vss-deploy-video-embedding

Deploy the VSS Video Embedding RT-Embed service with Docker Compose and GPU configuration.

Updated Apr 16, 2026

Search Tags:#gpu #deploy #docker-compose #nvidia #video-embedding #rt-embed #cosmos-embed1-448p

Ready to run

npx skills add https://github.com/sayalinvidia/sayali-skills-test --skill vss-deploy-video-embedding

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: vss-deploy-video-embedding
Source: https://github.com/sayalinvidia/sayali-skills-test/tree/main/skills/vss-deploy-video-embedding
Command: npx skills add https://github.com/sayalinvidia/sayali-skills-test --skill vss-deploy-video-embedding

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Deploy, operate, and integrate the NVIDIA VSS Video Embedding RT-Embed service to provide end-to-end video and text embeddings for search, retrieval, and analytics pipelines. It covers deployment orchestration, GPU prerequisites, model readiness, and integration with Redis, Kafka, and OpenTelemetry across a VSS deployment.

Core Features & Use Cases

Deploy the RT-Embed service from a Docker Compose file with proper GPU and storage configuration.
Enable embedding capabilities for video files, URLs, and live RTSP streams, plus text embeddings in the same vector space.
Validate health, readiness, and model readiness, and integrate with observability, messaging, and persistence layers.

Quick Start

Bring up the RT-Embed service with the dedicated Compose profile and verify readiness by querying /v1/ready.

Frequently Asked Questions about vss-deploy-video-embedding

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

What is the best way to verify if my video embedding deployment is ready?▼

Verify video embedding deployment readiness by querying the /v1/ready endpoint. The service validates health, readiness, and model readiness to ensure end-to-end embedding capabilities are fully operational.

How do I deploy a video embedding service with Docker Compose and GPU support?▼

Deploying a video embedding service requires GPU hardware, Docker Compose, and environment variables for port mapping and data paths. The RT-Embed service uses a dedicated Compose profile to orchestrate GPU and storage configuration for end-to-end video and text embeddings.

Can I generate embeddings from live RTSP streams and video URLs?▼

Yes, video embedding supports generating embeddings from video files, URLs, and live RTSP streams. The service also produces text embeddings within the same vector space for search and retrieval pipelines.

Do I need NVIDIA GPU hardware to run the Cosmos embedding model?▼

NVIDIA GPU hardware is required to run the Cosmos embedding model. The deployment validates model readiness and GPU prerequisites to ensure the VSS Video Embedding service operates correctly.

How does the VSS video embedding service integrate with Redis and Kafka?▼

VSS video embedding integrates with Redis, Kafka, and OpenTelemetry through environment variables configured for peer services. This setup enables messaging, persistence, and observability across the deployment pipeline.

What is the best way to verify if my video embedding deployment is ready?▼