{"data":{"slug":"hkuds-videorag","name":"VideoRAG","tagline":"Chat with Your Videos","github_url":"https://github.com/HKUDS/VideoRAG","owner":"HKUDS","repo":"VideoRAG","owner_avatar_url":"https://avatars.githubusercontent.com/u/118165258?v=4","primary_language":"Python","stars":3288,"forks":467,"topics":["large-language-models","llms","long-video-understanding","multi-modal-llms","rag","retrieval-augmented-generation"],"archived":false,"github_pushed_at":"2026-03-18T08:33:07+00:00","maintenance_label":"Slowing","stars_delta_30d":104,"url":"https://www.graphcanon.com/tools/hkuds-videorag","markdown_url":"https://www.graphcanon.com/tools/hkuds-videorag.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hkuds-videorag","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hkuds-videorag","description":"[KDD'2026] \"VideoRAG: Chat with Your Videos\"","homepage_url":"https://arxiv.org/abs/2502.01549","license":"Other","open_issues":21,"watchers":52,"ai_summary":"VideoRAG is an AI desktop application allowing users to interact with videos through natural language queries, capable of processing extreme long-context video content.","readme_excerpt":"<div align=\"center\">\n  <picture>\n      <img src=\"cover.png\" width=\"80%\" style=\"border: none; box-shadow: none;\" alt=\"Vimo: Chat with Your Videos\">\n  </picture>\n  \n  <h1>\n    <strong>VideoRAG: Chat with Your Videos</strong> • <strong>Vimo Desktop</strong>\n  </h1>\n\n  <a href=\"https://trendshift.io/repositories/16146\" target=\"_blank\"><img src=\"https://trendshift.io/api/badge/repositories/16146\" alt=\"HKUDS%2FVideoRAG | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/></a>\n  \n  <a href='https://arxiv.org/abs/2502.01549'><img src='https://img.shields.io/badge/arXiv-2502.01549-b31b1b'></a>\n  <a href='https://github.com/HKUDS/VideoRAG/issues/1'><img src='https://img.shields.io/badge/群聊-wechat/feishu-green'></a>\n  <a href='https://discord.gg/ZzU55kz3'><img src='https://discordapp.com/api/guilds/1296348098003734629/widget.png?style=shield'></a>\n  <a href='https://www.youtube.com/watch?v=D5vsxcp4QZI'><img src='https://img.shields.io/badge/YouTube-Watch%20Demo-red?style=flat&logo=youtube'></a>\n  \n  \n  \n\n  **🎬 Intelligent Video Conversations | Powered by Advanced AI | Extreme Long-Context Processing**\n\n</div>\n\n<br/>\n\n<img src='VideoRAG-algorithm/VideoRAG_cover.png' />\n\nVimo is a revolutionary desktop application that lets you **chat with your videos** using cutting-edge AI technology. Built on the powerful [VideoRAG framework](https://arxiv.org/abs/2502.01549), Vimo can understand and analyze videos of any length - from short clips to hundreds of hours of content - and answer your questions with remarkable accuracy.\n\n### 🎥 Watch Vimo in Action\n\nSee how Vimo transforms video interaction with intelligent conversations and deep understanding capabilities.\n\n<div align=\"center\">\n  <a href=\"https://www.youtube.com/watch?v=D5vsxcp4QZI\">\n    <img src=\"https://img.youtube.com/vi/D5vsxcp4QZI/maxresdefault.jpg\" width=\"80%\" alt=\"Vimo Introduction Video\">\n  </a>\n  <p><em>👆 Click to watch the Vimo demo video</em></p>\n</div>\n\n## ✨ Key Features\n\n### For Everyone\n- **Drag & Drop Upload**: Simply drag video files into Vimo\n- **Smart Conversations**: Ask questions in natural language\n- **Multi-Format Support**: Works with MP4, MKV, AVI, and more\n- **Cross-Platform**: Available on macOS, Windows, and Linux\n\n### For Power Users\n- **Extreme Long Videos**: Process videos up to hundreds of hours\n- **Multi-Video Analysis**: Compare and analyze multiple videos simultaneously\n- **Advanced Retrieval**: Find specific moments and scenes with precision\n- **Export Capabilities**: Save insights and references for later use\n\n### For Researchers\n- **VideoRAG Framework**: Access to cutting-edge retrieval-augmented generation\n- **Benchmark Dataset**: LongerVideos benchmark with 134+ hours of content\n- **Performance Metrics**: Detailed evaluation against existing methods\n- **Extensible Architecture**: Build upon our open-source foundation\n  \n## 🌟 Why Vimo?\n\n**For Video Enthusiasts & Professionals:**\n- **Effortless Video Analysis**: Upload any video and start asking questions immediately\n- **Natural Conversations**: Chat with your videos as if talking to a human expert\n- **No Length Limits**: Process everything from 30-second clips to 100+ hour documentaries\n- **Deep Understanding**: Combines visual content, audio, and context for comprehensive answers\n\n**For Researchers & Developers:**\n- **State-of-the-Art Algorithm**: Built on VideoRAG, featuring graph-driven knowledge indexing\n- **Benchmark Performance**: Evaluated on 134+ hours across lectures, documentaries, and entertainment\n- **Open Source**: Full access to VideoRAG implementation and research findings\n- **Scalable Architecture**: Efficient processing with single GPU (RTX 3090) capability\n\n## 📋 Table of Contents\n\n- [🚀 Quick Start](#-quick-start)\n- [✨ Key Features](#-key-features)\n- [🔬 VideoRAG Algorithm](#-videorag-algorithm)\n- [🛠️ Development Setup](#️-development-setup)\n- [🧪 Benchmarks & Evaluation](#-benchmarks--evaluation)\n- [📖 Citation](#-citation)\n- [🤝 Contributing](#-contributing","github_created_at":"2025-02-03T03:59:11+00:00","created_at":"2026-07-11T11:06:40.026101+00:00","updated_at":"2026-08-18T00:02:11.096067+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"large-language-models","name":"large language models"},{"slug":"llms","name":"llms"},{"slug":"long-video-understanding","name":"long-video-understanding"},{"slug":"multi-modal-llms","name":"multi-modal-llms"},{"slug":"rag","name":"rag"},{"slug":"retrieval-augmented-generation","name":"retrieval-augmented-generation"}],"trust":{"provenance":{"is_fork":false,"github_id":926334425,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-18T00:02:10.313Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":152,"last_release_at":null,"stars_delta_30d":104,"open_issues_delta_30d":1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:06:41.445Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-18T00:02:10.800Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-18T00:02:10.800Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-18T00:02:10.800Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You have long videos (up to hundreds of hours) and need precise analysis or summaries that require deep understanding of both audio and visual components.","Your work involves comparing multiple video files simultaneously and you need a tool that can handle cross-referencing content efficiently."],"when_not_to_use":["You are working with short clips (under one minute) where traditional search methods might be quicker or more straightforward.","If your needs are strictly for audio transcription or text-based retrieval, VideoRAG's features may offer more complexity than necessary.","Your video content has strict privacy concerns, as using desktop applications can sometimes pose security and confidentiality risks depending on the user’s context."],"source":"enrich:decision_facts","observed_at":"2026-07-14T20:59:04.972Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"VideoRAG is an AI desktop application that allows users to interact with video content through natural language queries, catering to enthusiasts and professionals alike."}]}}