wietsche
diff --git a/‎docs/reference/data-sources/README.md‎
Lines changed: 2 additions & 0 deletions b/‎docs/reference/data-sources/README.md‎
Lines changed: 2 additions & 0 deletions
diff --git a/‎docs/reference/data-sources/spark.md‎
Lines changed: 45 additions & 0 deletions b/‎docs/reference/data-sources/spark.md‎
Lines changed: 45 additions & 0 deletions
diff --git a/‎docs/reference/offline-stores/README.md‎
Lines changed: 2 additions & 0 deletions b/‎docs/reference/offline-stores/README.md‎
Lines changed: 2 additions & 0 deletions
diff --git a/‎docs/reference/offline-stores/spark.md‎
Lines changed: 38 additions & 0 deletions b/‎docs/reference/offline-stores/spark.md‎
Lines changed: 38 additions & 0 deletions
diff --git a/‎sdk/python/feast/__init__.py‎
Lines changed: 4 additions & 0 deletions b/‎sdk/python/feast/__init__.py‎
Lines changed: 4 additions & 0 deletions
diff --git a/‎sdk/python/feast/cli.py‎
Lines changed: 3 additions & 1 deletion b/‎sdk/python/feast/cli.py‎
Lines changed: 3 additions & 1 deletion
diff --git a/‎sdk/python/feast/inference.py‎
Lines changed: 5 additions & 2 deletions b/‎sdk/python/feast/inference.py‎
Lines changed: 5 additions & 2 deletions
diff --git a/‎sdk/python/feast/infra/offline_stores/contrib/spark_offline_store/__init__.py‎ b/‎sdk/python/feast/infra/offline_stores/contrib/spark_offline_store/__init__.py‎
@@ -9,3 +9,5 @@ Please see [Data Source](../../getting-started/concepts/feature-view.md#data-sou
 {% page-ref page="bigquery.md" %}
 
 {% page-ref page="redshift.md" %}
+
+{% page-ref page="spark.md" %}
@@ -0,0 +1,45 @@
+# Spark
+
+## Description
+
+**NOTE**: Spark data source api is currently in alpha development and the API is not completely stable. The API may change or update in the future.
+
+The spark data source API allows for the retrieval of historical feature values from file/database sources for building training datasets as well as materializing features into an online store.
+
+* Either a table name, a SQL query, or a file path can be provided.
+
+## Examples
+
+Using a table reference from SparkSession(for example, either in memory or a Hive Metastore)
+
+```python
+from feast import SparkSource
+
+my_spark_source = SparkSource(
+    table="FEATURE_TABLE",
+)
+```
+
+Using a query
+
+```python
+from feast import SparkSource
+
+my_spark_source = SparkSource(
+    query="SELECT timestamp as ts, created, f1, f2 "
+          "FROM spark_table",
+)
+```
+
+Using a file reference
+
+```python
+from feast import SparkSource
+
+my_spark_source = SparkSource(
+    path=f"{CURRENT_DIR}/data/driver_hourly_stats",
+    file_format="parquet",
+    event_timestamp_column="event_timestamp",
+    created_timestamp_column="created",
+)
+```
@@ -9,3 +9,5 @@ Please see [Offline Store](../../getting-started/architecture-and-components/off
 {% page-ref page="bigquery.md" %}
 
 {% page-ref page="redshift.md" %}
+
+{% page-ref page="spark.md" %}
@@ -0,0 +1,38 @@
+# Spark
+
+## Description
+
+The Spark offline store is an offline store currently in alpha development that provides support for reading [SparkSources](../data-sources/spark.md).
+
+## Disclaimer
+
+This Spark offline store still does not achieve full test coverage and continues to fail some integration tests when integrating with the feast universal test suite. Please do NOT assume complete stability of the API.
+
+* Spark tables and views are allowed as sources that are loaded in from some Spark store(e.g in Hive or in memory).
+* Entity dataframes can be provided as a SQL query or can be provided as a Pandas dataframe. Pandas dataframes will be converted to a Spark dataframe and processed as a temporary view.
+* A `SparkRetrievalJob` is returned when calling `get_historical_features()`.
+  * This allows you to call
+     * `to_df` to retrieve the pandas dataframe.
+     * `to_arrow` to retrieve the dataframe as a pyarrow Table.
+     * `to_spark_df` to retrieve the dataframe the spark.
+
+## Example
+
+{% code title="feature_store.yaml" %}
+```yaml
+project: my_project
+registry: data/registry.db
+provider: local
+offline_store:
+    type: spark
+    spark_conf:
+        spark.master: "local[*]"
+        spark.ui.enabled: "false"
+        spark.eventLog.enabled: "false"
+        spark.sql.catalogImplementation: "hive"
+        spark.sql.parser.quotedRegexColumnNames: "true"
+        spark.sql.session.timeZone: "UTC"
+online_store:
+    path: data/online_store.db
+```
+{% endcode %}
@@ -3,6 +3,9 @@
 from pkg_resources import DistributionNotFound, get_distribution
 
 from feast.infra.offline_stores.bigquery_source import BigQuerySource
+from feast.infra.offline_stores.contrib.spark_offline_store.spark_source import (
+    SparkSource,
+)
 from feast.infra.offline_stores.file_source import FileSource
 from feast.infra.offline_stores.redshift_source import RedshiftSource
 from feast.infra.offline_stores.snowflake_source import SnowflakeSource
@@ -47,4 +50,5 @@
     "RedshiftSource",
     "RequestFeatureView",
     "SnowflakeSource",
+    "SparkSource",
 ]
@@ -477,7 +477,9 @@ def materialize_incremental_command(ctx: click.Context, end_ts: str, views: List
 @click.option(
     "--template",
     "-t",
-    type=click.Choice(["local", "gcp", "aws", "snowflake"], case_sensitive=False),
+    type=click.Choice(
+        ["local", "gcp", "aws", "snowflake", "spark"], case_sensitive=False
+    ),
     help="Specify a template for the created project",
     default="local",
 )
 
@@ -8,6 +8,7 @@
     FileSource,
     RedshiftSource,
     SnowflakeSource,
+    SparkSource,
 )
 from feast.data_source import DataSource
 from feast.errors import RegistryInferenceFailure
@@ -84,7 +85,9 @@ def update_data_sources_with_inferred_event_timestamp_col(
         ):
             # prepare right match pattern for data source
             ts_column_type_regex_pattern = ""
-            if isinstance(data_source, FileSource):
+            if isinstance(data_source, FileSource) or isinstance(
+                data_source, SparkSource
+            ):
                 ts_column_type_regex_pattern = r"^timestamp"
             elif isinstance(data_source, BigQuerySource):
                 ts_column_type_regex_pattern = "TIMESTAMP|DATETIME"
@@ -97,7 +100,7 @@ def update_data_sources_with_inferred_event_timestamp_col(
                     "DataSource",
                     """
                     DataSource inferencing of event_timestamp_column is currently only supported
-                    for FileSource and BigQuerySource.
+                    for FileSource, SparkSource, BigQuerySource, RedshiftSource, and SnowflakeSource.
                     """,
                 )
             #  for informing the type checker