Cover image for Master Retrieval-Augmented Generation (RAG) Systems

Master Retrieval-Augmented Generation (RAG) Systems

Transform AI Applications with RAG: Expert Techniques in Information Retrieval and Generation

Paulo Dichone

Created by Paulo Dichone

Explore the world of Retrieval-Augmented Generation and learn how to build smarter AI applications that combine information retrieval with advanced answer generation. Move from foundational concepts to sophisticated techniques, gaining practical experience along the way. By the end, you will know how to design, implement, and optimize RAG systems for real-world use.

Packt | Jul 2024 | 99 min

What You Will Learn

You will work through practical exercises that reinforce each new concept, starting with basic RAG setups and moving to advanced optimization strategies. Real-world examples and project-based challenges help you apply what you learn, so you can confidently build and refine RAG systems for your own projects.

Key Features

  • Build and optimize RAG pipelines for accurate information retrieval and generation
  • Apply advanced techniques like query expansion and cross-encoder re-ranking
  • Integrate dense passage retrieval to improve AI application performance

Target Audience

Designed for AI professionals, data scientists, and NLP specialists with a solid grasp of Python and basic AI concepts. If you want to deepen your expertise in information retrieval and generation, and apply advanced RAG methods to complex problems, this course will help you reach your goals.

Related courses

Cover image for AI Chatbot with Apple Foundation Models, SwiftUI, and SwiftData
Cover image for Build an AI-Powered Goals App with Foundation Models in SwiftUI, iOS 26, and SwiftData
Cover image for OpenClaw for Developers: Create Your First AI Agent
Cover image for Claude Code Essentials: Your First AI-Assisted Coding Workflow
Cover image for Retrieval-Augmented Generation (RAG) for AI Engineers - Build Production-Ready Applications
Cover image for Applied Context Engineering for RAG & LLM Systems