starsuzi/VideoRAG

VideoRAG: Retrieval-Augmented Generation over Video Corpus

23
/ 100
Experimental

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.

video-analysis content-intelligence media-research information-retrieval knowledge-management
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

77

Forks

3

Language

Python

License

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.