Skip to main content
Go to documentation:
⌘U
Weaviate Database

Develop AI applications using Weaviate's APIs and tools

Deploy

Deploy, configure, and maintain Weaviate Database

Weaviate Agents

Build and deploy intelligent agents with Weaviate

Weaviate Cloud

Manage and scale Weaviate in the cloud

Additional resources

Academy
Integrations
Contributor guide

Need help?

Weaviate LogoAsk AI Assistant⌘K
Community Forum

220 Named vectors

Course overview

Sometimes, you might wish to provide multiple ways to represent the same data. For example, you might want to represent an article using its body, its title, or both.

Named vectors enable this capability. With named vectors, you can store multiple vector embeddings per one object, then search for the object using any of the vector spaces. This provides a great deal of flexibility in how you can represent and search for your data.

This course will teach you how to use named vectors through the lens of multimodality. It will show you how to use named vectors to represent and search for movies, using their text properties such as the title or the summary, or their visual properties such as the poster.

If you do not wish to use multimodal data, that's okay! The concepts you learn in this course can be applied to any kind of data, or any kind of vectorizer.

Learning objectives

  Here, we will cover:

Learning Goals
  • What named vectors can be used for, and how to add them to your data collection.

  By the time you are finished, you will be able to:

Learning Outcomes
  • Describe use cases for named vectors
  • Create a collection with named vectors
  • Add objects with multiple vector embeddings per object
  • Perform searches on named vectors

Units