Florida Man loves speed. He loves it so much that he’s going to do the unthinkable—he's going to use a cache as his primary database. We'll explore just how Florida Man will do this without losing persistence and without having to drop ACID—that's atomicity, consistency, isolation, and durability. And we'll see that Florida Man can have all the CRUD a database provides and the blazing fast speed that a cache provides. We'll do this with an app that would make Florida Man proud. I've cooked up a service that screen scrapes websites with articles featuring his exploits and loads them into Redis—my cache of choice. On top of this, I've built a website that allows users to view and search for articles—using tags, keywords, and vector search. I'll show how all of it works—covering the details above—and explain what vector search and embeddings are in a way that even Florida Man could understand. And, of course, I'll demo it live so we can find the Florida Man stories you need to see. When it's all said and done, you'll see how a cache like Redis can be persistent, ACID-compliant, and even searchable. You'll have an intuitive understanding of vector search, and—best of all—you'll have an app that you can use to start your own projects.

Do you look like a famous meme character? Does someone you know? Knowing this information is vital—both for your career and your personal life. After all, am I the only one around here who wants to avoid [Angry Walter](https://knowyourmeme.com/memes/am-i-the-only-one-around-here)? And who *wouldn't* want to work with [Success Kid](https://knowyourmeme.com/memes/success-kid-i-hate-sandcastles). But can we even find out if we have a meme twin? There are lots of memes. And lots of people. How could we possibly search them all? Well, it's easier than you think if we turn those memes into embeddings and search them with a vector database! But what's an embedding? And what's a vector database? Well, that's what I'll cover in this session. I'll begin by exploring embeddings, showing how unstructured data, such as text and images, can be translated into hyper-dimensional arrays—called vectors—using both common and custom AI models. Then I'll talk about vector databases, covering what they are and how you can use them to store and search those embeddings with embeddings of your own. Of course, we'll do this all by example. I've turned all the big memes—from [Ancient Aliens Guy](https://knowyourmeme.com/memes/ancient-aliens) to [Zombie Boy](https://imgflip.com/memegenerator/184608242/zombie-boy)—into embeddings and have loaded them into a vector database. I've built an application around these embeddings and that database. I'll show you the code and the queries of this application so that you can build something similar for yourself. And, most importantly, we'll take some photos during the session and use it all to find your meme twin! So, are you ready to find your meme twin? Or are you ready to learn how to use this technology? I say, [Why Not Both](https://knowyourmeme.com/memes/why-not-both-why-dont-we-have-both).