Databricks Feature Store

Databricks Feature Store is a central registry for the features used in your AI and ML models. When you register features and models in Unity Catalog, you get built-in governance, lineage, point-in-time joins, and cross-workspace feature sharing and discovery.

You can author features using two strategies.

Both produce Unity Catalog-governed features that publish to the Online Feature Store. See Choose an authoring strategy.

• Feature Views, which define features declaratively and let Databricks compute and manage the feature pipelines for you. This capability is in Public Preview.
• Feature tables, which you populate yourself by writing feature values to a Delta table.

With Databricks, the entire model training workflow takes place on a single platform, including:

• Data pipelines that ingest raw data, create feature tables, train models, and perform batch inference.
• Model and feature serving endpoints that are available with a single click and that provide milliseconds of latency.
• Data and model monitoring.

When you use features from Databricks Feature Store to train models, the model automatically tracks lineage to the features that were used in training. At inference time, the model automatically looks up the latest feature values. Databricks Feature Store also provides on-demand computation of features for real-time applications, handling all feature computation tasks. This eliminates training/serving skew, ensuring that the feature computations used at inference are the same as those used during model training. It also significantly simplifies the client-side code, as all feature lookups and computation are handled by Databricks Feature Store.

note

This page describes Databricks Feature Store for workspaces that are enabled for Unity Catalog. If your workspace is not enabled for Unity Catalog, see Workspace Feature Store (deprecated).

Conceptual overview

For an overview of how Databricks Feature Store works and a glossary of terms, see Databricks Feature Store overview and glossary.

Choose an authoring strategy

Feature Store supports two ways to author features. Both create Unity Catalog-governed features and both can publish to the Online Feature Store. In general, Feature Views are recommended for most new cases, although feature tables are the best fit for flexible, multi-stage batch workloads.

Strategy	Best for	How it works
Feature Views (recommended)	Most new projects, time-windowed aggregations, and streaming features.	Define features declaratively as Unity Catalog Feature objects. Databricks creates and manages the feature pipelines. You can experiment on locally defined features in a notebook before registering them, and materialize feature pipelines. Stream Feature Views support sub-second fresh feature data with direct writes from Real-time mode to the Online Feature Store.
Feature tables	Features you compute using Lakeflow or Spark Declarative Pipelines, and workloads that need Delta Sharing, a third-party online store, or a generally available (GA)-only authoring path.	Write feature values to a Delta table in Unity Catalog that has a primary key. You own the pipeline that populates and refreshes the table.

Strategy	Best for	How it works
Feature Views (recommended)	Most new projects, time-windowed aggregations, and streaming features.	Define features declaratively as Unity Catalog Feature objects. Databricks creates and manages the feature pipelines. You can experiment on locally defined features in a notebook before registering them, and materialize feature pipelines. Stream Feature Views support sub-second fresh feature data with direct writes from Real-time mode to the Online Feature Store.
Feature tables	Features you compute using Lakeflow or Spark Declarative Pipelines, and workloads that need Delta Sharing, a third-party online store, or a generally available (GA)-only authoring path.	Write feature values to a Delta table in Unity Catalog that has a primary key. You own the pipeline that populates and refreshes the table.

Develop features

Feature	Description
Feature Views	Define and compute features declaratively using Feature Views, including time-windowed aggregations and streaming features.
Materialize Feature Views	Materialize Feature Views for offline training or online serving.
Feature tables in Unity Catalog	Create and work with feature tables.

Feature	Description
Feature Views	Define and compute features declaratively using Feature Views, including time-windowed aggregations and streaming features.
Materialize Feature Views	Materialize Feature Views for offline training or online serving.
Feature tables in Unity Catalog	Create and work with feature tables.

Discover and share features

Feature	Description
Explore feature tables in Unity Catalog	Explore and manage feature tables using Catalog Explorer and the Features UI.
Use tags with feature tables and features in Unity Catalog	Use simple key-value pairs to categorize and manage your feature tables and features.
Explore Feature Views in Unity Catalog	Browse Feature View definitions and materialization status in the Databricks UI.

Feature	Description
Explore feature tables in Unity Catalog	Explore and manage feature tables using Catalog Explorer and the Features UI.
Use tags with feature tables and features in Unity Catalog	Use simple key-value pairs to categorize and manage your feature tables and features.
Explore Feature Views in Unity Catalog	Browse Feature View definitions and materialization status in the Databricks UI.

Use features in training workflows

Feature	Description
Train models with feature tables	Use features to train models.
Point-in-time feature joins	Use point-in-time correctness to create a training dataset that reflects feature values as of the time a label observation was recorded.
Feature Engineering Python API	Python API reference

Feature	Description
Train models with feature tables	Use features to train models.
Point-in-time feature joins	Use point-in-time correctness to create a training dataset that reflects feature values as of the time a label observation was recorded.
Feature Engineering Python API	Python API reference

Serve features

Feature	Description
Databricks Online Feature Stores	Serve feature data to online applications and real-time machine learning models. Powered by Databricks Lakebase.
Model Serving with automatic feature lookup	Automatically look up feature values from an online store.
Feature Serving endpoints	Serve features to models and applications outside of Databricks.
On-demand feature computation	Calculate feature values at the time of inference.

Feature	Description
Databricks Online Feature Stores	Serve feature data to online applications and real-time machine learning models. Powered by Databricks Lakebase.
Model Serving with automatic feature lookup	Automatically look up feature values from an online store.
Feature Serving endpoints	Serve features to models and applications outside of Databricks.
On-demand feature computation	Calculate feature values at the time of inference.

Feature governance and lineage

Feature	Description
Feature governance and lineage	Use Unity Catalog to control access to feature tables and view the lineage of a feature table, model, or function.

Feature	Description
Feature governance and lineage	Use Unity Catalog to control access to feature tables and view the lineage of a feature table, model, or function.

Tutorials

Tutorial	Description
Example notebooks to get started	Basic notebook. Shows how to create a feature table, use it to train a model, and run batch scoring using automatic feature lookup. Also shows the Feature Engineering UI to search for features and view lineage. Taxi example notebook. Shows the process of creating features, updating them, and using them for model training and batch inference.
Example: Deploy and query a feature serving endpoint	Tutorial and example notebook showing how to deploy and query a feature serving endpoint.
Example: use features with structured RAG applications	Tutorial showing how to use Databricks online tables and feature serving endpoints for retrieval augmented generation (RAG) applications.

Tutorial	Description
Example notebooks to get started	Basic notebook. Shows how to create a feature table, use it to train a model, and run batch scoring using automatic feature lookup. Also shows the Feature Engineering UI to search for features and view lineage. Taxi example notebook. Shows the process of creating features, updating them, and using them for model training and batch inference.
Example: Deploy and query a feature serving endpoint	Tutorial and example notebook showing how to deploy and query a feature serving endpoint.
Example: use features with structured RAG applications	Tutorial showing how to use Databricks online tables and feature serving endpoints for retrieval augmented generation (RAG) applications.

Requirements

To use Databricks Feature Store, your workspace must be enabled for Unity Catalog. If your workspace is not enabled for Unity Catalog, see Workspace Feature Store (deprecated).

Supported data types

Databricks Feature Store and legacy Workspace Feature Store support the following PySpark data types:

• IntegerType
• FloatType
• BooleanType
• StringType
• DoubleType
• LongType
• TimestampType
• DateType
• ShortType
• ArrayType
• BinaryType [1]
• DecimalType [1]
• MapType [1]
• StructType [2]

[1] BinaryType, DecimalType, and MapType are supported in all versions of Feature Engineering in Unity Catalog and in Workspace Feature Store v0.3.5 or above. [2] StructType is supported in Feature Engineering v0.6.0 or above.

The data types listed above support feature types that are common in machine learning applications. For example:

• You can store dense vectors, tensors, and embeddings as ArrayType.
• You can store sparse vectors, tensors, and embeddings as MapType.
• You can store text as StringType.

When published to online stores, ArrayType and MapType features are stored in JSON format.

The Feature Store UI displays metadata on feature data types:

More information

For more information on best practices, download The Comprehensive Guide to Feature Stores.