返回初创公司


Document AI
Unstructured
ETL and preprocessing infrastructure that turns complex documents into AI-ready data.
所在地
San Francisco, USA
成立年份
2022
创始人
Brian Raymond
浏览
10
GitHub forks
1,308
开放 Issues
295
开源许可
Apache-2.0
仓库最近更新
2026年8月24日
公司介绍
Unstructured provides open-source libraries and managed workflows for ingesting PDFs, office documents, images, HTML and many other formats. Its pipelines partition, clean, enrich and route document content so teams can build higher-quality retrieval and agent systems without maintaining a large collection of file-specific parsers. Public product claims can change; confirm current capabilities, deployment requirements, pricing and support with the vendor.
Open SourceData IngestionDocument Processing