AI Engineering: Retrieval Augmented Generation (RAG) for LLMs

Overview

Thrive in the AI era with this hands-on course that teaches you to build better AI applications using one of the most important AI techniques used in the real-world to supplement an AI model's knowledge with proprietary or new information: Retrieval Augmented Generation (RAG).

Combine generative AI models with Retrieval Augmented Generation to build smarter AI systems
Use OpenAI APIs for text generation and processing unstructured data
Master FAISS for efficient similarity searches in massive datasets
Apply prompt engineering techniques for optimal AI responses
Build real-world AI projects like chatbots and financial analysis tools
Explore advanced RAG concepts like multimodal and agentic RAG

Syllabus

Section 1: Introduction to Retrieval Augmented Generation (RAG) Systems

Course Outline
Exercise: Meet Your Classmates and Instructor
Meet Rubber Ducky! Your AI Course Assistant using RAG
Link to Your AI Course Assistant
Understanding Your Video Player
[ACTION] Download the Course Resources
Set Your Learning Streak Goal

PART A: BASICS OF PROMPT ENGINEERING, PYTHON AND OPENAI API

Who Is This Part For?

Section 2: Prompt Engineering Basics

Game Plan for Prompt Engineering Basics
Setting Up the OpenAI API
Few-Shot Prompting
Few-Shot in Practice
Role, Persona and Goal
Role, Persona and Goal in Practice
System Message
System Message in Practice
My Favourite Prompt

Section 3: Understanding LLMs Part 1

Understanding Transformers
Attention Mechanisms

Section 4: Python for RAG and GenAI

Game Plan for Python for RAG and GenAI
Loops
Loops: Easy Level
Loops: Medium Level - Part 1
Loops: Medium Level - Part 2
Loops: Hard Level
Functions
Functions: Easy Level - Part 1
Functions: Easy Level - Part 2
Functions: Medium Level - Part 1
Functions: Medium Level - Part 2
Functions: Hard Level
Introduction to Classes
Classes: Easy Level - Part 1
Classes: Easy Level - Part 2
Classes: Medium Level

Section 5: Understanding LLMs Part 2

OpenAI Tokenizer

Section 6: OpenAI API

Overview: Working with the OpenAI API
OpenAI API for Text
Setting Up OpenAI API Key
OpenAI API
Generating Text with OpenAI API
OpenAI API Parameters
OpenAI API for Images
With Image URL
With Image in Base64
Adding Few-Shot Prompting
What Did You Learn in this Section?

Section 7: Understanding LLMs Part 3

Playing the Dice, Rock, Paper, Scissors, and Guess the Number

Section 8: CAPSTONE PROJECT: Deploy With Lovable

Claim Your Free Credits
Project Presentation: Build a LinkedIn Post Writer App
UI Design via Image Generation
Lovable Build Prompt
Deploy on Lovable
Course Check-In

PART B - RAG

What to Expect of Part B

Section 9 - RAG with OpenAI File Search

OpenAI File Search
Project Presentation: Build a Mini Rubber Ducky
Vector Stores
Setup
Retrieving the Files Path
File and Vector Stores in OpenAI
Responses Endpoint with File Search

Section 10 - Deploy RAG with Streamlit

Setting Up on Cursor and Requirements
Building Your AI Web App
Virtual Environment and .env File
Configuring the Page
Session State and Vector Store
Start Building the App: Sidebar
Building the App: Chat Inputs
Building the App: Bot Common Kwargs
Building the App: Bot Answers
Building the App: System Instructions
GitHub Repository
Deploying to Streamlit

Section 11: Working With Unstructured Data

Overview: Working With Unstructured Data
Introduction to Langchain Library
Excel Data: Best Practices for Data Handling
Initial Setup for Data Processing
Loading Data
Developing a Retrieval System for Unstructured Data
Building a Generation System for Dynamic Content
Building Retrieval and Generation Functions
Working with Word Documents
Setting Up Word Documents for RAG
Working with PowerPoint Presentations
PowerPoint Setup for RAG
Working with EPUB Files
EPUB Setup for RAG
Working with PDF Files
PDF Setup for RAG
What Did You Learn in This Section?
Exercise: Imposter Syndrome

Section 12: Multimodal RAG

Overview: Multimodal RAG
Introduction to Multimodal RAG
Setup and Video Processing
Extracting Audio from Video
Compressing Audio Files
Transcribing Audio with OpenAI Whisper
Whisper Model
Extracting Frames from Video
Introduction to Contrastive Learning
Understanding the CLIP Model
Tokenizing Text for Multimodal Tasks
Chunking and Embedding Text
Embedding Images for Multimodal Analysis
Understanding Cosine Similarity in Multimodal Contexts
Applying Contrastive Learning and Cosine Similarity
Visualizing Text and Image Embeddings
Query Embedding Techniques
Calculating Cosine Similarity for Query and Text
GenAI Model Setup for Multimodal Tasks
Building a GenAI Model
What Did You Learn in This Section?

Section 13: Project - Starbucks Financial Data

Project Briefing: Starbucks Financial Data
Transcribing Audio with OpenAI Whisper
Embedding Transcription with CLIP
Converting PDF to Images
Embedding Images for Multimodal Analysis
Retrieval System
Preparing Context
Generative System

Section 14: Knowledge Graphs with LightRAG

Game Plan for Knowledge Graphs with LightRAG
Knowledge Graphs
Knowledge Graphs vs Embeddings
LightRAG Setup
What is LightRAG?
Setting the Working Directory
Local RAG
Knowledge Graph Visualization
Global and Hybrid RAG
Naive, Mix and Bypass RAG

Section 15: Agentic RAG

Overview: Agentic RAG
AI Agents
Agentic RAG
Setup, Data Loading and AgentState
State Management and Memory in Agentic Systems
Greeting The Customer
AI Agent that Checks the Question
AI Agent that Assesses the Validity of the Question
AI Agent that Generates the Answer
AI Agent that Improves the Answer
Asking User for More Questions
Testing and Improving Agentic RAG
Agentic RAG Recap - Key Learnings and Next Steps

Section 16: Deploy Agentic RAG with Vercel

Preparing the Prompt with ChatGPT or Gemini
Game Plan for Deploying Agentic RAG
UX Mock Ups with Stich
Setting Up with Cursor
Testing the App Locally
Final Debugging
Push to Github
Deploying to Vercel
Testing the App

Section 17: RAGAS

Game Plan for RAGAS
Assessing RAG with RAGAS
RAGAS Setup
RAG
Synthetic Data
Generating Synthetic Data
Answering Synthetic Dataset
ROUGE (Recall-Oriented Understudy for Gisting Evaluation) Score
ROUGE
LLM-Based Assessment
Simple Criteria Score - Part 1
Simple Criteria Score - Part 2
Factual Correctness
Rubrics Score
Semantic Similarity
Factual Correctness
Context Precision
Semantic Similarity
Context Recall
Context Precision
Response Relevancy
Context Recall
Response Relevancy
Key Learnings and Outcomes: RAGAS

Where To Go From Here?

Thank You!
Review This Course!
Become An Alumni
Learning Guideline
ZTM Events Every Month
LinkedIn Endorsements

Taught by

Diogo Resende

Reviews

Start your review of AI Engineering: Retrieval Augmented Generation (RAG) for LLMs

Go to class

Taught by

RAG, AI Agents and Generative AI with Python and OpenAI 2026

LLM Engineering with RAG: Optimizing AI Solutions

Large Language Models (LLMs) and Retrieval Augmented Generation (RAG)

RAG-Driven Generative AI

AI Engineering: Building AI Applications (LangChain, LLM APIs + more)

Introduction to Retrieval Augmented Generation (RAG)

From Zero to GenAI: 9 Unique Ways to Understand Large Language Models

12 Best Retrieval-Augmented Generation (RAG) Courses in 2026

Write Prompts That Actually Work: ZTM’s Prompt Engineering Bootcamp Review

12 Best ChatGPT & Prompt Engineering Courses for 2026

9 Best Vector Database Courses to Implement AI’s Searchable Memory

11 Best Courses to Master Embeddings and Transformer Models in 2026

Never Stop Learning.