adithya-s-k/VARAG
Vision-Augmented Retrieval and Generation (VARAG) - Vision first RAG Engine
This tool helps people who work with documents containing both text and images to quickly find precise information. You input documents like scanned PDFs, research papers, or infographics, and it helps you retrieve relevant text, figures, or entire pages based on your questions. It's designed for professionals who need to extract insights from complex, visually rich documents.
497 stars. No commits in the last 6 months.
Use this if you need to extract information from documents where images, diagrams, or page layouts are just as important as the text, and traditional text-only search tools fall short.
Not ideal if your documents are purely text-based without any visual elements that contribute to their meaning, as simpler text-focused retrieval methods might suffice.
Stars
497
Forks
48
Language
Python
License
—
Category
Last pushed
Jul 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/adithya-s-k/VARAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
illuin-tech/colpali
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
AnswerDotAI/byaldi
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
jolibrain/colette
Multimodal RAG to search and interact locally with technical documents of any kind
nannib/nbmultirag
Un framework in Italiano ed Inglese, che permette di chattare con i propri documenti in RAG,...
OpenBMB/VisRAG
Parsing-free RAG supported by VLMs