{"id":18400429,"url":"https://github.com/dataelement/bisheng-unstructured","last_synced_at":"2025-04-06T12:07:43.899Z","repository":{"id":192781886,"uuid":"678623154","full_name":"dataelement/bisheng-unstructured","owner":"dataelement","description":"bisheng-unstructured library","archived":false,"fork":false,"pushed_at":"2025-03-27T08:42:35.000Z","size":44360,"stargazers_count":42,"open_issues_count":1,"forks_count":18,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-03-30T11:06:32.395Z","etag":null,"topics":["etl4llms"],"latest_commit_sha":null,"homepage":"https://m7a7tqsztt.feishu.cn/wiki/CTXNwpqGKiMs5FkKlPJcylfonuD","language":"Python","has_issues":false,"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/dataelement.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"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}},"created_at":"2023-08-15T01:34:40.000Z","updated_at":"2025-02-25T01:34:52.000Z","dependencies_parsed_at":null,"dependency_job_id":"9609594f-85fc-4e51-b5d5-a66f6fe65b28","html_url":"https://github.com/dataelement/bisheng-unstructured","commit_stats":null,"previous_names":["dataelement/bisheng-unstructured"],"tags_count":21,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataelement%2Fbisheng-unstructured","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataelement%2Fbisheng-unstructured/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataelement%2Fbisheng-unstructured/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataelement%2Fbisheng-unstructured/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dataelement","download_url":"https://codeload.github.com/dataelement/bisheng-unstructured/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247478319,"owners_count":20945266,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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"}},"keywords":["etl4llms"],"created_at":"2024-11-06T02:33:07.919Z","updated_at":"2025-04-06T12:07:43.877Z","avatar_url":"https://github.com/dataelement.png","language":"Python","readme":"## What is bisheng-unstructured?\n\nBisheng-unstructured is an open-source unstructured data parsing library built to \npower LLM applications like pretrain, finetune, prompting engineering. \nBisheng-unstructured makes the unstructured data porcessing more easily and provides a consistent user experience regardless of any file types.\n\nThe project is a sub-project of [bisheng](https://github.com/dataelement/bisheng).\n\n## Key features\n\n- High precision pdf layout parser\n- High precision table structure recovering\n- High precision OCR ability\n- More friendly for token prossing for the visual text element, like table, list\n\n## Quick start\n\n### Start With Bisheng Platform\n\nUse as a chain node [ElemUnstructureLoader](https://m7a7tqsztt.feishu.cn/wiki/VpyNwTt7ZiypbdkoPuJcn5w2nxf)\n\n### Start with DataElem Services.\n\nWe provide a open cloud service for easily use. See [free trial](https://m7a7tqsztt.feishu.cn/wiki/CTXNwpqGKiMs5FkKlPJcylfonuD).\n\n### Install bisheng-unstructured\n\n- Install from pip: `pip install bisheng-unstructured`\n- [Quick Start Guide](https://m7a7tqsztt.feishu.cn/wiki/CTXNwpqGKiMs5FkKlPJcylfonuD)\n\n### Using from pre-builded image\n\n## Documentation\n\nFor guidance on installation, development, deployment, and administration, \ncheck out [bisheng-unstructured Docs](https://m7a7tqsztt.feishu.cn/wiki/CTXNwpqGKiMs5FkKlPJcylfonuD). \n\n## Issues\n\nReporting problems, asking questions\nWe appreciate any feedback, questions or bug reporting regarding this project. \n\nUser can posting [Issues](https://github.com/dataelement/bisheng/issues), \nfollow the process outlined in the [Stack Overflow document](https://stackoverflow.com/help/mcve). \n\nFor questions, we recommend posting in our community GitHub [Discussions](https://github.com/dataelement/bisheng/discussions).\n\n\n## Acknowledgments\n\nbisheng-unstructured adopts dependencies from the following:\n\n- Thanks to [unstructured](https://github.com/Unstructured-IO/unstructured) for the main framework.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdataelement%2Fbisheng-unstructured","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdataelement%2Fbisheng-unstructured","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdataelement%2Fbisheng-unstructured/lists"}