Retrieval Augmented Generation (RAG)

Source: https://www.deeplearning.ai/courses/retrieval-augmented-generation

What you’ll learn

RAG for real-world applications: Learn how retrieval and generation work together, and how to design each component to build reliable, flexible RAG systems.
Search techniques and vector databases: Use techniques like keyword search, semantic search, hybrid search, chunking, and query parsing to support RAG applications across domains like healthcare and e-commerce.
Prompt design, evaluation, and deployment: Craft prompts that make the most of retrieved context, evaluate RAG system performance, and prepare your pipeline for production.

This course, taught by AI engineer and educator Zain Hasan, gives you the hands-on experience and conceptual understanding to design, build, and evaluate production-ready RAG systems.

You’ll learn to choose the right architecture for your use case, work with vector databases like Weaviate, experiment with prompt and retrieval strategies, and monitor performance using tools like Phoenix from Arize.

Throughout the course, you’ll build progressively more advanced components of a RAG system, using real-world datasets from domains like e-commerce, media, and healthcare. You’ll also explore critical tradeoffs, like when to use hybrid retrieval, how to manage context window limits, and how to balance latency and cost, preparing you to make informed engineering decisions in practice.