SnowNation101/Nyx

Code for the paper “Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation”

27
/ 100
Experimental

This project offers a unified mixed-modal retriever for researchers and developers working on Retrieval-Augmented Generation (RAG) systems. It helps create systems that can accurately answer questions using both text and images. You provide a query and a collection of text and images, and it retrieves the most relevant information to generate a comprehensive answer.

Use this if you are a machine learning researcher or engineer developing advanced RAG models that need to process and respond to queries based on both textual and visual information.

Not ideal if you are a non-technical end-user looking for a ready-to-use application or a developer working with only text-based RAG systems.

multimodal-AI retrieval-augmented-generation natural-language-processing computer-vision question-answering-systems
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Python

License

MIT

Last pushed

Dec 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/SnowNation101/Nyx"

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