A common use of AI is similarity search. This technique uses an embedding model to take data and turn it into a vector embedding—a multi-dimensional array that records many different dimensions of said data. This can be any type of data, including visual data!

In this talk, I'll show you how to build a multimodal similarity search tool that accepts your own photos, text, or a combination of both as a search query. The result will be an app that matches objects around you to real-world archaeological finds.