Skip to content

A multimodel rag built for video search using Bridge tower, LanceDB, and LLava

Notifications You must be signed in to change notification settings

utk7arsh/video-RAG

Repository files navigation

VIDEO RAG

A Multimodal Retrieval Augmented Generation model built using Gradio for interface, LanceDB for vector database, mm-rag library which allowed additional features like Bridgetower for embeddings, LanceMultimodal for specific Db usecase, and LVLM for vision-natutal language interface interaction.

Inspired by Intel labs's resources on Multimodal RAG: Chat with Videos by Vasudev Lal

About

A multimodel rag built for video search using Bridge tower, LanceDB, and LLava

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published