HKUDS/RAG-Anything

"RAG-Anything: All-in-One RAG Framework"

66
/ 100
Established

Effectively process and query complex documents that contain not just text, but also images, tables, and mathematical equations. This system takes your mixed-content documents, like research papers or financial reports, and allows you to ask questions across all their elements, providing comprehensive answers. It's designed for professionals who work with rich, mixed-media content and need to extract insights from all modalities.

14,187 stars. Actively maintained with 21 commits in the last 30 days.

Use this if you need to thoroughly analyze and query documents that integrate text with visual diagrams, structured data in tables, or mathematical formulas.

Not ideal if your documents are exclusively text-based or if you only need to process simple, single-modality content.

academic-research technical-documentation financial-analysis enterprise-knowledge-management data-extraction
No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 21 / 25

How are scores calculated?

Stars

14,187

Forks

1,691

Language

Python

License

MIT

Last pushed

Mar 13, 2026

Commits (30d)

21

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/HKUDS/RAG-Anything"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.