OpenAI Cookbook
Working code examples for the recurring tasks in AI application work: embeddings and retrieval, structured output, function calling, evaluation and batching. Recipes you can read and adapt rather than architecture essays.
Guide
AI & Machine Learning
OpenAI
Ongoing reference
Intermediate
Free
What it is
An open source repository of runnable notebooks solving specific problems, maintained alongside the API it targets.
Why it is useful even if you use another provider
The techniques are mostly provider neutral. How to chunk documents for retrieval, how to structure an evaluation set, how to handle rate limits and retries, how to batch requests economically. The API calls differ between vendors; the surrounding engineering does not.
How to use it
Search it when you have a specific problem. It is a cookbook in the literal sense, which means reading it cover to cover is the wrong approach and looking up the recipe you need is the right one.
Best for: engineers already building something, who want a known good implementation of the next piece.
Ready to start?
Opens on OpenAI in a new tab.
Stuck on something specific?
Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Every session is free; a few slots open each week.
Follow along
New writing, resources and project ideas land here first.