Large Language Models (LLMs) Bootcamp 2026

About this course

This course contains the use of artificial intelligence.

Want to learn how to build applications powered by Large Language Models (LLMs)?

In this course, you’ll learn how to work with LLMs using Python and turn them into practical applications — even if you’re completely new to LLM application development.

We’ll start with the fundamentals and gradually build real applications. You’ll learn what LLMs are, how they generate responses, how to work with APIs, and how to connect Python to an LLM.Then we’ll move from simple API requests to interactive applications. You’ll learn how to create conversation memory, build multi-turn conversations, control an AI assistant with system instructions, and customize the way your LLM responds.

We’ll also explore some of the most important techniques used in modern LLM applications, including structured outputs, JSON, text summarization, information extraction, streaming, and error handling.

Next, you’ll learn how to make an LLM work with your own data. We’ll explore embeddings, semantic search, document chunking, and Retrieval-Augmented Generation (RAG), and you’ll build a practical RAG application.

After that, we’ll introduce tool calling and AI agents. You’ll learn how to give an LLM access to Python functions and external tools, understand what makes an LLM agentic, and build your own simple AI agent.

Finally, you’ll put what you’ve learned together in a complete LLM application project.

Read the full description on Udemy on Udemy (opens in a new tab)

Prices, discounts and availability are set by Udemy. We may earn a commission when you purchase through links on this site.