Featureform Resource Types
Embeddings
Embeddings represent a specialized type of feature stored in a Vector DB. They are primarily used for nearest neighbor lookups. If you’d like to explore a comprehensive explanation of what an embedding is, you can read our definitive guide to embeddings.
Defining an embedding is quite similar to defining a feature. It’s associated with an entity, and the data is stored in a data set. An embedding must be a vector of floats, so all that needs specification is the dimensions of the embedding and the vector DB in which it’s stored.
Here’s an example:
Additionally, we provide a more detailed end-to-end example of building with embeddings.