Hi and welcome to this tutorial series on Google Gemini! In this series you will learn everything you need to know to work effectively with Google Gemini, from the very basics up to more advanced topics like parallel function calling and error handling.
- In part 1, we will start by looking at Gemini, the AI Studio, how everything works, and getting our API key.
- In part 2, we’ll start coding. First setting up our environment and then looking at how to make a simple request. We’ll also abstract away some repetitive code by writing a utility file.
- In the next part, we’ll look at taking our simple request and adding memory and a loop, so we can have a real conversation with multiple turns and context. We will also implement error handling to stop blocked responses from crashing our program.
- The fourth part will deal with the file API, adding the ability to insert images into our chat conversations at any point, and creating a function to calculate the cost of our API calls in dollars.
- In part 5 we will start by refactoring our code, and then we’ll create a function in a manner that Gemini can understand, giving our function to Gemini and using function calling.
- Part 6 is where we’ll put everything together and make the ultimate version of the chat with multiple functions and even parallel function calling added on.
- Finally, in part 7, we’ll have a look at some of the newest features added by Gemini while the course was already being made, code execution, and context caching.
I hope you’re as excited as I am to get started! Let’s dive in!