From the course: Introduction to AI-Native Vector Databases
Join today to access over 24,800 courses taught by industry experts.
Scalability: When to use a vector DB
From the course: Introduction to AI-Native Vector Databases
Scalability: When to use a vector DB
In the last chapter, we learned about how vector databases use machine learning models to generate vectors for data points. We even built our own multimedia search functionality that allows us to search with images and text. In this chapter, we'll discuss scaling up with vector databases, how to assess how good a vector database is, and how you can perform CRUD operations with vector databases. Let's start off with scalability. If you have tens of millions or even billions of data objects and want to perform vector search or semantic search over them, this is where other solutions will slow down and you'll need vector databases. They're optimized to perform mathematical operations on vectors and can retrieve relevant objects in real-time, even when you have billions of vectors in the database. Vector databases use a class of algorithms called approximate nearest neighbors, ANN, to find which vectors are in the nearest neighborhood of the query vector. This method allows them to…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.