Build a Video Search and Summarization (VSS) Agent

Basic idea

Deploy NVIDIA's Video Search and Summarization (VSS) AI Blueprint to build intelligent video analytics systems that combine vision language models, large language models, and retrieval-augmented generation. The system transforms raw video content into real-time actionable insights with video summarization, Q&A, and real-time alerts. You'll set up either a completely local Event Reviewer deployment or a hybrid deployment using remote model endpoints.

What you'll accomplish

You will deploy NVIDIA's VSS AI Blueprint on NVIDIA Spark hardware with Blackwell architecture, choosing between two deployment scenarios: VSS Event Reviewer (completely local with VLM pipeline) or Standard VSS (hybrid deployment with remote LLM/embedding endpoints). This includes setting up Alert Bridge, VLM Pipeline, Alert Inspector UI, Video Storage Toolkit, and optional DeepStream CV pipeline for automated video analysis and event review.

What to know before starting

• Working with NVIDIA Docker containers and container registries
• Setting up Docker Compose environments with shared networks
• Managing environment variables and authentication tokens
• Basic understanding of video processing and analysis workflows

Prerequisites

• NVIDIA Spark device with ARM64 architecture and Blackwell GPU
• DGX OS (suggested: 7.4.0 or higher)
• Driver version 580.95.05 or higher installed: nvidia-smi | grep "Driver Version"
• CUDA version 13.0 installed: nvcc --version
• Docker installed and running: docker --version && docker compose version
• Access to NVIDIA Container Registry with NGC API Key
• NVIDIA Container Toolkit
• [Optional] NVIDIA API Key for remote model endpoints (hybrid deployment only)
• Sufficient storage space for video processing (>10GB recommended in /tmp/)

Ancillary files

• VSS Blueprint GitHub Repository - Main codebase and Docker Compose configurations
• VSS Official Documentation - Complete system documentation

Time & risk

• Duration: 30-45 minutes for initial setup, additional time for video processing validation
• Risks:
  • Container startup can be resource-intensive and time-consuming with large model downloads
  • Network configuration conflicts if shared network already exists
  • Remote API endpoints may have rate limits or connectivity issues (hybrid deployment)
• Rollback: Stop all containers with scripts/dev-profile.sh down
• Last Updated: 3/16/2026
  • Update required OS and Driver versions
  • Support for VSS 3.1.0 with Cosmos Reason 2 VLM