6.1 How to evaluate a RAG system: methods and metrics

Автор: Evidently AI

Загружено: 2025-05-20

Просмотров: 1867

Описание: 00:03 Intro
00:24 What is RAG?
01:03 How to evaluate RAG? Look at both sides.
01:34 Evaluating retrieval quality: ground truth-based evals.
02:23 Evaluating retrieval quality: labeling relevance.
02:55 Evaluating retrieval quality: LLM-labeled relevance / context quality judge.
03:55 Evaluating generation quality: ground truth-based evals.
04:36 Using synthetic data to create the test dataset.
05:10 Evaluating generation quality: faithfulness, completeness, etc.
06:09 Stress-testing RAG.
06:42 Recap

COURSE PLAYLIST
Full playlist: • Course: LLM evaluation for builders
Instructor: Elena Samuylova, CEO Evidently AI.

LINKS
Ranking metrics https://www.evidentlyai.com/ranking-m...
RAG evaluation https://www.evidentlyai.com/blog/open...

EVIDENTLY
Sign up for Evidently Cloud https://www.evidentlyai.com/register
Support Evidently on GitHub https://github.com/evidentlyai/evidently

Не удается загрузить Youtube-плеер. Проверьте блокировку Youtube в вашей сети.
Повторяем попытку...

6.1 How to evaluate a RAG system: methods and metrics

Доступные форматы для скачивания:

Скачать видео

Информация по загрузке:

Скачать аудио

Похожие видео

6.2. Tutorial: Building and evaluating a RAG system

6.2. Tutorial: Building and evaluating a RAG system

Все стратегии RAG объясняются за 13 минут (без лишних слов)

Все стратегии RAG объясняются за 13 минут (без лишних слов)

1. Introduction to LLM evaluations in 10 key ideas

1. Introduction to LLM evaluations in 10 key ideas

Do Reranking Models Actually Improve RAG?

Do Reranking Models Actually Improve RAG?

RAG Evaluation Metrics Explained: Context Precision, Recall, Relevancy & Faithfulness

RAG Evaluation Metrics Explained: Context Precision, Recall, Relevancy & Faithfulness

How to evaluate an LLM-powered RAG application automatically.

How to evaluate an LLM-powered RAG application automatically.

Экспресс-курс RAG для начинающих

Экспресс-курс RAG для начинающих

Session 7: RAG Evaluation with RAGAS and How to Improve Retrieval

Session 7: RAG Evaluation with RAGAS and How to Improve Retrieval

3. Tutorial: How to create an LLM judge and align with human labels

3. Tutorial: How to create an LLM judge and align with human labels

Feed Your OWN Documents to a Local Large Language Model!

Feed Your OWN Documents to a Local Large Language Model!

2 метода улучшения поиска в RAG

2 метода улучшения поиска в RAG

Course: LLM evaluation for builders

Course: LLM evaluation for builders

Finally a Local RAG That WORKS!! (+ FULL RAG Pipeline)

Finally a Local RAG That WORKS!! (+ FULL RAG Pipeline)

9 AI-навыков, которые должен освоить каждый в 2026 году

9 AI-навыков, которые должен освоить каждый в 2026 году

RAG Evaluation Sucks: Here's a Totally New Way to Do It - e17 RAG Masters

RAG Evaluation Sucks: Here's a Totally New Way to Do It - e17 RAG Masters

RAGAS: How to Evaluate a RAG Application Like a Pro for Beginners

RAGAS: How to Evaluate a RAG Application Like a Pro for Beginners

7 measurements that help minimize model risk for RAG

7 measurements that help minimize model risk for RAG

RAG vs Fine-Tuning vs Prompt Engineering: Optimizing AI Models

RAG vs Fine-Tuning vs Prompt Engineering: Optimizing AI Models

AI Agent Evaluation with RAGAS

AI Agent Evaluation with RAGAS

Самая сложная модель из тех, что мы реально понимаем

Самая сложная модель из тех, что мы реально понимаем