Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/NVIDIA-AI-Blueprints/ragnpx agentmods add skills/nvidia-ai-blueprints/rag/rag-evalWrote 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.
[](https://agentmods.dev/skills/nvidia-ai-blueprints/rag/rag-eval)<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/rag/rag-eval"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/rag/rag-eval.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00048 | $0.02343 |
| Opus 5 | $0.00024 | $0.01171 |
| Sonnet 5 | $0.00010 | $0.00469 |
| Haiku 4.5 | $0.00005 | $0.00234 |
Grade A, and why
rag-eval scanned grade A with 0 findings 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 6d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
On-disk RAG evaluation (corpus/ + train.json)
Purpose
Guide agents through NVIDIA RAG Blueprint filesystem benchmarks: preparing corpus/ and train.json, running scripts/eval/evaluate_rag.py, tuning retrieval and generation flags for quality comparisons, interpreting RAGAS JSON outputs, and triaging failures (HTTP/stream errors, empty contexts, collection mismatch, judge API).
For latency, throughput, and load testing, use the rag-perf skill (scripts/rag-perf, docs/performance-benchmarking.md) — not this skill.
When not to use
Do not use this skill for: deploying or repairing services (use rag-blueprint); evaluating APIs without the corpus/ + train.json layout; general ML experimentation unrelated to this evaluator; production monitoring/alerting; or latency/throughput benchmarking (use rag-perf).
Prerequisites
- Repo cloned; run commands from repo root (imports and paths assume this).
- Python 3.11+ and uv; eval deps:
uv sync --project scripts/eval. - Reachable RAG server and ingestor (defaults often
localhost:8081/8082). NVIDIA_API_KEYfor RAGAS (see credential hygiene); optionalRAG_EVAL_JUDGE_MODEL.- Dataset roots passed to
--dataset-pathseach containcorpus/andtrain.json.
Instructions
- Prepare data — Ensure each dataset directory matches the layout and
train.jsonrules inreferences/dataset-and-conversion.md. When sources arrive as public links (sites or dataset pages), materialize documents undercorpus/—prefer PDF for multimodal content so images stay embedded; convert CSV/JSONL/etc. using the patterns there. - Run eval —
uv run --project scripts/eval python scripts/eval/evaluate_rag.pywith--dataset-paths,--host, and--port. Seereferences/benchmark-execution.mdfor command examples, outputs, and errors. Usereferences/evaluate-rag-cli.mdfor flag-level detail. - Tune quality — Adjust
--top_k/--vdb_top_k, reranker and query-rewriting toggles, and generation overrides (--temperature,--top-p,--max-tokens) as documented inreferences/benchmark-execution.mdwhen comparing retrieval/generation configs for RAGAS scores. - Analyze results — Use
references/result-analysis.mdfor scripts; scanrag_*_evaluation_summary.jsonfor headline RAGAS metrics. - Triage errors — Use the error signal table and the Troubleshooting section below.
What ships with it
9 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.
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.
- 6d ago First seen · 131 lines · 48 tokens per session scan A 572126a6a3e1
rag-eval is a skill published in the GitHub repository NVIDIA-AI-Blueprints/rag (757 stars, last pushed 3d ago), licensed Apache-2.0. It adds 48 tokens to every session and 2,343 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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"…
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…
rag-code-review
When performing code review on a PR, diff, snippet, or "look at this change" request, first consult the corpus for related ADRs, coding standards, prior patterns, and similar files. Grounds review comments in the team's actual decisions instead of generic best practices. Trigger on any review-style request — "review"…
rag-deep-dive
Three-step multi-tool workflow — search the corpus, fetch the most relevant document in full, then find similar documents. Use when a single searchknowledge hit is not enough because the user asked a "how does X work end to end" or "explain the pattern" or "give me the full picture" question. Prevents shallow answers…
rag-check-first
Before answering any technical question, code request, architecture decision, or factual claim, call searchknowledge to check the local corpus. Trigger on any query that could be answered with prior work, indexed docs, ADRs, runbooks, or team context. Prevents hallucination and forces reliance on the indexed knowledge…
rag-cite-sources
Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section. Trigger whenever the response quotes, paraphrases, or acts on knowledge that came from a searchknowledge or getdocument call. Makes answers auditable and lets the user jump to source in one click.