NVIDIA-AI-Blueprints

Deploy, debug, or tear down any VSS profile using a compose-centric workflow — config (dry-run) with env overrides, review resolved compose, then compose up. Use this skill when the user says "deploy vss", "deploy `profile`", "debug deploy", "verify deployment", or "why is my vss deploy broken".

Use this skill when working with the RTVI VLM or RT-VLM microservice API on VSS 3.1. Generate dense captions and alerts for stored video files and live RTSP streams via `/v1/generate_captions_alerts`; upload media via `/v1/files`; add and remove live streams with `/v1/streams/add` and `/v1/streams/delete/{stream_id}`; call OpenAI-compatible `/v1/chat/completions`; consume Kafka caption, incident, and error topics; or debug rtvi-vlm responses. For deployment, read `references/deploy-rt-vlm-service.md` first.

Summarize a video by calling the VLM NIM or the Long Video Summarization (LVS) microservice directly. For short videos (under 60s) call the VLM's OpenAI-compatible chat completions endpoint; for long videos (60s or longer) call the LVS microservice. Use when asked to summarize a video, describe what happens in a video, analyze a recording, call or debug LVS summarize/model/health/recommended-config/metrics endpoints, or configure and troubleshoot the LVS service that backs long-video summarization.

Query VIOS REST APIs: sensor list, recording timelines, video clip extraction, snapshot capture, add/delete sensors and streams

Manage and monitor VSS alerts after the alerts profile is deployed. The deployment's mode (CV vs VLM real-time) is fixed at deploy time and determines the workflow — start/stop real-time alerts via the VSS Agent on a VLM deployment, onboard CV alerts by adding RTSP streams to VIOS on a CV deployment, query incidents, customize verifier prompts. Use when asked to start/stop a real-time alert, check or list alerts, add a camera, use a sample video for alerts, customize alert prompts, or view verdicts.

Produce video analysis reports by discovering the deployed VSS agent, querying POST /generate for a timestamped captioned summary of the clip, then formatting the agent reply as the standard Video Analysis Report markdown.

Query video analytics data and metrics from Elastic search via the VA-MCP server (port 9901). This includes incidents, alerts, sensor data, and metrics. Use for any question about violations, alerts, incidents, object counts, speeds, occupancy, or anything that requires looking up recorded events. This is the primary way to answer a question that requires incidents, alerts and other metrics such as people counts and violations.

Search video archives using natural language — find events, objects, actions, and people across recorded video using fusion search (Cosmos Embed1 semantic search + CV attribute search). Use when asked to search for something in video, find actions and events, locate objects and people, or query video archives. For these types of questions, default to this top-level fusion search unless user specifies otherwise. Requires the search profile to be deployed.

Start, stop, configure, inspect, and troubleshoot the Retail Shopping Assistant locally with backend Python and React code outside containers, local Milvus infra containers, and remote NIM endpoints from docker-compose-nim-local.yaml.

Run the Retail Shopping Assistant test suites under tests/, including offline pytest unit tests in tests/unit and live integration scripts in tests/integration for conversation, quality, timing, and plots.

Start, stop, configure, inspect, and troubleshoot the Retail Shopping Assistant locally with backend Python and React code outside containers, local Milvus infra containers, and remote NIM endpoints from docker-compose-nim-local.yaml.

Run the Retail Shopping Assistant test suites under tests/, including offline pytest unit tests in tests/unit and live integration scripts in tests/integration for conversation, quality, timing, and plots.

Launch all services for the Retail Agentic Commerce project. Validates prerequisites, configures environment, and starts the full stack. Supports Docker deployment (recommended) and local development. Use when the user types "setup", "install", or asks to start/launch the project.

Python backend development standards for FastAPI, SQLModel, and pytest. Enforces Ruff linting, Pyright type checking, and test coverage. Use when writing Python code, creating API endpoints, implementing services, adding database models, or modifying backend logic in src/merchant/, src/payment/, or src/apps_sdk/.

React/Next.js frontend development standards with TypeScript, Tailwind CSS, and Kaizen UI. Enforces ESLint, Prettier, and browser validation via MCP. Use when creating React components, modifying pages, styling with Tailwind, implementing hooks, or working in src/ui/. Validates changes in browser when MCP tools available.

Comprehensive code analysis before committing changes. Verifies mock data exists, MCP communication is real (not hardcoded), tool calls are correct, and Apps SDK web isolation. Use before git commits, for big changes, or when the user asks to validate implementation quality.

Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.

Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

Use this skill for converting researched facts or user-provided data into structured tables by writing code, then running Python/pandas calculations in the job-scoped sandbox. This skill is for numeric normalization, tabular analysis, rankings, growth rates, summary statistics, CSV/JSON generation, and markdown tables. Triggers: "compute table", "calculate growth", "normalize values", "extract figures", "rank companies", "QoQ", "YoY", "CAGR", "summary statistics", "CSV", "JSON", "markdown table", "standardize quarters", "standardize currencies", "compare over time" Outputs: Markdown tables, CSV text, JSON records, summary statistics, rankings, and data-quality notes.

NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, and more).

Deploy Nemotron Voice Agent on Workstation (x86), Jetson Thor, or Cloud NIMs. Real-time speech-to-speech using NVIDIA ASR, TTS, LLM with WebRTC/WebSocket transport.