Workflow·AI & Agents·v2.6.0

RAG Blueprint

Name: RAG Blueprint
Author: NVIDIA

NVIDIA RAG Blueprint — deploy, configure, troubleshoot and manage any RAG action: agentic RAG, VLM, guardrails, query rewriting…

You say

Buy it · $15 Read it before you buy $15 Written by NVIDIA · unverified publisher

Context cost: 32.1k tokensestimated from the bundle, loaded when it triggers
Bundle: 37 files · 128.4 kBtext throughout, nothing executable
Licence: Apache-2.0paid listing
Last change: —v2.6.0
Servers it uses: Noneruns standalone

What it does

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).

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Workflow

Runs a procedure end to end.

ragdeploymentnvidiallm

Filed under

AI & Agents

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md11.4 kB · 205 lines

--- 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 ---

38# NVIDIA RAG Blueprint

40## Purpose

42Use this skill for NVIDIA RAG Blueprint operations: deployment, configuration,

43troubleshooting, shutdown, and feature management across Docker, Helm, and

44library deployments.

46## Instructions

481. Match the user request to the intent routing table below.

492. Read the referenced playbook before making changes.

503. Use repository docs and deployment config files as the source of truth.

514. Verify the affected service or workflow after changes.

53## Prerequisites

55- NVIDIA RAG Blueprint repository checkout.

56- Docker/Compose or Kubernetes/Helm for deployments.

57- Python 3.11+ for library workflows.

58- NVIDIA GPU tooling for self-hosted NIM services.

60## Autonomy Principles

62- Auto-detect everything: GPU, VRAM, drivers, Docker, CUDA, disk, OS, ports, existing services, NGC key, repo state.

63- If it can be checked with a command, check it — don't ask the user.

64- Ask only when user action is required: providing an API key, confirming data deletion, or choosing between equally valid options.

65- Once analysis is done, route to the correct workflow and execute.

67## Intent Detection

69Determine what the user wants and route immediately:

71| User Intent | Action |

72|-------------|--------|

73| Deploy, install, set up, start RAG | Read and follow references/deploy.md |

74| Configure, enable, change, toggle a feature | Use the Configure section below |

75| Troubleshoot, debug, fix, error, unhealthy | Read and follow references/troubleshoot.md |

76| Stop, shutdown, tear down, clean up | Read and follow references/shutdown.md |

78If the intent is ambiguous, infer from context (e.g., "RAG isn't working" → troubleshoot; "get RAG running" → deploy). Only ask if genuinely unclear.

80---

82## Configure

84Requires a running RAG deployment. If services are not running, deploy first via references/deploy.md.

86Match the user's request to a reference file, then read and follow it:

88| Feature Keywords | Reference |

89|-----------------|-----------|

90| VLM, VLM embeddings, image captioning | references/configure/vlm.md |

91| NeMo Guardrails | references/configure/guardrails.md |

92| Agentic RAG, planning/execution agent, agentic streaming, stage events | references/configure/agentic-rag.md |

93| Query rewriting, decomposition, multi-turn | references/configure/query-and-conversation.md |

94| Ingestion (text-only, audio, Nemotron Parse, OCR, batch CLI, NV-Ingest, volume mount, performance) | references/configure/ingestion.md |

95| Search, retrieval, hybrid search, multi-collection, metadata, filters, Elasticsearch filters, reranker, topK, accuracy/performance | references/configure/search-and-retrieval.md |

96| LLM/embedding/ranking model changes, vector DB, Milvus/Elasticsearch auth, service keys, model profiles, ports/GPU | references/configure/models-and-infrastructure.md |

97| Reasoning, thinking mode, reasoning_content, self-reflection, prompts, generation params (tokens, temperature, citations), per-request LLM params | references/configure/reasoning-and-generation.md |

98| Summarization | references/configure/summarization.md |

99| Observability (tracing, Zipkin, Grafana, Prometheus) | references/configure/observability.md |

100| Multimodal query (image + text) | references/configure/multimodal-query.md |

101| Data catalog (collection/document metadata) | references/configure/data-catalog.md |

102| User interface (UI settings, reasoning panel, metadata filters) | references/configure/user-interface.md |

103| API reference (endpoints, schemas) | references/configure/api-reference.md |

104| Evaluation (RAGAS metrics) | references/configure/evaluation.md (and skill rag-eval) |

105| MCP server & client, agent toolkit | references/configure/mcp.md |

106| Migration (version upgrades) | references/configure/migration.md |

107| Notebooks (setup and catalog) | references/configure/notebooks.md |

108

109### Configure Flow

110

1111. Match the user's request to a reference file from the table above.

112

1132. Detect what's running:

114 ```bash

115 echo "=== NIM ===" && docker ps --format '{{.Names}}' 2>/dev/null | grep -iE '(nim-llm|nemotron-(vlm-)?embedding|nemotron-ranking|nemotron-vlm|nemotron-3-nano-omni|page-elements|graphic-elements|table-structure|nemotron-ocr)' || echo "NO_LOCAL_NIMS"; echo "=== RAG ===" && docker ps --format '{{.Names}}' 2>/dev/null | grep -iE '(rag-server|ingestor-server|elasticsearch|milvus|seaweedfs|lancedb)' || echo "NO_DOCKER_RAG"; echo "=== K8S ===" && kubectl get pods -n rag 2>/dev/null | head -5 || echo "NO_K8S"; echo "=== LIBRARY ===" && ps aux 2>/dev/null | grep -E '(nvidia_rag|uvicorn.*rag)' | grep -v grep || echo "NO_LIBRARY"

116 ```

117

1183. Use this table to determine platform, deployment type, and where config lives:

119

121 |---------------------|-----------------------|-----------------|-----------------|

127 | No | No | Not running | Deploy first via references/deploy.md |

128

129 Tell the user what you detected and ask to confirm. Example: "I see local NIM containers running (nim-llm-ms, nemotron-vlm-embedding-ms) — this is a self-hosted deployment. Config file is deploy/compose/.env. Correct?"

130

1314. Check current feature state before changing anything — read the config location from step 3, then cross-check the live service:

132 - Docker: docker exec rag-server env 2>/dev/null | grep -E "<VAR_NAME>"

133 - Helm: kubectl get pod -n rag -l app=rag-server -o jsonpath='{.items[0].spec.containers[0].env}' 2>/dev/null

134

135 If the config file and live service disagree, tell the user the service has stale config and will need a restart.

136

1375. If the feature needs extra GPUs, check availability against hardware restrictions (see below):

138 ```bash

139 nvidia-smi --query-gpu=index,name,memory.total,memory.used --format=csv,noheader 2>/dev/null || echo "NO_GPU"

140 ```

141

1426. Read the reference file and apply changes:

143 - Docker: edit the env file (uncomment to enable, re-comment to disable — the env file is the source of truth). Then restart the affected service:

144 ```

145 source <env-file> && docker compose -f deploy/compose/<compose-file> up -d

146 ```

147 | Service | Compose File |

148 |---------|-------------|

149 | rag-server | docker-compose-rag-server.yaml |

150 | ingestor-server | docker-compose-ingestor-server.yaml |

151 | Elasticsearch, Milvus, etcd, SeaweedFS | vectordb.yaml |

152 | NIM containers (LLM, embedding, ranking, VLM, OCR, parse, audio, extraction) | nims.yaml |

153 | guardrails | docker-compose-nemo-guardrails.yaml |

154 | observability (Grafana, Prometheus, Zipkin) | observability.yaml |

155 - Helm: edit values.yaml, then upgrade: helm upgrade rag <chart> -n rag -f values.yaml

156 - Library: edit notebooks/config.yaml, then restart the Python process

157

1587. Verify:

159 - Docker: docker ps --format "table {{.Names}}\t{{.Status}}" | head -20; curl -s http://localhost:8081/v1/health?check_dependencies=true 2>/dev/null | head -1

160 - Helm: kubectl get pods -n rag; kubectl rollout status deployment/rag-server -n rag --timeout=120s

161 - Library: curl -s http://localhost:8081/v1/health 2>/dev/null | head -1

162

1638. If restart fails, read references/troubleshoot.md. If multiple features requested, repeat from step 1 for each.

164

165## Examples

166

167- "Deploy RAG" -> route to references/deploy.md.

168- "Enable VLM" -> route to references/configure/vlm.md.

169- "RAG is unhealthy" -> route to references/troubleshoot.md.

170- "Stop RAG" -> route to references/shutdown.md.

171

172## Limitations

173

174- Operational guidance only applies to this RAG Blueprint repository.

175- Live deployment changes require a running Docker, Helm, or library target.

176- Secrets such as NGC_API_KEY must be supplied by the user environment.

177

178## Troubleshooting

179

180| Error / signal | What to do |

181|----------------|------------|

182| Services are not running | Follow references/deploy.md before configuring features. |

183| Restart or health check fails | Follow references/troubleshoot.md. |

184| User requests teardown | Follow references/shutdown.md and confirm destructive cleanup. |

185

186### When User Says "Configure" Without Specifics

187

188Run steps 2–3 above, then read the identified config file to list what's currently enabled:

189```bash

190grep -E "^(export )?(ENABLE_|APP_)" <config-file> 2>/dev/null | sort

191```

192Summarize what's running and enabled, then ask which feature to change.

193

194---

195

196## Hardware Restrictions

197

198Read docs/support-matrix.md for current GPU requirements per deployment mode.

199Read docs/service-port-gpu-reference.md for port mappings and GPU assignments.

200

201| GPU | Feature Restrictions |

202|-----|---------------------|

203| B200 | No VLM, No Guardrails, No Nemotron Parse. May need multi-GPU LLM (LLM_MS_GPU_ID). |

204| RTX PRO 6000 | No Nemotron Parse. No Audio on Helm. |

205

In the file

SKILL.md1,453 words

Files37

LicenceApache-2.0

Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈550

always loaded

The name and description, so the model knows the skill exists and when to reach for it.

31,550

on trigger

The instruction body and 36 supporting files, read only when the skill fires.

16.1%

of a 200k window

Ten skills this size would take about 161% of the window before you open a file.

050k100k150k200k context window

32.1k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption

Installsnone yet

Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for

Writes filesno

Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

If this is not it

14 other skills in AI & Agents

What is in the bundle

37 files, 128.4 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

BENCHMARK.md4.7 kB
SKILL.md11.4 kB
skill-card.md3.2 kB
eval/h100.json2.5 kB
eval/nvidia_hosted.json3.7 kB
references/deploy.md8.1 kB
references/shutdown.md4.8 kB
references/troubleshoot.md9.0 kB
references/configure/agentic-rag.md5.1 kB
references/configure/api-reference.md1.7 kB
references/configure/data-catalog.md1.8 kB
references/configure/evaluation.md2.9 kB
references/configure/guardrails.md1.7 kB
references/configure/ingestion.md3.6 kB
references/configure/mcp.md1.3 kB
references/configure/migration.md1.6 kB
references/configure/models-and-infrastructure.md4.7 kB
references/configure/multimodal-query.md2.0 kB
references/configure/notebooks.md2.9 kB
references/configure/observability.md1.5 kB
references/configure/query-and-conversation.md3.8 kB
references/configure/reasoning-and-generation.md3.9 kB
references/configure/search-and-retrieval.md4.1 kB
references/configure/summarization.md2.1 kB
references/configure/user-interface.md1.7 kB
references/configure/vlm.md3.7 kB
references/deploy/docker-nvidia-hosted.md2.2 kB
references/deploy/docker-retrieval-only.md1.7 kB
references/deploy/docker-self-hosted.md2.3 kB
references/deploy/docker.md4.4 kB
references/deploy/helm-mig.md2.1 kB
references/deploy/helm-openshift.md3.7 kB
references/deploy/helm-standard.md2.4 kB
references/deploy/helm.md5.7 kB
references/deploy/library-full.md2.3 kB
references/deploy/library-lite.md1.8 kB
references/deploy/library.md2.3 kB

What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 37 files you can review in full before installing. The Apache-2.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

$15 once

RAG Blueprint · Apache-2.0 · NVIDIA

one-time

Price$15 once

LicenceApache-2.0 — the author’s, unchanged by this purchase

Paid throughStripe, once, on the card you add at the checkout

Keeps workingfor good — the files are yours once they are on disk

Updatesevery release of 2.x through this account

You can read the whole bundle before paying — the SKILL.md above is the product, not a preview of it. What the money buys is the delivery: the folder packaged and handed to your machine by key, every update its author ships, and our support if it does not do what this listing says. The terms of use are Apache-2.0, set by the author and unchanged by buying it here.

Payment runs through Stripe, on a page like this one rather than a redirect. Once there is an account it joins the same mcprush invoice as everything else you run, so there is never a second card to enter.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/

Claude Desktop

ChatGPT

Cursor.cursor/skills/

VS Code.github/skills/

Codex CLI.agents/skills/

Gemini CLI.gemini/skills/

Grok.grok/skills/

Zed.agents/skills/

Windsurf.windsurf/skills/

Agent SDK.claude/skills/

HTTP / API

This release

Version2.6.0

Publishedno release date on file

Price$15

Referencenvidia/rag-blueprint

Versions

v2.6.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v2.6.0

No earlier releases have been published to the marketplace.

Pinning

Put nvidia/rag-blueprint@2.6.0 in the install command to hold this exact version. Without the suffix you get whatever is current the day you install, and nothing moves under you afterwards.

Reviews

—no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Who wrote it

NVIDIA

Publishes on mcprush.

0 servers listed9 skills listednot claimed

Profile

Publisher

Servers0