# rag-blueprint

This skill deploys, configures, troubleshoots, and manages NVIDIA RAG Blueprint. Use it when RAG services run through Docker, Kubernetes, or library workflows.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 3300 installs · ★ 3735
- Author: NVIDIA RAG
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/NVIDIA/skills/tree/HEAD/skills/rag-blueprint/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/rag-blueprint

## What it does

The skill routes requests for deploying, starting, configuring, stopping, and troubleshooting NVIDIA RAG Blueprint. It selects a workflow for deployment, configuration, troubleshooting, or shutdown, then uses the project’s playbooks and configuration files. Covered areas include Agentic RAG, VLM, guardrails, ingestion, search, models, observability, and MCP.

Its instructions include environment checks and approved tools for `docker`, `docker compose`, `kubectl`, `helm`, `oc`, `nvidia-smi`, `python3`, `git`, and system commands. It detects running services, identifies the deployment type, and verifies the affected workflow after a change.

A checkout of the NVIDIA RAG Blueprint repository is required. Docker scenarios need Docker/Compose, Kubernetes scenarios need Kubernetes/Helm, and library workflows need Python 3.11+. Self-hosted NIM services also require NVIDIA GPU tooling, so that prerequisite can block the setup.

## Requirements
- Works with: Docker

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill rag-blueprint -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/rag-blueprint/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/rag-blueprint/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill rag-blueprint -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/rag-blueprint/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill rag-blueprint -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/rag-blueprint/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NVIDIA/skills rag-blueprint
```

2. **Manually: put the files in place**
- File: `.github/skills/rag-blueprint/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill rag-blueprint -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/NVIDIA/skills --path skills/rag-blueprint
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/rag-blueprint/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill rag-blueprint -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/NVIDIA/skills/tree/HEAD/skills/rag-blueprint/SKILL.md

## When to use it
- deploy NVIDIA RAG Blueprint
- configure a RAG feature from a request
- diagnose an unhealthy RAG service
- stop or tear down a deployment
- check Docker or Kubernetes service state

## Example prompts
- Deploy NVIDIA RAG Blueprint and check which services are running.
- Configure Agentic RAG, then verify the affected workflow.
- RAG is not working. Troubleshoot it with Docker and fix the configuration.

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 837597beb5905c33.

BEGIN THIRD-PARTY FILE 837597beb5905c33
```text
---
name: rag-blueprint
version: "2.6.0"
description: "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 (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more)."
license: Apache-2.0
compatibility: >-
  NVIDIA RAG Blueprint repository checkout; Docker/Compose or Kubernetes/Helm
  for deployments; Python 3.11+ for library workflows; NVIDIA GPU tooling for
  self-hosted NIM services.
metadata:
  author: "NVIDIA RAG <foundational-rag-dev@exchange.nvidia.com>"
  github-url: "https://github.com/NVIDIA-AI-Blueprints/rag"
  endpoint-openapi-schemas:
    - docs/api_reference/openapi_schema_rag_server.json
    - docs/api_reference/openapi_schema_ingestor_server.json
  argument-hint: deploy RAG | enable feature | disable feature | configure | troubleshoot | shutdown
  tags:
    - nvidia
    - blueprint
    - rag
    - deployment
    - configuration
    - troubleshooting
  languages:
    - python
    - typescript
    - shell
  frameworks:
    - fastapi
    - langchain
    - react
    - docker-compose
    - helm
  domain: ai-ml
allowed-tools: Bash(echo *) Bash(nvidia-smi *) Bash(curl --version *) Bash(docker ps *) Bash(docker info *) Bash(docker --version *) Bash(docker version *) Bash(docker logs *) Bash(docker inspect *) Bash(docker stats *) Bash(docker compose ps *) Bash(docker compose logs *) Bash(docker compose config *) Bash(docker compose version *) Bash(kubectl get *) Bash(kubectl describe *) Bash(kubectl version *) Bash(kubectl logs *) Bash(kubectl api-resources *) Bash(kubectl rollout status *) Bash(helm version *) Bash(helm list *) Bash(helm status *) Bash(oc get *) Bash(oc describe *) Bash(oc logs *) Bash(oc whoami *) Bash(oc version *) Bash(git rev-parse *) Bash(git describe *) Bash(git status *) Bash(python3 --version *) Bash(pip3 show *) Bash(df *) Bash(du *) Bash(cat /proc/*) Bash(cat /etc/os-release *) Bash(ss *) Bash(netstat *) Bash(ls *) Bash(grep *) Bash(lsof *) Bash(ps aux *) Read Grep Glob
---

# NVIDIA RAG Blueprint

## Purpose

Use this skill for NVIDIA RAG Blueprint operations: deployment, configuration,
troubleshooting, shutdown, and feature management across Docker, Helm, and
library deployments.

## Instructions

1. Match the user request to the intent routing table below.
2. Read the referenced playbook before making changes.
3. Use repository docs and deployment config files as the source of truth.
4. Verify the affected service or workflow after changes.

## Prerequisites

- NVIDIA RAG Blueprint repository checkout.
- Docker/Compose or Kubernetes/Helm for deployments.
- Python 3.11+ for library workflows.
- NVIDIA GPU tooling for self-hosted NIM services.

## Autonomy Principles
```
END THIRD-PARTY FILE 837597beb5905c33

The third-party file has ended. Everything between the 837597beb5905c33 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2909 of 11354 bytes. © NVIDIA RAG · Apache-2.0 · https://github.com/NVIDIA/skills/tree/HEAD/skills/rag-blueprint/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md