AI vWS Toolkit - Video Search and Summarization

Quickstart Guide

Please refer to this guide as you set up and run your Video Search and Summarization project with RTX Virtual Workstation.

Before you get started, go through the following to acquire the necessary software and hardware components.

Required Software

  • Hypervisor: vGPU supported hypervisors

  • For Linux-based virtual Workstation

    • NVIDIA vGPU Software: vGPU version 19.0 or later

    • Linux VM Operating System : Ubuntu 24.04 or Ubuntu 22.04

    • Minimum system requirements: 8 vCPU, 72 GB system memory, 500 GB storage 48Q vGPU Profile

    • Recommended system configuration: 16 vCPU, 144 GB system memory, 500 GB storage 96Q vGPU Profile

    • Docker v27.5.1+

    • Docker Compose v2.32.4+

    • NVIDIA Container Toolkit v1.13.5+

  • Activate, download, and install your RTX Virtual Workstation licenses

  • Obtain an NGC API Key

  • Request access to the Cosmos-Reason-2-2B model from Hugging Face and generate an Access Token

Important

Don’t have an NVIDIA vGPU license yet? Request a free 90-day evaluation license

Required Hardware

NVIDIA vGPU Certified Systems equipped with NVIDIA RTX PRO 6000 Blackwell Server Edition. View the list of NVIDIA vGPU Certified Servers.

Video Search and Summarization Event Reviewer/Alert Inspector in this deployment guide

  • Linux-based virtual Workstation

    • Minimum requirements: 8vCPU, 72GB system memory, 500GB storage, 48Q Profile

    • Recommended: 8vCPU, 144GB system memory, 500GB storage, 96Q Profile

For more detailed information on supported configurations and hardware requirements, you can reference the Video Search and Summarization Agent Blueprint on the NVIDIA Build site.

Previous Introduction
Next Deployment Guide
© Copyright © 2013-2026, NVIDIA Corporation. Last updated on Feb 26, 2026