Automatic feature lookup with Databricks Model Serving
Model Serving can automatically look up feature values from published online stores or from online tables. For more details about creating and working with online tables, see Use online tables for real-time feature serving.
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). - For third-party online stores, the online store must be published with read-only credentials.
You can publish the feature table at any time prior to model deployment, including after model training.
Automatic feature lookup
Databricks Model Serving supports automatic feature lookup from these online stores:
- Databricks Online Tables
- Amazon DynamoDB (v0.3.8 and above)
Automatic feature lookup is supported for the following data types:
IntegerTypeFloatTypeBooleanTypeStringTypeDoubleTypeLongTypeTimestampTypeDateTypeShortTypeDecimalTypeArrayTypeMapType
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.
Save the augmented DataFrame in the inference table
For endpoints created starting February 2025, you can configure a model serving endpoint to log the augmented DataFrame that contains the looked-up feature values and function return values. The DataFrame is saved to the inference table for the served model.
For instructions on setting this configuration, see Log feature lookup DataFrames to inference tables.
For information about inference tables, see Inference tables for monitoring and debugging models.
Notebook examples: Unity Catalog
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.
The following notebook illustrates how to publish features to online tables for real-time serving and automated feature lookup.
Online tables demo notebook
This example notebook illustrates how to publish features to an online store and then serve a trained model that automatically looks up features from the online store.
Third-party online store example notebook (Unity Catalog)
Notebook examples: Workspace Feature Store (legacy)
This example notebook illustrates how to publish features to an online store and then serve a trained model that automatically looks up features from the online store.