Bigfoot has been a staple of American folklore since the 19th century. Many are convinced that Bigfoot is real. Others suggest he’s merely a cultural phenomenon. And some just want to believe. There is even a group, the Bigfoot Field Researchers Organization, that tracks Bigfoot sightings and makes the reports available online. And they have thousands of reports.

I want to explore this delightful data but, unfortunately, it’s been made for the convenience of humans and not computers. While this makes it easy for me to read, searching for reports can be a bit of a challenge. Some of the data is tidy and computer-friendly—like the latitude and longitude. Other bits are really for us humans—like the eyewitness accounts. So, how can I find the Bigfoot sightings that interest me most with data structured like this?

Well, it's easier than you think if we turn these Bigfoot sightings into embeddings and search them semantically with a vector database!

But what's an embedding? And what's a vector database? And what's semantic search? 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 using off-the-shelf AI models that anyone can download for free. 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 converted all of the eyewitness accounts to embeddings. I've loaded them into a vector database—Redis in this case because, well, that's where I work. I've built an application around these embeddings and that database so that anyone can find Bigfoot sightings that match queries optimized for humans and not machines. And, I'll show you the code and the queries of this application so that you can build something similar for yourself.

When we’re done, you’ll know what embeddings are and how *you* can use them with a vector database to search semantically. You can use this newfound power for boring old corporate data, but I’m going to use it to find Bigfoot!