A benchmark tool for a deployed NVIDIA RAG server. RAG, or retrieval-augmented generation, answers questions using information retrieved from a document collection.

Use it to profile processing stages and optionally run load tests that measure response time, token and request throughput, and errors.

It measures server performance in one report, so you do not need to assemble separate profiling and load-testing steps by hand.

rag-perf — Skill for Claude Code by NVIDIA-AI-Blueprints

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add NVIDIA-AI-Blueprints/rag --skill rag-perf

Clone the repo

git clone --depth 1 https://github.com/NVIDIA-AI-Blueprints/rag

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nvidia-ai-blueprints/rag/rag-perf/github.svg)](https://agentmods.dev/skills/nvidia-ai-blueprints/rag/rag-perf)

Your own site

<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/rag/rag-perf"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/rag/rag-perf/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/rag/rag-perf"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/rag/rag-perf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,124 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.04124
Opus 5	$0.00028	$0.02062
Sonnet 5	$0.00011	$0.00825
Haiku 4.5	$0.00006	$0.00412

Measured 9d ago against content hash 81f1d3a07186, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rag-perf scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Read Grep Glob Bash(ls *) Bash(python3 *) Bash(uv *) Bash(cat *) Bash(curl *) Write Edit

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

rag-perf — 88% identical, 84 lines differ

skills/rag-perf/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RAG-Perf — config-driven perf benchmark CLI

Purpose

Drive a deployed NVIDIA RAG Blueprint server with a YAML config, run a server-side profiling pass (per-stage timing, citation quality, bottleneck inference) and an optional aiperf load test (TTFT / E2E / token & request throughput / error rate), and write a unified report. The CLI is intentionally minimal: rag-perf -c <config> plus --help / --version. Behaviour is fully config-driven; field variations belong in YAML.

Scope

Accuracy / RAGAS scoring of answer quality → use the rag-eval skill.
Deploying, repairing, or configuring services (compose, helm, NIM env vars) → use the rag-blueprint skill.
Production monitoring / alerting — rag-perf is a one-shot benchmark tool.
Runtime requirement: a deployed RAG server reachable on the network.

Prerequisites

Repo cloned; run commands from the repo root (config paths in the presets are repo-root-relative).
Python 3.11+ and uv on PATH.
Install rag-perf into its own uv-managed venv: uv sync --project scripts/rag-perf.
For unit tests: install dev extras as well — uv sync --project scripts/rag-perf --extra dev (otherwise pytest-asyncio is missing and async tests error out at collection time).
A reachable RAG server (default http://localhost:8081). For the aiperf phase, the bundled nvidia_rag endpoint plugin must be installed — pip install -e ./scripts/rag-perf registers it via the aiperf.plugins entry point.
For synthetic queries: an OpenAI-compatible chat-completions endpoint reachable at synthetic.llm_url (default http://localhost:8999/v1/chat/completions).
rag-perf itself runs without NVIDIA_API_KEY (unlike rag-eval). The synthetic LLM endpoint may require its own auth — that's the deployment's concern.

Instructions

Pick a preset. The three under scripts/rag-perf/configs/ are:
- quick_profile.yaml — profile-only, ~30 s. Skips load test. For fast iteration on retrieval / reranker tuning.
- single_run.yaml — one concurrency level, profiling + aiperf, ~2 min. Regression checks.
- sweep.yaml — multi-axis sweep. load.concurrency, rag.vdb_top_k, rag.reranker_top_k are all int | list[int]; any of them as a list becomes a sweep axis (Cartesian product).

Read the full file on GitHub · 180 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 180 lines · 56 tokens per session scan A 81f1d3a07186

Subscribe to this mod's changes

rag-perf is a skill published in the GitHub repository NVIDIA-AI-Blueprints/rag (757 stars, last pushed 5d ago), licensed Apache-2.0. It adds 56 tokens to every session and 4,124 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI RAG and vectors Testing blueprint nim retrieval-augmented-generation

generate-rag-dataset

Generate a synthetic evaluation dataset from your RAG knowledge base. Creates diverse Q&A pairs with expected answers and relevant context, ready for LangWatch experiments and platform import. Use when you need test data for your RAG pipeline.

langwatch/langwatch · 51 tokens

neuron-test-engineer

Write tests for Neuron AI agents, RAG systems, workflows, and tools using the built-in testing utilities. Use this skill when the user mentions testing agents, writing unit tests, mocking AI providers, testing tool execution, verifying RAG retrieval, testing workflow behavior, or creating test cases for Neuron AI…

neuron-core/neuron-ai · 94 tokens

rag-eval

Use when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or "is my RAG…

agentscope-ai/OpenJudge · 86 tokens

session-rag-eval

Run and debug Chatbox session attachment RAG model evaluation with synthetic and real long-file fixtures.

chatboxai/chatbox · 25 tokens

rag-evaluate-quality

Periodically measure the retrieval quality of the knowledge base using evaluateretrieval (MRR@5, Recall@5, Precision@5) plus getindexstats for health metrics. Run weekly, after significant reindex activity, or when the user reports declining answer quality. Prevents silent index rot and grounds "should we tune X"…

lyonzin/knowledge-rag · 78 tokens

rag-index-decisions

After making a non-obvious architectural decision, solving a novel bug, agreeing on a coding standard, or reaching a conclusion worth remembering, index it back into the knowledge base so the next occurrence is one search away. Uses adddocument or addfromurl. Closes the feedback loop that makes a RAG-backed team…

lyonzin/knowledge-rag · 72 tokens

rag-perf