In the previous chapter, you built a basic generative AI application that could chat with a model in natural language and retrieve data from the SportsWorldCentral API. You created quite a bit of Python code to accomplish that.
In this chapter, you will use custom GPTs from OpenAI to accomplish this task without creating any Python code other than the SportsWorldCentral API. You can think of a custom GPT as a low-code method for creating a generative AI application that connects to your API.
Architecture of Your Application
Figure 15-1 shows the high-level architecture of the project you will create in this chapter.
If you compare this diagram to Figure 14-1, you will see a few similarities. In both cases, a user is using natural language chat to retrieve data from the SportsWorldCentral API. In both cases, a function-calling LLM is used to chat with the user and decide when to call the API for additional information. Although you used an Anthropic model in Chapter 14, you could have used the same OpenAI GPT-4o model that you will use in this chapter.
However, there are also large differences from Chapter 14’s architecture. Where Chapter 14 required many different Python components to be developed and run on GitHub Codespaces, in this chapter, only the SportsWorldCentral API will be running there. As you continue through this chapter, I will share more contrasts with Chapter 14.
Figure 15-1. High-level architecture
Warning
As with ...
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.
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
Julian F.
Head of Cybersecurity
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.
Addison B.
Field Engineer
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.
Amir M.
Data Platform Tech Lead
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
