starsuzi/VideoRAG
VideoRAG: Retrieval-Augmented Generation over Video Corpus
VideoRAG helps you answer questions or generate information using a library of videos, going beyond just text or images. You provide a question, and it sifts through your video collection to find the most relevant clips, using both what's seen and said in the video. The result is a more accurate and context-rich answer. This is for researchers, analysts, or content creators who need to leverage video archives for detailed insights.
No commits in the last 6 months.
Use this if you need to extract precise information or generate comprehensive responses by querying a large collection of videos, where both visual and spoken content are crucial for accuracy.
Not ideal if your primary data source is static text or images, or if your video corpus is small and easily searchable manually.
Stars
77
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/starsuzi/VideoRAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
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