Learn the fundamentals of Retrieve-Augmented Generation (RAG) for enhancing Large Language Models (LLMs). This course covers the core components, architecture, and implementation steps needed to build RAG systems. Gain practical experience connecting external knowledge sources to generative models.
Prerequisites Python & LLM concepts
Level:
RAG Fundamentals
Understand the motivation behind RAG and its core architecture.
Information Retrieval
Grasp the role of the retriever component and techniques for finding relevant information.
Vector Embeddings and Databases
Learn how text is vectorized and stored for efficient retrieval.
Generation Augmentation
Understand how retrieved context is integrated with the LLM prompt.
Basic RAG Pipeline Implementation
Build a simple RAG system using standard libraries and models.
Data Preparation for RAG
Learn techniques for chunking and preparing documents for retrieval.