Intermediate

Retrieval-Augmented Generation (RAG)

Build RAG systems that ground LLM responses in external knowledge. Learn about document processing, embeddings, vector databases, and retrieval optimization.

Estimated Time 30 hours

Introduction

Build RAG systems that ground LLM responses in external knowledge. Learn about document processing, embeddings, vector databases, and retrieval optimization.

4 Lessons
30h Est. Time
4 Objectives
1 Assessment

By completing this module you will be able to:

Design and implement retrieval pipelines
Work with vector databases and semantic search
Optimize retrieval relevance and efficiency
Implement hybrid retrieval strategies

Lessons

Work through each lesson in order. Each one builds on the concepts from the previous lesson.

1

RAG Architecture and Vector Databases

55 min

Start Lesson
2

Building an End-to-End RAG Pipeline

55 min

Start Lesson
3

Advanced Retrieval Strategies

50 min

Start Lesson
4

RAG Evaluation and Optimization

50 min

Start Lesson

Recommended Reading

Supplement your learning with these selected chapters from the course library.

📖

Building Data-Driven Applications with LlamaIndex

Chapters 1-6

📖

Unlocking Data with Generative AI and RAG

Chapters 1-7

📖

RAG-Driven Generative AI

Chapters 1-5

Module Assessment

Retrieval-Augmented Generation (RAG)

Question 1 of 3

What is the primary purpose of RAG systems?