sk Skill · NVIDIA-AI-Blueprints
rag-eval
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
Open on skills.sh ↗read 2026-09-18
- installs 8w
- 0
- 30-day movement
- starts with the next reading
- Related entries
- 2
- Connections
- 1
bashPythonragasragbenchmarkingblueprintnvidia-rag-blueprintevaluationnvidia
- Host repository
- NVIDIA-AI-Blueprints/rag
- Version
- 2.6.0
- Allowed tools
- Read Grep Glob Bash(ls *) Bash(python3 *) Bash(uv *) Write Edit
- Compatible with
- Repository checkout with uv, Python 3.11+, run from repo root, uv sync --project scripts/eval (eval deps live in scripts/eval/pyproject.toml), network to RAG, ingestor, and vdb endpoints, NVIDIA_API_KEY for RAGAS, optional RAG_EVAL_JUDGE_MODEL (default mistralai/mixtral-8x22b-instruct-v0.1).
- Licence
- Apache-2.0
- Host stars
- 767
- Host language
- Python