Sign in to confirm you’re not a bot
This helps protect our community. Learn more
Intro to FastAPI: Tips and Tricks for ML
Learn how to create an API ready for production in very little time using FastAPI... explained with memes. And learn the tips and tricks for serving Machine Learning, simple and advanced. Your API will have automatic validation, documentation based on standards, high performance, and several other features. All this, having editor support including autocompletion everywhere. You will learn how to optimize model loading, avoid common mistakes, and make development iterations more efficient. In this talk, you will learn what FastAPI can do, and how it could benefit you, and the tips and tricks to effectively deploy ML models. You will see how to declare the data you want to receive in each request using standard Python type annotations. Including path parameters, query parameters, body payloads with JSON, etc. You will also see how to use simple, standard, Python type annotations to declare complex JSON body payloads with deeply nested structures, and get automatic data validation, serialization, and documentation. You will learn techniques to load ML models, including caching, lazy loading, and more. [eventID:21290]

Follow along using the transcript.

Microsoft Reactor

114K subscribers
Live chat replay is not available for this video.