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

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.

语言：Python · GitHub 星标：1,958 · Fork：416

话题：computer-vision · generative-ai · long-video-understanding · model-context-protocol · multimodal-ai · natural-language-search · nvidia-nim · rag

在 GitHub 上查看原仓库