wgcyeo/UniversalRAG

UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities

37
/ 100
Emerging

This framework helps AI developers build advanced Retrieval-Augmented Generation (RAG) systems capable of searching across various data types like text, images, and videos. It takes diverse data corpora and user queries, then intelligently directs each query to the most relevant data source, providing a more accurate and nuanced context for generative AI models. AI researchers and machine learning engineers who are building next-generation AI applications will find this valuable.

161 stars. No commits in the last 6 months.

Use this if you are building an RAG system and need to accurately retrieve information from a complex mix of text, images, and videos to provide context for a large language model.

Not ideal if you are a business user looking for a no-code solution or only dealing with simple text-based data for your RAG applications.

AI development Multimodal AI Generative AI Information Retrieval Machine Learning Engineering
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 10 / 25

How are scores calculated?

Stars

161

Forks

10

Language

Python

License

Apache-2.0

Last pushed

May 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/wgcyeo/UniversalRAG"

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