vss-deploy-dense-captioning

Deploy and validate an RT-VLM dense-captioning service with REST API and Kafka streaming.

Updated Apr 16, 2026

Search Tags:#deployment #api #docker #kafka #rt-vlm #dense-captioning

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Deploying and testing an on-demand RT-VLM dense-captioning service can be complex, requiring coordination of Docker Compose, GPU access, NGC/Kafka credentials, and end-to-end API validation.

Core Features & Use Cases

Standalone RT-VLM deployment to run dense-captioning on local video files or RTSP streams.
API-centric validation of endpoints such as /v1/files, /v1/generate_captions, /v1/streams/add, /v1/chat/completions, and Kafka output for captions and incidents.
Workflow guidance for health checks, model loading, and topic wiring to ensure repeatable validation in isolated environments.

Quick Start

Follow the standalone deployment flow to spin up the RT-VLM service with the bp_developer_alerts_2d_vlm profile and verify its health and API endpoints on port 8018.

Frequently Asked Questions about vss-deploy-dense-captioning

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

FAQPage Schema

How do I deploy a standalone RT-VLM dense-captioning service with Docker Compose?▼

To deploy a standalone RT-VLM dense-captioning service, use the provided Docker Compose workflow with the bp_developer_alerts_2d_vlm profile. It handles preflight checks, model loading, and endpoint health verification to ensure a repeatable local validation environment.

What endpoints are available for testing RT-VLM dense-captioning APIs?▼

Available RT-VLM dense-captioning API endpoints include /v1/files, /v1/generate_captions, /v1/streams/add, and /v1/chat/completions. OpenAPI-driven endpoint discovery validates these routes on port 8018 during the deployment workflow.

Do I need GPU access and NGC credentials to run RT-VLM dense-captioning locally?▼

Yes, GPU-enabled deployment is required to run RT-VLM dense-captioning locally. You also need valid NGC and Kafka credentials to handle model loading and wire the Kafka topics for caption and incident streaming.

Does RT-VLM deployment support Kafka streaming for captions and incidents?▼

Yes, RT-VLM deployment supports Kafka-based caption and incident streaming. The deployment workflow includes topic wiring and health checks to validate Kafka output alongside the REST API endpoints.

What is the best way to validate RT-VLM endpoint health and model loading?▼

The best way to validate RT-VLM endpoint health and model loading is through the documented deployment workflow. It includes preflight checks, API-centric validation, and error handling to ensure the service is fully operational on port 8018.

Why is my RT-VLM dense-captioning deployment failing health checks?▼

RT-VLM dense-captioning deployment health checks may fail due to insufficient GPU access, missing NGC or Kafka credentials, or incorrect Docker Compose profile configuration. The workflow provides error handling to diagnose these common deployment issues.