Перейти к содержимому
TakoAPI
Назад к навыкам

rag-eval

от jonathanjing

Coding Agents & IDEs
381Число загрузок по данным clawskills.sh
2Звёзды
1Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Evaluate your RAG pipeline quality using Ragas metrics (faithfulness, answer relevancy, context precision).

Описание

Что делает этот навык

Evaluates RAG pipeline output quality using Ragas metrics: faithfulness, answer relevancy, and context precision. Requires an existing RAG system with a vector DB and retrieval pipeline. An LLM serves as the judge, configurable via OpenAI, Anthropic, or a local model like Ollama.

Ragas applies LLM-graded metrics for faithfulness and relevancy that manual spot-checking or simple string matching cannot reliably replicate.

Когда его использовать

  • Checking if a chatbot's answers are supported by retrieved documents
  • Detecting hallucinations in RAG-generated responses before shipping
  • Running batch quality checks on a Q&A dataset ahead of deployment
  • Identifying irrelevant context chunks reducing retrieval precision
  • Tracking RAG output quality over time with daily scored logs

Пример сценария

ВВОД

User asks: Evaluate this RAG response — question: 'What is the return policy?', answer: 'Returns are accepted within 30 days.', contexts: ['Our policy allows returns within 30 days of purchase.']

АГЕНТ
  1. 1

    Write the question, answer, and contexts as JSON to /tmp/rag-eval-input.json

  2. 2

    Run python3 scripts/run_eval.py --input-file /tmp/rag-eval-input.json

  3. 3

    Parse output scores for faithfulness, answer_relevancy, context_precision, and overall_score

  4. 4

    Delete the temp file

  5. 5

    Present a human-readable summary with PASS/REVIEW/FAIL verdict

ВЫВОД

Faithfulness: 0.95 ✅, Answer Relevancy: 0.91 ✅, Context Precision: 0.88 ✅, Overall: 0.91 — PASS

Требования

  • OPENAI_API_KEY environment variable (default judge, uses GPT-4o)
  • ANTHROPIC_API_KEY environment variable (alternative judge, uses Claude Haiku)

Установка

clawhub install jonathanjing/rag-eval

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки