Model Serving with automatic feature lookup
Model Serving can automatically look up feature values from a Databricks Online Feature Store or a third-party online store. For real-time serving of feature values, Databricks recommends using Databricks Online Feature Stores.
Requirements
- The model must have been logged with
FeatureEngineeringClient.log_model(for Feature Engineering in Unity Catalog) orFeatureStoreClient.log_model(for legacy Workspace Feature Store), requires v0.3.5 and above).
You can publish the feature table at any time prior to model deployment, including after model training.
Automatic feature lookup
Automatic feature lookup is supported for the following data types:
IntegerTypeFloatTypeBooleanTypeStringTypeDoubleTypeLongTypeTimestampTypeDateTypeShortTypeArrayTypeMapType
Override feature values in online model scoring
All features required by the model (logged with FeatureEngineeringClient.log_model or FeatureStoreClient.log_model) are automatically looked up from online stores for model scoring. To override feature values when scoring a model using a REST API with Model Serving include the feature values as a part of the API payload.
The new feature values must conform to the feature's data type as expected by the underlying model.
Notebook examples
With Databricks Runtime 13.3 LTS and above, any Delta table in Unity Catalog with a primary key can be used as a feature table. When you use a table registered in Unity Catalog as a feature table, all Unity Catalog capabilities are automatically available to the feature table.
Databricks Online Feature Store
The following notebook illustrates how to publish features to a Databricks Online Feature Store for real-time serving and automated feature lookup.