surya/"}}