In this exciting and hands-on talk, we’ll dive into the world of modern search technology, showing you how to build your very own search engine using DuckDB and embedding vectors. This session is perfect for developers, data scientists, and anyone interested in the intersection of databases and machine learning.
We’ll start by exploring the power of vector search and its applications in semantic search, recommendation systems, and more. You’ll learn why DuckDB, an in-process analytical database, is an excellent choice for this task, offering speed, simplicity, and seamless integration with Python.
The heart of our search engine lies in embedding vectors, and we’ll demystify these powerful tools, showing how they capture semantic meaning and transform text into a format that machines can understand and compare.
Through live coding and practical examples, we’ll walk through the entire process of building a search engine.
