Video RAG
-
Last Updated 21 August, 2025
-
by David Spuler, Ph.D.
What is Video RAG?
Video RAG is a Retrieval-Augmented Generation (RAG) AI system that returns video data as part of its results. Typically, this involves storing URL addresses of video snippets in a vector database, so that user answers can include a video that they can view. The whole video data is not usually stored inside the vector database itself, but it must contain all the metadata about each video. Video RAG does not usually encompass AI generation of new videos, which is a different technology ("video LLMs").
Research on Video RAG
Research papers include:
- Soyeong Jeong, Kangsan Kim, Jinheon Baek, Sung Ju Hwang, 10 Jan 2025, VideoRAG: Retrieval-Augmented Generation over Video Corpus, https://arxiv.org/abs/2501.05874
- Yongdong Luo, Xiawu Zheng, Xiao Yang, Guilin Li, Haojia Lin, Jinfa Huang, Jiayi Ji, Fei Chao, Jiebo Luo, Rongrong Ji, 20 Dec 2024 (v3), Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension, https://arxiv.org/abs/2411.13093
- Xubin Ren, Lingrui Xu, Long Xia, Shuaiqiang Wang, Dawei Yin, Chao Huang, 3 Feb 2025, VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos, https://arxiv.org/abs/2502.01549 https://github.com/HKUDS/VideoRAG
- Qiuchen Wang, Ruixue Ding, Zehui Chen, Weiqi Wu, Shihang Wang, Pengjun Xie, Feng Zhao, 25 Feb 2025, ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents, https://arxiv.org/abs/2502.18017
More AI Research Topics
Read more about:
- 500+ LLM Inference Optimization Techniques
- What's Hot in LLM Inference Optimization in 2025?
- Inference Optimization Research
- « Research Home