Unstructured-IO/unstructured

unstructured

✅ Recently maintained

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
+437-day stars

HTML · Apache-2.0 · Last push 2026-11-02

Official repository & installation ↗
deep-learningdocument-parsingmachine-learningnlpocrinformation-retrievaldata-pipelinesmlpreprocessingpdf-to-text

Star history

2025-09-292026-11-02
View historical data
DateStars
2026-10-0415,507
2026-10-0515,511
2026-10-0615,515
2026-10-0715,526
2026-10-0815,530
2026-10-0915,537
2026-10-1015,538
2026-10-1115,538
2026-10-1215,541
2026-10-1315,547
2026-10-1415,551
2026-10-1515,555
2026-10-1615,558
2026-10-1715,559
2026-10-1815,563
2026-10-1915,568
2026-10-2015,574
2026-10-2115,580
2026-10-2215,586
2026-10-2315,601
2026-10-2415,612
2026-10-2515,621
2026-10-2615,625
2026-10-2715,628
2026-10-2815,633
2026-10-2915,636
2026-10-3015,646
2026-10-3115,653
2026-11-0115,657
2026-11-0215,665

Get the project

git clone https://github.com/Unstructured-IO/unstructured.git

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

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-ngx

A community-supported supercharged document management system: scan, index and archive all your documents

★ 47,529recommenders

Best Practices on Recommendation Systems

★ 21,974