# Vss Deploy Dense Captioning

Use this skill when deploying standalone RT-VLM dense captioning or calling its REST...

- Repository: https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization (1959 stars)
- Category: DevOps
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add NVIDIA-AI-Blueprints/video-search-and-summarization --skill vss-deploy-dense-captioning -g -a claude-code -y`
Codex: `npx skills add NVIDIA-AI-Blueprints/video-search-and-summarization --skill vss-deploy-dense-captioning -g -a codex -y`
Cursor: `npx skills add NVIDIA-AI-Blueprints/video-search-and-summarization --skill vss-deploy-dense-captioning -g -a cursor -y`
Gemini CLI: `npx skills add NVIDIA-AI-Blueprints/video-search-and-summarization --skill vss-deploy-dense-captioning -g -a gemini-cli -y`

## Description

Use this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS profile deploy or video-search ingestion.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

## Purpose

Stand up the RT-VLM dense-captioning microservice on its own and exercise every endpoint it exposes (file upload, generate_captions, stream add/delete, chat-completions, Kafka topics).

## When to Use

- Deploy standalone RT-VLM dense captioning when no full VSS profile is running
- Generate dense captions for an uploaded file or RTSP stream via the RT-VLM REST API
- Manage RT-VLM stream lifecycle (add/get-info/delete) or call chat-completions against it
- Wire RT-VLM to Kafka/ELK/VIOS or sibling model services

Not for deploying a full VSS profile (use `vss-build-vision-ai`) or ingesting video for search (video-search ingestion is a separate path).

## Prerequisites

For standalone RT-VLM deployment:
- Docker, Docker Compose, NVIDIA Container Toolkit, and a visible GPU.
- NGC registry credentials in `$NGC_CLI_API_KEY` for `docker login nvcr.io`,
  image pulls, and local NGC model/artifact downloads.
- `curl`, `jq`, the current VSS checkout, and a writable directory for standalone env/state.

For API calls against an existing service:
- Running RT-VLM service reachable at `$BASE_URL`.
- Bearer token in `$RTVI_VLM_API_KEY` or `$NGC_CLI_API_KEY`, depending on how the
  service was configured.

For full VSS profile deployment:
- Use `../../vss-build-vision-ai/SKILL.md`; this skill does not deploy full VSS profiles.

## Instructions

Follow the routing tables and step-by-step workflows below. Each section that ends in *workflow*, *quick start*, or *flow* is intended to be executed top-to-bottom. Detailed reference material lives in `references/`; execute the documented workflows directly unless a future revision names a concrete helper.

## Examples

Worked end-to-end examples are kept under `evals/` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow `curl` blocks below. Run a Tier-3 evaluation with `nv-base validate <this-skill-dir> --agent-eval` to replay them.

## Limitations

The rest: https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization/blob/HEAD/skills/deployment/vss-deploy-dense-captioning/SKILL.md