Champ-X/MMA-RAG
KB-aware multimodal RAG: hybrid dense/sparse/visual retrieval and citation-grounded answers, self-hosted.
This project helps anyone who needs to quickly find specific information from a vast collection of documents, images, audio, and video files. It takes your various media files as input and provides precise, citable answers to your questions, showing you exactly where the information came from. It's designed for professionals like researchers, analysts, or anyone managing large, diverse knowledge bases.
Use this if you need to build a self-hosted knowledge base that can answer complex questions by drawing information from text, images, audio, and video, providing clear citations for its answers.
Not ideal if you only deal with simple text documents or prefer a cloud-based, managed service rather than a self-hosted solution.
Stars
10
Forks
—
Language
Python
License
—
Category
Last pushed
Apr 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Champ-X/MMA-RAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
trustgraph-ai/trustgraph
The context development platform. Store, enrich, and retrieve structured knowledge with...
vectorlessflow/vectorless
Vectorless is a hierarchical, reasoning-native document intelligence engine. 🌟 Star if you like it!
gabonavarroo/faultmap
Automatically discover where and why your LLM is failing — embedding-space clustering +...
Madhan230205/token-reducer
⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude...
hericlesferraz/DocVault
Intelligent Document RAG with citation extraction. Upload PDFs, DOCX, PPTX or images, ask...