Data & Analysis ✓ NVIDIA · Official rag-evaluationragasretrieval-augmented-generationpythonfastapibenchmarkingcorpus-datasets

RAGAS RAG Quality Evaluator

Benchmark retrieval-augmented generation quality against filesystem datasets.

FollowSkills review · FSRS-2.0
Not recommended
45/ 100 5-point scale 2.3 / 5
Trust12 / 25 · 2.4/5

The documentation requires secure handling of NVIDIA_API_KEY, avoiding committed secrets, and discloses access to RAG, ingestor, vector-database, and judge endpoints. However, Bash, Write, and Edit are allowed, while force_ingestion/delete_collection can delete collections without an explicit confirmation, isolation, or rollback procedure, so points are deducted.

Reliability8 / 20 · 2.0/5

The main workflow, prerequisites, CLI parameters, and common failure signals are documented with useful diagnosis guidance. However, the supplied static material contains no executed key-path evidence or comprehensive tests; the BENCHMARK report is an overall FAIL and identifies duplication and structure issues, so the score remains below the static ceiling.

Adaptability9 / 15 · 3.0/5

The audience, dataset layout, outputs, exclusions, and semantic trigger terms are relatively precise. Chinese-language guidance is absent, and core evaluation depends on reachable RAG/ingestor services and NVIDIA judge APIs without mainland-China reachability or fallback guidance, so points are deducted.

Convention9 / 15 · 3.0/5

The skill has a version, Apache-2.0 license, author attribution, references, examples, limitations, and troubleshooting guidance. Maintenance responsibility and update path are mostly delegated to the external product repository; the BENCHMARK reports unexpected files, deeply nested references, and duplicate content, with publication still requiring review, so points are deducted.

Effectiveness4 / 15 · 1.3/5

The skill clearly covers dataset preparation, execution, quality tuning, result analysis, and error triage, which plausibly supports the core task. However, no representative directly usable output is verified, and the BENCHMARK is an overall FAIL with Tier 3 unavailable; conservative static scoring therefore remains low.

Verifiability3 / 10 · 1.5/5

The material provides source-path references, OpenAPI schema references, CLI documentation, and a static evaluation report, giving limited auditability. It provides no key-path test results, third-party execution evidence, or corroborating evidence types, and Tier 3 results are missing, so points are deducted.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 55f18499943e
Before you use it
  • Before execution, configure least-privilege access for Write/Edit, network calls, and collection deletion, and obtain confirmation before force_ingestion or delete_collection.
  • NVIDIA_API_KEY is sent to an external judge service; inject it through a secrets manager or uncommitted environment file and prevent leakage through logs, shell history, or outputs.
  • The BENCHMARK report is FAIL and lists duplicate content, deeply nested references, and unexpected files; fix these findings and rerun the full evaluation before publication.
  • Core functionality depends on RAG, ingestor, and NVIDIA API endpoints; verify mainland-China reachability and provide an offline or alternative judging path if they are unavailable.
See the full review method →

What does this skill do, and when should you use it?

rag-eval provides the filesystem-based evaluation workflow for NVIDIA RAG Blueprint. It expects each dataset directory to contain corpus/ and train.json, then runs evaluate_rag.py to produce RAGAS JSON results. Retrieval, reranking, query rewriting, and generation settings can be varied for quality comparisons. It is not intended for production monitoring, latency or throughput testing, or evaluations outside this directory contract.

It guides agents to prepare corpus/ and train.json, synchronize the evaluation dependencies with uv, and run scripts/eval/evaluate_rag.py. The evaluator connects to a RAG server and ingestor, reads the dataset, and produces JSON outputs including evaluation_data.json and rag_*_evaluation_summary.json. It also covers RAGAS metric review, tuning top_k, vdb_top_k, reranking, query rewriting, and generation parameters, plus triage for API keys, network and stream errors, collection mismatches, empty contexts, and incorrect ingestor URLs.

  1. A RAG engineer needs a repeatable quality benchmark for a local document corpus, including PDF-based content.
  2. An evaluator needs to compare RAGAS scores across top-k, reranking, or query-rewriting configurations.
  3. A developer needs to validate train.json, ingestion behavior, and generated contexts before comparing runs.
  4. An integration engineer needs a guided path for diagnosing RAG, ingestor, collection, or endpoint failures during evaluation.

What are this skill's strengths and limitations?

Pros
  • Provides a concrete workflow for the corpus/ + train.json filesystem contract.
  • Supports quality comparisons through retrieval, reranking, query rewriting, and generation controls.
  • Includes RAGAS JSON analysis guidance and practical triage for network, ingestion, and collection issues.
  • Clearly separates quality evaluation from latency, throughput, load testing, and production monitoring.
Limitations
  • Requires reachable RAG and ingestor services.
  • Requires NVIDIA_API_KEY, and scores depend on judge-model availability as well as retrieval quality.
  • Vector database and embedding choices are controlled by deployed service configuration, not this CLI alone.
  • The source does not provide evidence of an independent test suite or broad platform coverage for this skill.

How do you install this skill?

Use the repository README installation flow: npx skills add nvidia/skills. The CLI prompts for a skill and installation destination; select rag-eval. You can first run npx skills add nvidia/skills --list to browse the catalog. The source does not provide a prompt-free command specifically for rag-eval.

How do you use this skill?

From the RAG Blueprint repository root, run: uv sync --project scripts/eval; then execute uv run --project scripts/eval python scripts/eval/evaluate_rag.py --dataset-paths /path/to/my_dataset --host localhost --port 8081. The dataset directory must contain corpus/ and train.json. Set NVIDIA_API_KEY and make sure the RAG server and ingestor are reachable. Inspect a summary with python3 -m json.tool results/my_dataset/rag_my_dataset_evaluation_summary.json.

How does this skill compare with similar options?

Compared with rag-perf, rag-eval measures RAGAS quality while rag-perf covers latency, throughput, and load testing. Compared with rag-blueprint, rag-eval does not deploy or repair services.

FAQ

Can it evaluate any RAG API?
No. It is fixed to the corpus/, train.json, and evaluate_rag.py filesystem contract; the source explicitly excludes APIs outside that layout.
What does it require at runtime?
Python 3.11+, uv, reachable RAG and ingestor services, and NVIDIA_API_KEY for RAGAS.
What should I check when generated contexts are empty?
Check the collection, ingestion, top_k/vdb_top_k, and ensure ingestor_server_url has no /v1 suffix. Stale collections may also persist unless force_ingestion is used.
Is it suitable for production monitoring or performance load tests?
No. The skill explicitly excludes production monitoring, latency, throughput, and load testing.

More skills from this repository

All from NVIDIA/skills

Data & Analysis ✓ NVIDIA · Official

NeMo Data Designer Synthetic Data Skill

Build synthetic datasets and declarative data-generation pipelines from a natural-language description.

Data & Analysis ✓ NVIDIA · Official

Data Designer Synthetic Data Skill

Build synthetic datasets and data-generation pipelines from a natural-language specification.

Automation & Ops ✓ NVIDIA · Official

NVIDIA RAG Blueprint Operations

Deploy, configure, troubleshoot, and manage NVIDIA RAG Blueprint environments.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Installation Guide

Choose and verify the right NeMo Relay path for CLIs, language packages, and maintained frameworks.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Quick Start

Helps first-time NeMo Relay users prove observable execution value through the smallest suitable trial.

Data & Analysis ✓ NVIDIA · Official

DICOM Series Preflight

Header-only validation for one DICOM series before conversion or inference.

Dev & Engineering ✓ NVIDIA · Official

DALI Dynamic Mode Assistant

Helps agents write, review, and migrate NVIDIA DALI imperative dynamic-mode code.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Migration Assistant

Safely migrate NeMo Flow projects to NeMo Relay.

Dev & Engineering ✓ NVIDIA · Official

Earth2Studio Diagnostic Builder

Build Earth2Studio wrappers for single-step diagnostic data transformations.

Data & Analysis ✓ NVIDIA · Official

Earth2Studio Weather Data Fetch

Fetch validated weather and climate variables from Earth2Studio sources by time and data type.

Data & Analysis ✓ NVIDIA · Official

NVIDIA AI-Q Deep Research

Run deep research through a reachable local or self-hosted AI-Q Blueprint backend.

Dev & Engineering ✓ NVIDIA · Official

AMC Sample Dataset Calibration

Verify a running NVIDIA AutoMagicCalib service end to end with its bundled sample dataset.

Dev & Engineering ✓ NVIDIA · Official

Holoscan SDK Setup Guide

Inspects a Linux host and selects the most suitable Holoscan SDK installation path.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Typed Wrappers & Codecs

Add typed boundaries to NeMo Relay integrations while preserving predictable JSON middleware semantics and caller-visible behavior.

Dev & Engineering ✓ NVIDIA · Official

Omniverse Realtime Viewer

Routes USD viewer requests to the right architecture and guides rendering, interaction, UI, and validation.

Dev & Engineering ✓ NVIDIA · Official

CUDA-Q Quantum Onboarding

Guides developers from CUDA-Q installation to quantum kernels, GPU simulation, and real QPU execution.

Dev & Engineering ✓ NVIDIA · Official

Clinical ASR Flywheel: Environment Setup

Validate that a clinical ASR evaluation environment can complete a TTS-to-ASR round trip through NVIDIA-hosted speech services.

Data & Analysis ✓ NVIDIA · Official

TAO DAFT Dataset Converter

Guides AI agents through tao-daft conversion between supported NVIDIA TAO DAFT dataset formats.

Dev & Engineering ✓ NVIDIA · Official

AutoMagicCalib Video Calibration

Turn local multi-camera MP4 recordings into AutoMagicCalib calibration results through a REST API.

Data & Analysis ✓ NVIDIA · Official

DICOM CT Series to NIfTI Volume

Converts one CT DICOM series into a HU NIfTI volume with affine evidence.

Related skills