Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

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

Name: RAG, AI Agents and Generative AI with Python and OpenAI 2026
Rating: 4.5 (939 reviews)

Mastering Retrieval-Augmented Generation (RAG), Generative AI (Gen AI), AI Agents, Agentic RAG, OpenAI API with Python

Created byDiogo Alves de Resende

Last updated 9/2026

English

German [Auto],English [Auto],

What you'll learn

Build Retrieval-Augmented Generation (RAG) systems using Python and OpenAI.
Develop AI Agents with state management and memory using OpenAI Swarm.
Master Generative AI models like OpenAI GPTs for text generation.
Leverage Agentic RAG and LangChain for efficient retrieval systems.
Integrate Multimodal RAG using text, audio, and images with Whisper and CLIP models.
Build real-world projects, including a capstone project analyzing financial data.
Stay ahead with the latest advancements in AI, Generative AI, and AI Agents in 2026.
Develop AI Agents using CrewAI for advanced task automation and orchestration.
Deploy an Agentic RAG System with LangGraph for a Digital Waiter.
Fine-tune GPT models using Python for customized AI solutions.

Coding Exercises

This course includes our updated coding exercises so you can practice your skills as you learn.

Course content

46 sections • 403 lectures • 38h 0m total length

RAG, AI Agents and Generative AI with Python and OpenAI Promotional Video1:30
Explore realistic uses of AI, agents, and generative AI with Python and OpenAI, through hands-on projects and exercises that move beyond hype toward practical skills.
Course Overview: RAG, AI Agents and Generative AI with Python and OpenAI5:34
Master retrieval systems and information retrieval basics, including tokenization and pre-processing, and implement vector space, tf-idf, boolean, probabilistic models with Python to enable RAG and AI agent solutions.
[ACTION] Get Your Course Materials: RAG and Generative AI0:13
RAG and Generative AI Course Assistant Link0:08
Your RAG, AI Agents and Generative AI Course Assistant is Here6:35
Build an AI assistant that stores transcripts and Python files in a vector store, runs on GPT five, and deploys via Streamlit, with rag, file search, and multimodal techniques.
Diogo's Introduction and Background2:29
Diogo shares his background in management and analytics, highlighting data-driven decisions and experiments. He notes startup Betacom and insights like menu optimization, pricing, and invites you to connect on LinkedIn.
Unlimited Updates and Enhancements 20261:15
Deliver up-to-date content for 2026 on RAG, AI agents, and generative AI with Python and OpenAI, and invite your feedback to improve course quality.
Submit Your Update and Enhancement Requests Here0:05

Game for Python for RAG and AI2:04
Explore python for rag and gen AI with an optional appendix python crash course for beginners, and practice functions and classes with solutions on Google Colab.
Functions4:50
Discover how Python functions act as reusable building blocks, using parameters and returns to organize code, enable debugging, and support multi-step workflows.
Exercise 13:43
Practice writing Python functions by implementing calculate_sum to sum a list and calculate_area that returns the area, in hands-on labs.
Exercise 25:56
Tackle medium-level Python exercises by implementing string reversal using slicing and building an anagram finder that cleans spaces, lowercase, sorts, and compares two strings.
Exercise 35:02
Build a palindrome checker by cleaning input: remove non-alphanumeric characters, convert to lowercase, and compare the string to its reverse.
Introduction to Classes5:06
Explore how classes serve as blueprints and objects as instances in Python, using a Pokemon example to show attributes like name, type, and level, plus the init method and self.
Exercise 44:54
Define a book class with title, author, and pages, implement an init, and a book info method that returns an f-string; test by printing the attributes.
Exercise 54:49
Define a rectangle class with length and width, implement area and perimeter methods, and test by creating an instance and printing results with f-strings.
Exercise 67:17
Define a bank account class with an account holder and balance, implement deposit and withdraw with balance checks, and add a get balance method tested through simple scenarios.

Game Plan for Your First RAG3:28
Build a RAG architecture by combining retrieval and generation models to ground answers in a database of knowledge, then construct and optimize an AI agent and course assistant.
RAG4:15
RAG combines retrieval, augmentation, and generation to keep answers up to date, reduce hallucinations, and provide sources from your knowledge base across domains like healthcare, finance, and education.
RAG
Sign Up to Lovable0:03
Overview of Lovable3:12
My Favourite Prompt5:16
Develop a detailed initial prompt to define the ai system architecture, then brainstorm with a step by step qa prompt, plan features, and configure Lovable integrations.
Building your First Chatbot2:17
Build your first chatbot by creating a flow wise agent with retrieval via tools, memory, and document stores, exploring chunking and an Excel-based workflow on the free plan.
Chunking3:23
Split large documents into sections like a table of contents, so the AI jumps to relevant chunks, boosting speed and accuracy while avoiding the lost in the middle problem.
Chunking Text4:36
Learn to chunk text for retrieval-augmented generation using fixed window sizes, overlaps, and embeddings. See how vector stores and RAG work on text data with a private, no-code visualization tool.
Chunking
Embeddings3:45
Explore how embeddings turn words into numbers, placing related meanings near each other to power search, recommendations, chatbots, and answering questions, with context and large text training shaping the map.
Setting up the Embeddings3:34
Explore embeddings visualization using PCA to reduce 3072 dimensions to two, interpret vector relationships among nine chunks, and connect these insights to the RAG approach and architecture.
Embeddings
Vector stores3:14
Use vector stores to organize embeddings into a memory-like database that searches by meaning, enabling ai to retrieve relevant data and answer questions.
Visualizing Querying Text3:45
Visualizing querying text shows how a query is embedded into a vector, compared with all chunks to identify closest four, and used as context to build a prompt with citations.
Vector Stores
Setting CSV Data4:16
Setting Up Images2:42
Learn to integrate images in RAG workflows using Gemini multimodal embedding to extract image components and region tiles, then embed text plus image with a chosen grid size.
Setting Up PDF3:10
Testing the AI Assistants4:00
Test and refine AI assistants using an ingestion and retrieval pipeline, exploring prompt templates, file support (pdf, csv, images, docx, excel), and evidence-based answers with citations.
Adding the RAG to the AI Assistant5:52
Explore adding the RAG to an AI assistant by debugging embedding models, chunking, and ingestion, using Gemini embedding two via an open router to control LLM routing.
Finalizing the AI Assistant with RAG3:45
RAG

Game Plan for Prompt Engineering - System Message3:20
Explore prompt engineering to optimize interactions with large language models by defining a system message that sets the tone, role, and goals for reliable, relevant outputs in RAG agents.
What is the System Message?4:17
Explore how the system message acts as the rulebook that defines AI role, tone, and boundaries, shaping prompt structure, priorities, and outcomes for robust responses.
System Message in the Playground7:03
Explore the OpenAI playground chat models, including GPT five, five nano, and five mini, and learn how system and developer messages shape responses within a hidden hierarchy.
Building on your first RAG4:56
Plan and version a system message for a RAG assistant, maintain a single active version, and create a concise, reusable setup for beta startup courses and tools.
CHALLENGE Presentation - Tell me your secrets3:28
Learn how to hide the system message and prevent prompt injection by examining developer messages and game-like challenges that reveal hidden guidelines in AI conversations.
Link to Game App0:04
Tell Me Your Secrets Challenge

Requirements

Python Proficiency (For Loops, Functions)

Description

UPDATES SEPTEMBER 2026:

Flowise was sunset, so I added equivalent sections using Lovable, Cursor and Claude Code
Python Exercises remade.

UPDATES NOVEMBER 2025

2026 Version of the course was released with all code up to date.
OpenAI Responses Endpoint and GPT-5 implemented across the sections.
New no-code RAG with Flowise.
New Project with Streamlit.

UPDATES JUNE 2025

Launched 2 sections: Image Generation with OpenAI and Reasoning Models
MCP is now live!

UPDATES MAY 2025

Launch of 2 new sections: RAG with OpenAI File Search and RAGAS
Minor video remakes due to mistakes.

UPDATES APRIL 2025:

Remake of 3 sections: Retrieval Fundamentals, Generative Fundaments and Introduction to RAG
Added Knowledge Graphs with Light RAG

UPDATES DECEMBER 2024:

Fine Tuning OpenAI GPT-4o
Python Crash Course + Self-assessment

UPDATES NOVEMBER 2024:

CrewAI and CrewAI Capstone Project launched
The section on OpenAI API for Text and Images is live + OpenAI API Capstone Project

UPDATES OCTOBER 2024:

OpenAI Swarm is live
Agentic RAG is live
Multimodal RAG Project is live

Unlock the Power of RAG, AI Agents, and Generative AI with Python and OpenAI in 2026!

Welcome to "RAG, AI Agents, and Generative AI with Python and OpenAI 2026"—the ultimate course to master Retrieval-Augmented Generation (RAG), AI Agents, and Generative AI using Python and OpenAI's cutting-edge technologies.

If you aspire to become a leader in artificial intelligence, machine learning, and natural language processing, this is the course you've been waiting for!

Why Choose This Course?

Full-stack RAG: retrieval → augmentation → grounded generation with citations, sources, and guardrails.
OpenAI-first: GPT-5, Responses Endpoint, File Search vector stores, image generation, Whisper, CLIP.
No-code + code: Lovable, Claude Code and Cursor visual pipelines and Python implementations (Chroma, LangChain, Streamlit).
Evaluation-driven: RAGAS metrics (context precision/recall, response relevancy, factual correctness).
Agentic systems: CrewAI and OpenAI Swarm for multi-agent orchestration, tools, memory, and state.
Advanced GenAI: reasoning models (setup, prompting, verification), fine-tuning, MCP approvals, secure integrations.
Business outcomes: customer support copilots, knowledge search, policy Q&A, analytics assistants, finance research, content operations.

About Your Instructor

Hi, I'm Diogo, a data expert with a Master's degree in Management specializing in Analytics from ESMT Berlin.

With extensive experience tackling complex business challenges—from managing billion-euro sales planning to conducting A/B tests that led to significant investments—I bring real-world expertise to this course.

As a startup founder helping restaurants worldwide optimize menus and pricing through data insights, I'm passionate about leveraging AI for practical solutions.

Personalized Support

One of the key benefits of this course is the direct access to me as your instructor.

I personally respond to all your questions within 24 hours.

No outsourced support—just personalized guidance to help you overcome challenges and advance your skills.

Continuous Improvements

I'm dedicated to keeping this course up-to-date with the latest advancements in AI.

Your feedback shapes the course—I'm always listening and ready to add new content that benefits your learning journey.

Hands-on projects you actually ship

No-code Lovable RAG (zero to answers with citations).
OpenAI File Search RAG + Streamlit app (upload, index, chat).
Unstructured data RAG (Excel/Word/PPT/EPUB/PDF).
Multimodal RAG (Whisper + CLIP + cosine search).
CrewAI & Swarm agent systems (researcher, writer, counselor, product manager).
Reasoning model demos (setup, prompting, verification).
Image generation pipelines (single/batch edits, animated GIFs).
Fine-tuned GPT evaluation and testing.

What You'll Learn

RAG architecture: retrieval, augmentation, grounded generation, source citations, metadata.
Embeddings & vector stores: semantic search, nearest neighbors, FAISS, File Search.
Chunking strategies: fixed/semantic/hierarchical, overlaps, LongRAG.
System messages and prompt engineering: temperature, top-p, few-shot, persona.
Reasoning models: chain-of-thought controls, verification, structured output.
Agentic patterns: planning, tool use, memory/state, error handling.
MCP with approvals: safe external actions (web fetch, APIs, Stripe).
Evaluation with RAGAS: context precision/recall, relevancy, factual correctness.
Deployment: Streamlit, environment secrets, requirements, debugging.

Why Master RAG and AI Agents Now?

The future of AI lies in systems that can retrieve relevant information and generate intelligent responses—Retrieval-Augmented Generation is at the forefront of this revolution.

By mastering RAG, AI agents, and generative models, you position yourself at the cutting edge of technology, making you invaluable in today's tech landscape.

Get Started Today!

Lifetime Access: Enroll now and get lifetime access to all course materials and updates.
Interactive Learning: Engage with coding exercises, challenges, and real-world projects.
Support: Get your questions answered from me, Diogo, in less than 24 hours.
Certification: Receive a certificate upon completion to showcase your new skills.

Don't Miss Out!

The world of AI is advancing rapidly.

Stay ahead of the curve by enrolling in "RAG, AI Agents, and Generative AI with Python and OpenAI 2026" today. Unlock endless possibilities in AI and machine learning!

Enroll Now and transform your career with the most comprehensive RAG and Generative AI course available!

Who this course is for:

Data Scientists and Machine Learning Engineers looking to deepen their knowledge of generative AI systems.
AI Researchers and Enthusiasts interested in exploring the latest advancements in (RAG) and generative AI technologies.
oftware Developers and Programmers who want to expand their skill set to include AI and machine learning techniques.
Technical Product Managers and AI Strategists who manage AI projects and need a deeper technical understanding of how RAG systems work and their potential applications.
AI Consultants and Data Analysts aiming to add AI capabilities to their skillset
Entrepreneurs and business leaders in the tech space who want to understand the potential of RAG systems and generative AI to innovate.

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

What you'll learn

Explore related topics

Coding Exercises

Course content

RAG and Generative AI with Python8 lectures • 18min

Community1 lecture • 1min

Python for RAG and AI9 lectures • 44min

PART A - INTRODUCTION TO RAG1 lecture • 2min

Your First RAG with Flowise18 lectures • 1hr 5min

Scientific Literature Review - RAG1 lecture • 5min

Prompt Engineering - System Message6 lectures • 23min

Scientific Literature - LLMs3 lectures • 24min

Prompt Engineering - Temperature and Top P1 lecture • 9min

Prompt Engineering Techniques1 lecture • 3min

Requirements

Description

Who this course is for: