Learning

OpenAI's official collection of examples and guides for the OpenAI API — embeddings, RAG, function calling, evals, structured outputs and more.

Sebastian Raschka's step-by-step guide (and book code) to implementing a GPT-style large language model in PyTorch from the ground up.

A catalogue of advanced Retrieval-Augmented Generation techniques, each with a detailed, runnable notebook tutorial.

Microsoft's 21-lesson course to start building with generative AI — prompting, RAG, agents, fine-tuning and responsible use — with runnable examples.

A 12-week, 26-lesson curriculum from Microsoft covering classic machine learning with hands-on projects, quizzes and real-world data.

The official code for the O'Reilly book "Hands-On Large Language Models" — practical notebooks on using and understanding LLMs.

A comprehensive, reference-style guide to prompt engineering — techniques, patterns, papers and notebooks — extended with context engineering, RAG and agents.

Andrej Karpathy's video course building neural networks and language models from scratch, from backprop basics to a mini-GPT.

Jake VanderPlas's full-text handbook, in Jupyter notebooks, covering NumPy, pandas, Matplotlib and scikit-learn for working with data in Python.