Skip to content
UdemyData SciencePaid courseExpert levelCertificate

Advanced Retrieval Augmented Generation (Udemy.com)

How to make Advanced RAG work in practice with Evaluations, Agentic Patterns and Generative AI with LLM

Created by: Rémi Connesson

Last updated June 2025

icon
What you will learn

  • You will learn how to increase the robustness of you LLM calls by implementing structured outputs, acing, caching and retries
  • How to generate synthetic data to establish a baseline for your RAG system, even if your RAG system don't have users yet
  • How to filter out redundant generated data
  • How to make all your LLM calls faster AND cheaper using asynchronous Python and caching
  • How to not be held back by OpenAI rate limits

How it compares

Against the other 461 rated Udemy courses in Data Science on CourseDuck:

  • Rating4.4 out of 5higher than 28% of them
  • Reviews96#428 of 462 by number of reviews
  • Length10.5 hourslonger than 58% of them
  • Last updatedJune 2025earlier than 56% of them

icon
Course Description

Master Advanced Retrieval Augmented Generation (RAG) with Generative AI & LLM

Unlock the Power of Advanced RAG Techniques for Robust, Efficient, and Scalable AI Systems

Course Overview:

Dive deep into the cutting-edge world of Retrieval Augmented Generation (RAG) with this comprehensive course, meticulously designed to equip you with the skills to enhance your Large Language Model (LLM) implementations. Whether you're looking to optimize your LLM calls, generate synthetic datasets, or overcome common challenges like rate limits and redundant data, this course has you covered.

What You'll Learn:

  • Implement structured outputs to enhance the robustness of your LLM calls.

  • Master asynchronous Python to make your LLM calls faster and more cost-effective.

  • Generate synthetic data to establish a strong baseline for your RAG system, even without active users.

  • Filter out redundant generated data to improve system efficiency.

  • Overcome OpenAI rate limits by leveraging caching, tracing, and retry mechanisms.

  • Combine caching, tracing, and retrying techniques for optimal performance.

  • Secure your API keys and streamline your development process using best practices.

  • Apply advanced agentic patterns to build resilient and adaptive AI systems.

Course Content:

  • Introduction to RAG and Structured Outputs: Gain a solid foundation in RAG concepts and learn the importance of structured outputs for agentic patterns.

  • Setup and Configuration: Step-by-step guidance on setting up your development environment with Docker, Python, and essential tools.

  • Asynchronous Execution & Caching: Learn to execute multiple LLM calls concurrently and implement caching strategies to save time and resources.

  • Synthetic Data Generation: Create high-quality synthetic datasets to simulate real-world scenarios and refine your RAG system.

  • Advanced Troubleshooting: Master debugging techniques for async code and handle complex challenges like OpenAI rate limits.

Requirements:

  • A modern laptop with Python installed or access to Google Drive.

  • Experience as a software engineer (2+ years preferred).

  • Intermediate Python programming skills or ability to learn quickly.

  • Basic understanding of data science (precision, recall, pandas).

  • Access to a pro version of ChatGPT or equivalent LLM tools.

Who Should Enroll:

  • Software engineers with experience in basic RAG implementations who want to advance their skills.

  • Data scientists and AI professionals looking to optimize their LLM-based systems.

  • Developers interested in mastering the latest RAG techniques for robust, scalable AI solutions.

Join this course today and transform your AI systems with the latest Advanced RAG techniques!

icon
Udemy Discount

The discount is applied through our link. Open the course from here and Udemy's current promotional price is applied at checkout on most courses, no code to type.

Some courses are excluded from Udemy's promotions. If the price does not drop, clear your browser cookies and use the button again.

icon
Instructor Details

Rémi Connesson

Rémi Connesson est un autodidacte en Machine Learning et Intelligence Artificielle. Des bases de Python jusqu'au Deep Learning , il s'est formé et a pratiquement tout appris en suivant des cours en ligne. Après avoir lancé avec succès son activité de Freelance en IA il y a 2 ans, il décide de rendre la pareille et d'à son tour proposer des cours en lignes pour aider les pays francophones à prendre la vague de l'IA.

Diplômé d'une grande école d'ingénieur, il en sort à une époque où, excepté dans les écoles d'élites dont il ne fait pas parti, les cursus académiques n'ont pas encore attrapé le tournant de l'Intelligence Artificielle.

Résultat, malgré son diplôme flambant neuf, il part litéralement de zéro en IA. Curieux à propos du domaine qu'il sent d'avenir, il décide de faire des recherches sur les manières de débuter dans le milieu et se heurte très vite à des réponses péremptoires décourageantes :

- "Il faut faire au moins 8 ans d'études pour faire de l'IA"

- "Il faut un QI plus élevé que celui d'Einstein"

- "Il faut absolument tout connaître en maths, en programmation et même en neurologie."

Amoureux de l'effort, de l'apprentissage de nouvelles compétences et de l'acquisition efficace de connaissances, il décide malgré tout de tenter sa chance et de se mettre au boulot.

icon
More Data Science courses

Free

Free

Free

Free

$124.99

Free

icon
Reviews

4.4

96 ratings on Udemy

Select a bar to show only those reviews.Select the bar again to show every rating.

By Cor van der Meer on 6/17/2026

good pace, clearly explained basic of the concepts

By Anonymized User on 5/18/2026

nice content and training

By Franck Edery on 8/3/2025

Explanations are very clear, and the lab is really helpful. For the next update, some very punctual coding parts (when some little errors are being corrected in the code) should be cut off.

By Koteshwar Chandanala on 6/11/2025

Source code is not included. It isn't easy to follow your video and write the code.

By Michael Förster on 6/11/2025

This course is really above my expectations and I think everyone can take away some things you didn't know about before.

By Robert Kleszczynski on 5/10/2025

The course has loads of hands on techniques not seen in other RAG courses and it's very informative and hands-on. I'm looking forward to new content being added to this course and learning more in the future!

By Diogo Ribeiro dos Santos on 3/22/2025

So far, the course intro was good. The disclaimer was on point!

By Jan Bergerhoff on 2/11/2025

Rémi does a really good job at teaching you practical skills not only at RAG but at programming in general. He goes fast, but he gives you great content that -if you take the time to work through it- is all you need for a successful RAG project. I hope he will still finish the course (maybe including a section about evaluation with RAGAS?), but I am already a happy customer. Thanks!

By Ali Rana on 2/8/2025

Individuals lectures could be planned better to save readers time, at least spelling mistakes and random bug and troubleshooting is making lectures really really long and boring. Also when troubleshooting instructor jump across up and down on the code so reader can't really work out what's happening but has to keep watching and trying to stay awake!

By Mia Xiang on 10/21/2024

This is what we have been looking for. The insights can only be gained with real experience. Rémi Connesson is a self-taught expert in Machine Learning and Artificial Intelligence. From the basics of Python to Deep Learning, he trained himself and practically learned everything by taking online courses. After successfully launching his freelance AI business two years ago, he decided to give back and, in turn, offer online courses to help French-speaking countries catch the AI wave. Graduating from a prestigious engineering school, he entered the workforce at a time when, except in elite schools of which he was not a part, academic programs had not yet embraced the rise of Artificial Intelligence. As a result, despite having a brand-new diploma, he literally started from scratch in AI. Curious about the field, which he sensed was the future, he began researching ways to get started but quickly encountered discouraging, definitive answers such as: "You need at least eight years of study to do AI." "You need an IQ higher than Einstein’s." "You must know everything about math, programming, and even neurology." Loving the challenge, learning new skills, and acquiring knowledge efficiently, he decided to take a chance and get to work anyway. Very soon, he realized it was indeed very difficult, so he decided to prioritize practice and approach learning differently than other aspiring Data Scientists. And this approach paid off because it took him only four months after writing his first "import sklearn" to land an R&D Deep Learning internship at a cutting-edge Parisian fintech specializing in artificial intelligence and computer vision in the banking sector. This internship allowed him to see how fascinating the field was, but also to realize that there was still a lot for him to learn. After the internship, Rémi continued his self-study through foreign online courses and chose to pursue freelancing to quickly gain hands-on experience and work on as many AI projects as possible. Within less than a year, he secured his first AI clients and was able to make a living from freelancing. Since then, feeling fulfilled and still convinced that Artificial Intelligence is a field of the future, he has decided to help as many people as possible learn AI. To do this, he co-founded a volunteer association with a friend to enable more people to enter the world of AI. The conferences, workshops, and free courses he organizes in this context confirmed his passion for teaching. Shortly after, he moved into professional training, becoming the lead instructor for the "Ecole IA" created by Microsoft and Simplon and a professor for the Data Science & Machine Learning specialization at ECE Paris. Now, he shares with you the advice and techniques that allowed him to learn Artificial Intelligence and succeed in Data Science as a self-taught learner, here on Udemy.

Showing all 10 reviews on CourseDuck

Read all 96 reviews on Udemy

icon
Quality Score

No CourseDuck member has rated this course yet. Taken it? Give each part a thumbs up or down.

Content Quality
/
Video Quality
/
Qualified Instructor
/
Course Pace
/
Course Depth & Coverage
/

Overall Score : 88 / 100