unstructured
✅ 近期有维护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.
15,665Stars
1,379Forks
+43近 7 天 Star
HTML · Apache-2.0 · 最近推送 2026-11-02
官方仓库与安装文档 ↗Star 历史
2025-09-292026-11-02
查看历史数据
| 日期 | Stars |
|---|---|
| 2026-10-04 | 15,507 |
| 2026-10-05 | 15,511 |
| 2026-10-06 | 15,515 |
| 2026-10-07 | 15,526 |
| 2026-10-08 | 15,530 |
| 2026-10-09 | 15,537 |
| 2026-10-10 | 15,538 |
| 2026-10-11 | 15,538 |
| 2026-10-12 | 15,541 |
| 2026-10-13 | 15,547 |
| 2026-10-14 | 15,551 |
| 2026-10-15 | 15,555 |
| 2026-10-16 | 15,558 |
| 2026-10-17 | 15,559 |
| 2026-10-18 | 15,563 |
| 2026-10-19 | 15,568 |
| 2026-10-20 | 15,574 |
| 2026-10-21 | 15,580 |
| 2026-10-22 | 15,586 |
| 2026-10-23 | 15,601 |
| 2026-10-24 | 15,612 |
| 2026-10-25 | 15,621 |
| 2026-10-26 | 15,625 |
| 2026-10-27 | 15,628 |
| 2026-10-28 | 15,633 |
| 2026-10-29 | 15,636 |
| 2026-10-30 | 15,646 |
| 2026-10-31 | 15,653 |
| 2026-11-01 | 15,657 |
| 2026-11-02 | 15,665 |
获取项目
git clone https://github.com/Unstructured-IO/unstructured.git
相关项目与平替候选
同领域不等于功能完全相同,选型前请核对官方文档和许可证。
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports
★ 92,095paperless-ngxA community-supported supercharged document manage… 开源技术工具。
★ 47,529recommendersBest Practices on Recommendation Systems
★ 21,974