RAG Blueprint

NVIDIAOfficialCreated by NVIDIA RAG

Skill
Tool integration
Automation and integrations
Apache-2.0
Medium risk

From the author

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).

— the description by NVIDIA RAG

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The NVIDIA RAG Blueprint skill provides a structured operational framework for managing RAG services. It automates the detection of deployment environments (Docker, Helm, or library-based) and guides users through installation, configuration, troubleshooting, and teardown procedures. By mapping user intent to specific reference documentation and configuration files, it ensures consistent management of features like Agentic RAG, VLM, guardrails, and ingestion pipelines.

What it does

Deploys and manages RAG services using Docker Compose or Helm charts.
Configures specific RAG features such as Agentic RAG, VLM, and NeMo Guardrails.
Troubleshoots service health and connectivity issues.
Provides automated environment detection to identify active services and configuration locations.
Supports lifecycle management including startup, shutdown, and teardown of RAG infrastructure.
Validates configuration changes against live service states.

When to use it

When you need to deploy or tear down an NVIDIA RAG Blueprint environment.
When you need to enable or toggle specific features like Agentic RAG or VLM.
When a RAG service is reporting errors or is in an unhealthy state.
When you need to update configuration settings for models, search, or observability.

Advantages

Standardizes operational procedures across different deployment types.
Reduces manual configuration errors by referencing source-of-truth documentation.
Automates environment discovery to quickly identify the correct configuration files.
Provides clear paths for both global deployment-wide changes and per-request overrides.

Usage examples

“Deploy the RAG Blueprint.”: The agent will read the deployment documentation and initiate the setup process based on the detected environment.
“Enable Agentic RAG.”: The agent will identify the current deployment mode, locate the relevant configuration file, and guide you through enabling the agentic pipeline.
“My RAG service is unhealthy.”: The agent will run diagnostic checks on the containers or pods and suggest troubleshooting steps based on the error state.
“Stop all RAG services.”: The agent will execute the shutdown sequence to safely tear down the RAG infrastructure.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/nvidia/rag-blueprint/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip rag-blueprint.zip -d .agents/skills

Documentation by NVIDIA RAG

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

Match the user request to the intent routing table below.
Read the referenced playbook before making changes.
Use repository docs and deployment config files as the source of truth.
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

Auto-detect everything: GPU, VRAM, drivers, Docker, CUDA, disk, OS, ports, existing services, NGC key, repo state.
If it can be checked with a command, check it — don't ask the user.
Ask only when user action is required: providing an API key, confirming data deletion, or choosing between equally valid options.
Once analysis is done, route to the correct workflow and execute.

Intent Detection

Determine what the user wants and route immediately:

User Intent	Action
Deploy, install, set up, start RAG	Read and follow `references/deploy.md`
Configure, enable, change, toggle a feature	Use the Configure section below
Troubleshoot, debug, fix, error, unhealthy	Read and follow `references/troubleshoot.md`
Stop, shutdown, tear down, clean up	Read and follow `references/shutdown.md`

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

Configure

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

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

Feature Keywords	Reference
VLM, VLM embeddings, image captioning	`references/configure/vlm.md`
NeMo Guardrails	`references/configure/guardrails.md`
Agentic RAG, planning/execution agent, agentic streaming, stage events	`references/configure/agentic-rag.md`
Query rewriting, decomposition, multi-turn	`references/configure/query-and-conversation.md`
Ingestion (text-only, audio, Nemotron Parse, OCR, batch CLI, NV-Ingest, volume mount, performance)	`references/configure/ingestion.md`
Search, retrieval, hybrid search, multi-collection, metadata, filters, Elasticsearch filters, reranker, topK, accuracy/performance	`references/configure/search-and-retrieval.md`
LLM/embedding/ranking model changes, vector DB, Milvus/Elasticsearch auth, service keys, model profiles, ports/GPU	`references/configure/models-and-infrastructure.md`
Reasoning, thinking mode, `reasoning_content`, self-reflection, prompts, generation params (tokens, temperature, citations), per-request LLM params	`references/configure/reasoning-and-generation.md`
Summarization	`references/configure/summarization.md`
Observability (tracing, Zipkin, Grafana, Prometheus)	`references/configure/observability.md`
Multimodal query (image + text)	`references/configure/multimodal-query.md`
Data catalog (collection/document metadata)	`references/configure/data-catalog.md`
User interface (UI settings, reasoning panel, metadata filters)	`references/configure/user-interface.md`
API reference (endpoints, schemas)	`references/configure/api-reference.md`
Evaluation (RAGAS metrics)	`references/configure/evaluation.md` (and skill `rag-eval`)
MCP server & client, agent toolkit	`references/configure/mcp.md`
Migration (version upgrades)	`references/configure/migration.md`
Notebooks (setup and catalog)	`references/configure/notebooks.md`

Configure Flow

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

Detect what's running:

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"

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

Local NIMs running?	RAG services running?	Deployment Type	Config Location
Yes (Docker)	Any	Self-hosted	`deploy/compose/.env`
No	Yes (Docker)	NVIDIA-hosted	`deploy/compose/nvdev.env`
Yes (K8s pods)	Any	Self-hosted	`values.yaml` (NIM sections)
No	Yes (K8s pods)	NVIDIA-hosted	`values.yaml` (envVars)
—	Library processes	Library mode	`notebooks/config.yaml`
No	No	Not running	Deploy first via `references/deploy.md`

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?"

Check current feature state before changing anything — read the config location from step 3, then cross-check the live service:
- Docker: docker exec rag-server env 2>/dev/null | grep -E "<VAR_NAME>"
- Helm: kubectl get pod -n rag -l app=rag-server -o jsonpath='{.items[0].spec.containers[0].env}' 2>/dev/null
If the config file and live service disagree, tell the user the service has stale config and will need a restart.

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

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

Read the reference file and apply changes:

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:

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

Service	Compose File
rag-server	`docker-compose-rag-server.yaml`
ingestor-server	`docker-compose-ingestor-server.yaml`
Elasticsearch, Milvus, etcd, SeaweedFS	`vectordb.yaml`
NIM containers (LLM, embedding, ranking, VLM, OCR, parse, audio, extraction)	`nims.yaml`
guardrails	`docker-compose-nemo-guardrails.yaml`
observability (Grafana, Prometheus, Zipkin)	`observability.yaml`

Helm: edit values.yaml, then upgrade: helm upgrade rag <chart> -n rag -f values.yaml
Library: edit notebooks/config.yaml, then restart the Python process

Verify:
- 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
- Helm: kubectl get pods -n rag; kubectl rollout status deployment/rag-server -n rag --timeout=120s
- Library: curl -s http://localhost:8081/v1/health 2>/dev/null | head -1
If restart fails, read references/troubleshoot.md. If multiple features requested, repeat from step 1 for each.

Examples

"Deploy RAG" -> route to references/deploy.md.
"Enable VLM" -> route to references/configure/vlm.md.
"RAG is unhealthy" -> route to references/troubleshoot.md.
"Stop RAG" -> route to references/shutdown.md.

Limitations

Operational guidance only applies to this RAG Blueprint repository.
Live deployment changes require a running Docker, Helm, or library target.
Secrets such as NGC_API_KEY must be supplied by the user environment.

Troubleshooting

Error / signal	What to do
Services are not running	Follow `references/deploy.md` before configuring features.
Restart or health check fails	Follow `references/troubleshoot.md`.
User requests teardown	Follow `references/shutdown.md` and confirm destructive cleanup.

When User Says "Configure" Without Specifics

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

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

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

Hardware Restrictions

Read docs/support-matrix.md for current GPU requirements per deployment mode. Read docs/service-port-gpu-reference.md for port mappings and GPU assignments.

GPU	Feature Restrictions
B200	No VLM, No Guardrails, No Nemotron Parse. May need multi-GPU LLM (`LLM_MS_GPU_ID`).
RTX PRO 6000	No Nemotron Parse. No Audio on Helm.

Files

ATTRIBUTION.mdAdded by AutoGineer901 B
BENCHMARK.md4.6 KiB
LICENSELicence file added by AutoGineer11.2 KiB
SKILL.md11.1 KiB
eval/h100.json2.5 KiB
eval/nvidia_hosted.json3.6 KiB
references/configure/agentic-rag.md5.0 KiB
references/configure/api-reference.md1.6 KiB
references/configure/data-catalog.md1.7 KiB
references/configure/evaluation.md2.8 KiB
references/configure/guardrails.md1.6 KiB
references/configure/ingestion.md3.6 KiB
references/configure/mcp.md1.3 KiB
references/configure/migration.md1.6 KiB
references/configure/models-and-infrastructure.md4.6 KiB
references/configure/multimodal-query.md2.0 KiB
references/configure/notebooks.md2.8 KiB
references/configure/observability.md1.4 KiB
references/configure/query-and-conversation.md3.7 KiB
references/configure/reasoning-and-generation.md3.8 KiB
references/configure/search-and-retrieval.md4.0 KiB
references/configure/summarization.md2.1 KiB
references/configure/user-interface.md1.7 KiB
references/configure/vlm.md3.6 KiB
references/deploy.md7.9 KiB
references/deploy/docker-nvidia-hosted.md2.2 KiB
references/deploy/docker-retrieval-only.md1.6 KiB
references/deploy/docker-self-hosted.md2.3 KiB
references/deploy/docker.md4.3 KiB
references/deploy/helm-mig.md2.0 KiB
references/deploy/helm-openshift.md3.6 KiB
references/deploy/helm-standard.md2.3 KiB
references/deploy/helm.md5.6 KiB
references/deploy/library-full.md2.2 KiB
references/deploy/library-lite.md1.8 KiB
references/deploy/library.md2.2 KiB
references/shutdown.md4.7 KiB
references/troubleshoot.md8.8 KiB
skill-card.md3.1 KiB
skill.oms.sig12.5 KiB

skill.oms.sig

{"mediaType":"application/vnd.dev.sigstore.bundle.v0.3+json","verificationMaterial":{"x509CertificateChain":{"certificates":[{"rawBytes":"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"},{"rawBytes":"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"},{"rawBytes":"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"}]},"tlogEntries":[]},"dsseEnvelope":{"payload":"{
  "_type": "https://in-toto.io/Statement/v1",
  "subject": [
    {
      "name": "rag-blueprint",
      "digest": {
        "sha256": "bbeafe60f76273bad075e2868130208b251b422923d1aeaab4f95f1fc4953df4"
      }
    }
  ],
  "predicateType": "https://model_signing/signature/v1.0",
  "predicate": {
    "resources": [
      {
        "algorithm": "sha256",
        "digest": "ad9dead0a8f17e4d3edd2430d4165a6c39ec051fa634e2accc3f6f34456a91c9",
        "name": "BENCHMARK.md"
      },
      {
        "algorithm": "sha256",
        "digest": "7167ef6b9d4f30ffe47b698ae7fdf9f0beafe4ea9a75752a056d0e4f03d6e51b",
        "name": "SKILL.md"
      },
      {
        "algorithm": "sha256",
        "digest": "d7fc33d23564eef5226b44154fc90adbe512fc4c76410f6271e99ac6bdec8cde",
        "name": "eval/h100.json"
      },
      {
        "algorithm": "sha256",
        "digest": "2129a48b92c0980285af7b9e4044feb94e7ce18d16fa034c731b04e5a0d219bc",
        "name": "eval/nvidia_hosted.json"
      },
      {
        "algorithm": "sha256",
        "digest": "6931cff1cb011b9deab888194ebe9bb8850b90125aafc3441ae26f83953908ec",
        "name": "references/configure/agentic-rag.md"
      },
      {
        "algorithm": "sha256",
        "digest": "b54c77326d2798d42e4f2a6aafe63426b3b80c09aa56e005fe686ebe2b611dc5",
        "name": "references/configure/api-reference.md"
      },
      {
        "algorithm": "sha256",
        "digest": "995dda145af478d4f143719c6ea91e8f690d7ab735f5a36d2c188e0c8574462f",
        "name": "references/configure/data-catalog.md"
      },
      {
        "algorithm": "sha256",
        "digest": "5a60598df857fb8dea95f73bf12b474ec6e8cf1616ce274e94bdf8e59616e0d9",
        "name": "references/configure/evaluation.md"
      },
      {
        "algorithm": "sha256",
        "digest": "81a9b41d645fe98519a5b30c9dd08c0cc7884d0a08962a1df1826f533c5dc044",
        "name": "references/configure/guardrails.md"
      },
      {
        "algorithm": "sha256",
        "digest": "c6638264d20e2ce3a60ff8c71c4570a851d80e2f0b236ff3dce8f10c73b5b79f",
        "name": "references/configure/ingestion.md"
      },
      {
        "algorithm": "sha256",
        "digest": "d56b81476c5da1fb4a539abd9108e6feeedea7619b99f5f5b021aa6c7ed6e802",
        "name": "references/configure/mcp.md"
      },
      {
        "algorithm": "sha256",
        "digest": "23ebc0eb94fa5095111dc9fb7d68fe01f7576958f8f5384c9abbfe78bac00e98",
        "name": "references/configure/migration.md"
      },
      {
        "algorithm": "sha256",
        "digest": "bd97b44294969473eeb671d3fb9ce18afd67fe2a212ef90f871f82b69a5a3091",
        "name": "references/configure/models-and-infrastructure.md"
      },
      {
        "algorithm": "sha256",
        "digest": "b8aff8ae28d07d1ab94cdc3d3b3ab7fa51e8df90560066e51291fff27d62afc5",
        "name": "references/configure/multimodal-query.md"
      },
      {
        "algorithm": "sha256",
        "digest": "699c61ee8b5535e162553bc3a4a92894953a3071319a4147b368595ad167eacf",
        "name": "references/configure/notebooks.md"
      },
      {
        "algorithm": "sha256",
        "digest": "f1c2d3617770b4e660212ccde6d7ce3c363be2fd2fab28901fd3d767e0b5922a",
        "name": "references/configure/observability.md"
      },
      {
        "algorithm": "sha256",
        "digest": "5024c059e00b9bf6a92a76085ec3be027ac1e560026c2c1339b0732d7d61264b",
        "name": "references/configure/query-and-conversation.md"
      },
      {
        "algorithm": "sha256",
        "digest": "f321410ce645d2c2d4042ca1474dfb72abc3da28b07fae58bce63a28b725164c",
        "name": "references/configure/reasoning-and-generation.md"
      },
      {
        "algorithm": "sha256",
        "digest": "318453642a660c430e004507f85df3ba5e534cc0a284cfb27d2fa4cff3d55ccd",
        "name": "references/configure/search-and-retrieval.md"
      },
      {
        "algorithm": "sha256",
        "digest": "97f43900f70b3eb02dfe71e367ca9045ec2cea457afbca4a9c43c19aa4b3cd56",
        "name": "references/configure/summarization.md"
      },
      {
        "algorithm": "sha256",
        "digest": "165312d168210a6324084c6b02335419499ffb09d4e4d4f594f685c9f1b72ef4",
        "name": "references/configure/user-interface.md"
      },
      {
        "algorithm": "sha256",
        "digest": "e0af2f8143871c1381245ca4c5e973bf1361e8adeadea8378113e668d3b0881f",
        "name": "references/configure/vlm.md"
      },
      {
        "algorithm": "sha256",
        "digest": "0ff4900057c89f5b13d7997f421692e5d5301f018214b20e221b8456864e9b90",
        "name": "references/deploy/docker-nvidia-hosted.md"
      },
      {
        "algorithm": "sha256",
        "digest": "44d629a51b746e89ed2680669598958661e4c4064eac58c23b2548675399026d",
        "name": "references/deploy/docker-retrieval-only.md"
      },
      {
        "algorithm": "sha256",
        "digest": "1fd41a62734cc0cfb19d2333938191ec47dbe3a00f54f93aa7bf15ce0b1c18f1",
        "name": "references/deploy/docker-self-hosted.md"
      },
      {
        "algorithm": "sha256",
        "digest": "96fe558100135ccfe767212b9b83ffd5c0540e2b36b9b329cbbe6cde4a310d49",
        "name": "references/deploy/docker.md"
      },
      {
        "algorithm": "sha256",
        "digest": "d1b0fdff3e5486c160623a68021226adb5ccff71a4ac44c6a8e30516081ff962",
        "name": "references/deploy/helm-mig.md"
      },
      {
        "algorithm": "sha256",
        "digest": "bce3e5b8a788628a372e12e032f81c610a8abcbd29888c16178b5a8dc45324ea",
        "name": "references/deploy/helm-openshift.md"
      },
      {
        "algorithm": "sha256",
        "digest": "54744f31ee5825c9a44a80ef851ecd9a34beb645e8c6cc2b65b278266ae497d1",
        "name": "references/deploy/helm-standard.md"
      },
      {
        "algorithm": "sha256",
        "digest": "edcdaa8aecde194b519e93243b820e5d23763e52aa7984d11b82d94e250933cb",
        "name": "references/deploy/helm.md"
      },
      {
        "algorithm": "sha256",
        "digest": "7bc35d06548d0fbf9e5e4804566fee1a8ad66085aa6c5ab91ff91788778b88b9",
        "name": "references/deploy/library-full.md"
      },
      {
        "algorithm": "sha256",
        "digest": "c7cd255ad8f43e0120b1caeae268874275090acd24acf54091a47771f3de3bb0",
        "name": "references/deploy/library-lite.md"
      },
      {
        "algorithm": "sha256",
        "digest": "a98a09d5bd9b519bc3920481c3fcd7b0973760f10de6ce6858748f9a001c5672",
        "name": "references/deploy/library.md"
      },
      {
        "algorithm": "sha256",
        "digest": "e6b6dcc479b2ee051e82d15bc35bad1ce32f7c256bdbbf32f4e25893fee1e8ea",
        "name": "references/deploy.md"
      },
      {
        "algorithm": "sha256",
        "digest": "c793fafa494c15736ddb4ee685f28fbcf04584f9ca318f7437a0e2f8b7e0f1e4",
        "name": "references/shutdown.md"
      },
      {
        "algorithm": "sha256",
        "digest": "cb2811af3036ce6c74998a9d5b9f58c84cd67b49ee8c515373ab24d7020b56bf",
        "name": "references/troubleshoot.md"
      },
      {
        "algorithm": "sha256",
        "digest": "729c059cee28eb26064d88ff0f37b81c10fc4cab26818028fe453ff596c8f835",
        "name": "skill-card.md"
      }
    ],
    "serialization": {
      "ignore_paths": [
        ".github",
        ".gitignore",
        ".git",
        ".gitattributes"
      ],
      "method": "files",
      "hash_type": "sha256",
      "allow_symlinks": false
    }
  }
}","payloadType":"application/vnd.in-toto+json","signatures":[{"sig":"MGUCMQCPltQrBh3tHHs9HLRsEtnYy2iIIWE345qscBUs+5sKfzYlkD9tsIpA9ledeOJf+JcCMDTZzHDyFZjbkaxjK6q9AA08pzsetK6v+KJBKEGzAq9ijZfR/XH5oNNfSIAJWyB5Og==","keyid":""}]}}

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Declares allowed tools, Needs an MCP server, Needs network access, Needs an API key

The author says: 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.

Security

What our scanner noticed· Medium risk

Large base64-encoded blobs
Instructions that use the network

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by

NVIDIA RAG

Publisher

NVIDIA (Official)

Source

NVIDIA/skills · skills/rag-blueprint · commit fce3cca

Licence

Apache License 2.0 (redistribution allowed)

LICENSE (added by AutoGineer from LICENSE-APACHE)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-09

AutoGineer is not affiliated with or endorsed by NVIDIA RAG or NVIDIA.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download rag-blueprint.zip