📘 LLMs, RAG & Agentic AI – Complete Course Content

Module 1: Introduction to Large Language Models (LLMs)

• What are LLMs?

• Understanding GPT, LLaMA, Mistral & other modern models

• How LLMs are trained (tokens, embeddings, attention mechanism)

• Strengths and limitations of LLMs

• Prompt Engineering basics

• Real-world use cases of LLMs

Module 2: Retrieval-Augmented Generation (RAG)

• Need for RAG and how it fixes LLM hallucinations

• How RAG works: Retrieve → Enhance → Generate

• Embeddings overview

• Chunking strategies and preprocessing

• Vector databases (FAISS, Chroma, Pinecone)

• Building a knowledge base from PDFs, websites, documents

• Creating embeddings and storing vectors

• Building a complete RAG pipeline

• Testing RAG responses

• Business applications (customer support, policy search, enterprise bots)