GitHub repository
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.
Python- Total stars
- 2.0K
- Today
- +1
- Last 7 days
- +16
- Last 30 days
- +74
Recorded star history
Snapshot: 2026-10-28. Counts recorded during the last 7 days, oldest first.
Oldest recordedLatest recorded
Topics
- rag
- skills
- generative-ai
- model-context-protocol
- computer-vision
- retrieval-augmented-generation
- vlm
- vision-language-model
- multimodal-ai
- video-summarization
- video-understanding
- long-video-understanding
- natural-language-search
- nvidia-nim
- real-time-video-analytics
- video-agent
- video-analytics
- video-rag
- video-search
- vision-agent