NVIDIA-AI-Blueprints/video-search-and-summarization

  • 类型:github
  • 标识:NVIDIA-AI-Blueprints/video-search-and-summarization
  • 链接:https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization
  • 主题:agent, rag, multimodal, llm-infra
  • 主分类:multimodal
  • 形态:app
  • 分类:skill
  • Stars:1790
  • 周增:+7
  • 语言:C++
  • 许可:NOASSERTION
  • 最近提交:2026-08-11
  • 简介:NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
  • 上次采集:2026-08-11
  • 首次采集:2026-07-22
  • 待LLM分类:否
  • 成熟度:research
  • 简介中文:NVIDIA AI Blueprint for video search and summarization(VSS)是一个 GPU 加速参考架构,用于构建具备实时验证告警、视觉问答与自动报告能力的视频分析 Agent。VSS Blueprint 采用 NVIDIA Cosmos 等视觉语言模型(VLM)、NVIDIA Nemotron 等 LLM,并结合 RAG 与 NVIDIA NIM。
  • 来源文件
  • [GitHub Search]