HKUDS/RAG-Anything
"RAG-Anything: All-in-One RAG Framework"
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.
Stars
14,187
Forks
1,691
Language
Python
License
MIT
Category
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.
Recent Releases
Related tools
HKUDS/LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
beir-cellar/beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across...
superlinear-ai/raglite
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
illuin-tech/vidore-benchmark
Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.
DataScienceUIBK/Rankify
🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented...