[🏫 In-Person] Finding Your Meme Twin with Embeddings & Vector Databases
Description changed:
This event will be a single talk on Modern Problems Require Modern Solutions: Finding Your Meme Twin with Embeddings & Vector Databases with Guy Royse
⚠️ This will be an in-person event, the venue is Sheffield Hallam University, room TBA.
🗺️ Hallam University Map: [https://www.shu.ac.uk/visit-us/how-to-find-us/city-campus-map](https://www.shu.ac.uk/visit-us/how-to-find-us/city-campus-map)
📌 Google Maps: [https://maps.app.goo.gl/kMU7RCsj3hdhWzXp9](https://maps.app.goo.gl/kMU7RCsj3hdhWzXp9)
🚗 Parking: The APCOA car park on Eyre Street is a five-minute walk from City Campus. You can park there for just £5. Just scan your blue chip at Owen Building Level 5, Charles Street, or Cantor to claim the discount.
Agenda:
🍕 Pizza/Drinks (18:15 - 18:30)
🗣 Introduction (18:30)
👉 Modern Problems Require Modern Solutions: Finding Your Meme Twin with Embeddings & Vector Databases (18:35ish)
🍻 Social @ Pub (after the talk)
👉 Modern Problems Require Modern Solutions: Finding Your Meme Twin with Embeddings & Vector Databases
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? And who *wouldn't* want to work with Success Kid.
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 to 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.
