A feature vector is a row of feature values. A training sample for a model includes a feature vector and the label(s). In inference pipelines, a feature vector in the input to a model that returns a prediction. In online inference pipelines, we use the entity_id ( primary key) to return a feature vector of precomputed features for the model. The returned feature vector may be joined with on-demand features to produce the final (encoded) feature vector used by the model to make a prediction.
Let's consider a dataset of houses with two features, the size of the house in square feet and the number of bedrooms, and a label, the price of the house. A feature vector for a specific house might look like:
Using a feature store like Hopsworks, in online inference pipelines, you can use retrieve a feature vector of precomputed features for an entity_id using the feature view’s get_feature_vector method: