Retrieval Augmented Generation for youtube videos with a BRAD agent

[NAACL 2024] Official Implementation of paper "Self-Adaptive Sampling for Efficient Video Question Answering on Image--Text Models"

A powerful Video RAG system that enables users to upload videos, automatically builds searchable indexes from transcripts, and answers questions using Google Gemini. Built with a focus on local processing and only free tools.

Multimodal-VideoRAG: Using BridgeTower Embeddings and Large Vision Language Models

Frameverse is a new way to search for movies 🎞️ Describe a moment, motive, or scene to jump to the exact fragment

Video Memory CLI: index once, search/ask forever (dense captions + transcripts + timestamps). Built for agents.

Multimodal Retrieval-Augmented Generation (RAG) system for video understanding. Enables semantic search and Q&A by indexing visual frames and audio context using vision-language models.

ASKORA is an intelligent RAG-powered system that lets users upload educational videos, automatically transcribe them, index their content into vector embeddings, and ask natural questions about any part of the video — with precise timestamped answers and references.

AI-powered system that processes and analyzes videos to retrieve and generate context-aware responses using Retrieval-Augmented Generation techniques.

🎥 Engage with your videos like never before by chatting directly with them using VideoRAG. Explore a new dimension of video interaction and insight.

A Cross-Frame Multimodal Retrieval Augmented Generation (CFM-RAG) for Video Intelligence. It retrieves the most relevant multimodal evidence and empowers LLMs to deliver context-rich answers.

Video RAG: Chat with your video.