Chapter 3. AI Integration and Model Serving
In this chapter, you will learn the mechanisms of various GenAI models and how to serve them in a FastAPI application. Additionally, using the Streamlit UI package, you will create a simple browser client for interacting with the model-serving endpoints. We will explore differing model-serving strategies, how to preload models for efficiency, and how to use FastAPI features for service monitoring.
To solidify your learning in this chapter, we will progressively build a FastAPI service using open source GenAI models that generate text, images, audio, and 3D geometries, all from scratch. In later chapters, you’ll build the functionality to parse documents and web content for your GenAI service so you can talk to them using a language model.
Note
In the previous chapter, you saw how to set up a fresh FastAPI project in Python.
Make sure you have fresh installation ready before you read the rest of this chapter.
Alternatively, you can clone or download the book’s GitHub repository.
Then once cloned, switch to the ch03-start branch, ready for the steps to follow.
By the end of this ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access