Automatic feature lookup with Databricks hosted MLflow models

Preview

This feature is in Public Preview.

Serverless Real-Time Inference and Classic MLflow Model Serving on Databricks can automatically look up feature values from published online stores.

Requirements

Note

You can publish the feature table at any time prior to model deployment, including after model training.

Automatic feature lookup

Databricks Serverless Real-time Inference supports automatic feature lookup from these online stores:

  • Amazon DynamoDB (v0.3.8 and above)

Databricks Classic MLflow Model Serving supports automatic feature lookup from these online stores:

  • Amazon DynamoDB (v0.3.8 and above)

  • Amazon Aurora (MySQL-compatible)

  • Amazon RDS MySQL

Automatic feature lookup is supported for the following data types:

  • IntegerType

  • FloatType

  • BooleanType

  • StringType

  • DoubleType

  • LongType

  • TimestampType

  • DateType

  • ShortType

  • DecimalType

  • ArrayType

  • MapType

Override feature values in online model scoring

All features required by the model (logged with 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 Serverless Real-Time Inference or Classic MLflow Model Serving, include the feature values as a part of the API payload.

Note

The new feature values must conform to the feature’s data type as expected by the underlying model.

Example 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.

Online Feature Store example notebook

Open notebook in new tab