Repolode
microsoft

microsoft/generative-ai-for-beginners

A 21-lesson Microsoft course teaching developers the fundamentals of building generative AI applications with Python and TypeScript.

Stars
121,685
Forks
64,131
Open issues
9
Last commit
yesterday

What is it?

Generative AI for Beginners is a structured course of 21 lessons created by Microsoft Cloud Advocates. Each lesson is either a "Learn" lesson that explains a generative AI concept or a "Build" lesson that pairs the concept with code, with examples in Python and TypeScript where possible. Lessons can be taken in any order.

The material covers topics from LLM fundamentals and prompt engineering through chat applications, embeddings-based search, image generation, function calling, retrieval augmented generation (RAG) with vector databases, open source models on Hugging Face, AI agents, fine-tuning, and small language models. Later lessons also address responsible use, security, UX design, and the LLMOps lifecycle.

The code examples run against Azure OpenAI Service, Microsoft Foundry Models, the OpenAI API, or Foundry Local for fully offline use. A separate .NET edition and a Co-op Translator-maintained set of translations are also available.

Key features

  • 0121 lessons, each covering a self-contained generative AI topic
  • 02Python and TypeScript code samples for build lessons
  • 03Covers Azure OpenAI, OpenAI API, and Foundry Local as model backends
  • 04Topics include prompt engineering, RAG with vector databases, function calling, and AI agents
  • 05Includes lessons on responsible AI, security, and LLMOps

Use cases

  • Developers new to LLMs who want a structured path into building AI apps
  • Engineers adding chat, search, or image generation features to an existing product
  • Teachers or study groups looking for a ready-made generative AI curriculum
  • Developers who want to run the examples fully offline with Foundry Local

Quick start

  1. 1

    Fork the repo to your own GitHub account

  2. 2

    Clone the repo without translations using sparse checkout (Bash/macOS/Linux)

    git clone --filter=blob:none --sparse https://github.com/microsoft/generative-ai-for-beginners.git
  3. 3

    Enter the cloned folder and set the sparse checkout paths

    cd generative-ai-for-beginners && git sparse-checkout set --no-cone '/*' '!translations' '!translated_images'
  4. 4

    Open the Course Setup lesson to configure your development environment and API access

Things to know

  • Running the code requires an Azure OpenAI, Microsoft Foundry Models, or OpenAI API account.
  • GitHub Models is retiring at the end of July 2026, so the README recommends Microsoft Foundry Models instead.
  • It is a course of lessons and code samples, not a software library or application.

Topics

FAQ

What is generative-ai-for-beginners?
A 21-lesson Microsoft course teaching developers the fundamentals of building generative AI applications with Python and TypeScript. Generative AI for Beginners is a structured course of 21 lessons created by Microsoft Cloud Advocates. Each lesson is either a "Learn" lesson that explains a generative AI concept or a "Build" lesson that pairs the concept with code, with examples in Python and TypeScript where possible. Lessons can be taken in any order.
Is generative-ai-for-beginners free to use? What license does it have?
generative-ai-for-beginners is open source under the MIT license. Check the license terms before using it in commercial products.
Is generative-ai-for-beginners still maintained?
Actively maintained. The last commit to generative-ai-for-beginners was on Oct 19, 2026.
What can I use generative-ai-for-beginners for?
Developers new to LLMs who want a structured path into building AI apps Engineers adding chat, search, or image generation features to an existing product Teachers or study groups looking for a ready-made generative AI curriculum Developers who want to run the examples fully offline with Foundry Local
How do I install generative-ai-for-beginners?
Fork the repo to your own GitHub account Clone the repo without translations using sparse checkout (Bash/macOS/Linux): git clone --filter=blob:none --sparse https://github.com/microsoft/generative-ai-for-beginners.git Enter the cloned folder and set the sparse checkout paths: cd generative-ai-for-beginners && git sparse-checkout set --no-cone '/*' '!translations' '!translated_images' Open the Course Setup lesson to configure your development environment and API access
Where can I get generative-ai-for-beginners?
The source code and installation instructions are on GitHub: https://github.com/microsoft/generative-ai-for-beginners

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects