Retrieval-Augmented Generation
Master the fundamentals of Retrieval-Augmented Generation (RAG) and learn how to build AI applications that generate accurate, context-aware responses using external knowledge. This course covers semantic search, embeddings, vector databases, RAG architecture, end-to-end workflows, and real-world use cases. Through hands-on coding labs, you'll build, debug, evaluate, and optimize a complete RAG pipeline while learning when to use RAG instead of a standalone LLM. By the end of the course, you'll have the practical skills to develop production-ready RAG applications powered by Large Language Models.
Why RAG?
FREE PREVIEWLab 1
RAG & it's Components
ENROLLMENT REQUIREDLab 2
What is Semantic Search?
ENROLLMENT REQUIREDLab 3
Vector Store and Embeddings
ENROLLMENT REQUIREDLab 4
Quiz 1
ENROLLMENT REQUIREDQuiz 1
RAG & its Real-World Use Cases
ENROLLMENT REQUIREDLab 5
RAG End-to-End Workflow & Tools
ENROLLMENT REQUIREDLab 6
RAG Concepts & Code Snippets
ENROLLMENT REQUIREDLab 7
Quiz 2
ENROLLMENT REQUIREDQuiz 2
RAG Code Lab Part 1
ENROLLMENT REQUIREDLab 8
RAG Code Lab Part 2
ENROLLMENT REQUIREDLab 9
Standalone LLM vs RAG
ENROLLMENT REQUIREDLab 10
Debugging RAG Pipeline
ENROLLMENT REQUIREDLab 11
Quiz 3
ENROLLMENT REQUIREDQuiz 3
RAG Evaluation
ENROLLMENT REQUIREDLab 12
RAG Evaluation Implementation Part 1
ENROLLMENT REQUIREDLab 13
RAG Evaluation Implementation Part 2
ENROLLMENT REQUIREDLab 14
Quiz 4
ENROLLMENT REQUIREDQuiz 4
Resources
ENROLLMENT REQUIREDLab 15