# Towards Retrieval Augmented Generation over Large Video Libraries

Source: [Towards Retrieval Augmented Generation over Large Video Libraries](<https://www.sota2.com/research/paper/68fa73c31e209131cea5e541>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:56:12.281Z

Authors: Yannis Tevissen, Khalil Guetari, Fr\\'ed\\'eric Petitpont

Published: 2024-06-21T07:52:01.000Z

## Abstract

Video content creators need efficient tools to repurpose content, a task that often requires complex manual or automated searches. Crafting a new video from large video libraries remains a challenge. In this paper we introduce the task of Video Library Question Answering (VLQA) through an interoperable architecture that applies Retrieval Augmented Generation (RAG) to video libraries. We propose a system that uses large language models (LLMs) to generate search queries, retrieving relevant video moments indexed by speech and visual metadata. An answer generation module then integrates user queries with this metadata to produce responses with specific video timestamps. This approach shows promise in multimedia content retrieval, and AI-assisted video content creation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.14938>)

[PDF](<https://arxiv.org/pdf/2406.14938.pdf>)
