{"id":60514226,"uuid":"541798154","full_name":"Unstructured-IO/unstructured","owner":"Unstructured-IO","description":"Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models.  Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.","archived":false,"fork":false,"pushed_at":"2026-10-24T18:48:06.000Z","size":237690,"stargazers_count":15616,"open_issues_count":330,"forks_count":1369,"subscribers_count":75,"default_branch":"main","last_synced_at":"2026-10-25T05:19:34.961Z","etag":null,"topics":["data-pipelines","deep-learning","document-image-analysis","document-image-processing","document-parser","document-parsing","docx","donut","information-retrieval","langchain","llm","machine-learning","ml","natural-language-processing","nlp","ocr","pdf","pdf-to-json","pdf-to-text","preprocessing"],"latest_commit_sha":null,"homepage":"https://www.unstructured.io/","language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Unstructured-IO.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"claude":null,"gemini":null,"cursor":null,"copilot":null,"dco":null,"cla":null,"disclosure":null}},"created_at":"2022-09-26T21:53:41.000Z","updated_at":"2026-10-25T04:47:17.000Z","dependencies_parsed_at":"2026-09-05T06:41:08.362Z","dependency_job_id":"3456d516-d98c-42b9-b3f2-260f29680286","html_url":"https://github.com/Unstructured-IO/unstructured","commit_stats":{"total_commits":1621,"total_committers":116,"mean_commits":"13.974137931034482","dds":0.8402220851326342,"last_synced_commit":"626f73af5b584866dfecf8b102c24c63334568de"},"previous_names":[],"tags_count":250,"template":false,"template_full_name":null,"purl":"pkg:github/Unstructured-IO/unstructured","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unstructured-IO%2Funstructured","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unstructured-IO%2Funstructured/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unstructured-IO%2Funstructured/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unstructured-IO%2Funstructured/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Unstructured-IO","download_url":"https://codeload.github.com/Unstructured-IO/unstructured/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unstructured-IO%2Funstructured/sbom","scorecard":null,"funding_links":[],"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":345237552,"owners_count":38525373,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-10-03T21:59:58.778Z","status":"online","status_checked_at":"2026-10-25T02:00:07.705Z","response_time":58,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}}