{"slug":"olmocr","name":"olmocr","category":"rag-docs","categoryName":"Document parsing & web scraping","audience":["for-ai"],"primary":"for-ai","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"stale","officialUrl":"https://github.com/allenai/olmocr","repo":"https://github.com/allenai/olmocr","latestVersion":"v0.4.27","latestRelease":"2026-03-12","stars":19794,"starsAsOf":"2026-10-22","description":"Toolkit for linearizing PDFs for LLM datasets/training","descriptionZh":"用 VLM 做 PDF 线性化 OCR","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":[],"language":"Python","lastPush":"2026-03-25","formerly":null,"packages":[{"registry":"pypi","name":"olmocr","url":"https://pypi.org/project/olmocr/","versionsUrl":"https://pypi.org/project/olmocr/#history","latestVersion":"0.4.27","latestDate":"2026-03-12"}],"recentVersions":[{"version":"v0.4.27","date":"2026-03-12","prerelease":false,"url":"https://github.com/allenai/olmocr/releases/tag/v0.4.27","source":"GitHub Release"},{"version":"v0.4.25","date":"2026-01-25","prerelease":false,"url":"https://github.com/allenai/olmocr/releases/tag/v0.4.25","source":"GitHub Release"},{"version":"v0.4.24","date":"2026-01-23","prerelease":false,"url":"https://github.com/allenai/olmocr/releases/tag/v0.4.24","source":"GitHub Release"},{"version":"v0.4.23","date":"2026-01-23","prerelease":false,"url":"https://github.com/allenai/olmocr/releases/tag/v0.4.23","source":"GitHub Release"},{"version":"v0.4.22","date":"2026-01-23","prerelease":false,"url":"https://github.com/allenai/olmocr/releases/tag/v0.4.22","source":"GitHub Release"}],"alternatives":["firecrawl","markitdown","ragflow","paddleocr","crawl4ai","mineru","docling","pandoc"],"stacks":[],"scenarios":["rag-and-documents"],"problems":[],"reasonZh":"PDF OCR","sources":["priority","oss","github-pool"],"record":"https://aimap.page/api/v1/software/olmocr.json","pages":{"en":"https://aimap.page/en/software/olmocr/","zh-hans":"https://aimap.page/zh-hans/software/olmocr/"}}