feat: Contrib azure provider with synapse/mssql offline store and Azu…

…re registry store (#3072) * Broken state Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * working state Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix the lint issues Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Semi working state Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fremove print Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix lint Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Run build-sphinx Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Add tutorials Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix? Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix lint Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix lint Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Begin configuring tests Signed-off-by: Danny Chiao <danny@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Working version Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix lint Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix lint Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix lint Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix azure Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix lint and address issues Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix integration tests Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix lint and address issues Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Revert Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix lint Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix lint Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix pyarrow Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * Fix lint Signed-off-by: Kevin Zhang <kzhang@tecton.ai> * add requirements files Signed-off-by: Danny Chiao <danny@tecton.ai> * fix name of docs Signed-off-by: Danny Chiao <danny@tecton.ai> * fix offline store readme Signed-off-by: Danny Chiao <danny@tecton.ai> * fix offline store readme Signed-off-by: Danny Chiao <danny@tecton.ai> * fix Signed-off-by: Danny Chiao <danny@tecton.ai> * fix Signed-off-by: Danny Chiao <danny@tecton.ai> Signed-off-by: Kevin Zhang <kzhang@tecton.ai> Signed-off-by: Danny Chiao <danny@tecton.ai> Co-authored-by: Danny Chiao <danny@tecton.ai>
feast-dev · Aug 19, 2022 · 9f7e557 · 9f7e557
1 parent 4310ed7
commit 9f7e557
Show file tree

Hide file tree

Showing 65 changed files with 3,806 additions and 87 deletions.
diff --git a/Makefile b/Makefile
@@ -81,7 +81,8 @@ test-python-integration-local:
 		python -m pytest -n 8 --integration \
 			-k "not gcs_registry and \
  				not s3_registry and \
- 				not test_lambda_materialization" \
+ 				not test_lambda_materialization and \
+ 				not test_snowflake" \
 		sdk/python/tests \
 	) || echo "This script uses Docker, and it isn't running - please start the Docker Daemon and try again!";
 
@@ -113,7 +114,8 @@ test-python-universal-spark:
 			not test_push_features_to_offline_store.py and \
 			not gcs_registry and \
 			not s3_registry and \
-			not test_universal_types" \
+			not test_universal_types and \
+			not test_snowflake" \
  	 sdk/python/tests
 
 test-python-universal-trino:
@@ -136,9 +138,27 @@ test-python-universal-trino:
 			not test_push_features_to_offline_store.py and \
 			not gcs_registry and \
 			not s3_registry and \
-			not test_universal_types" \
+			not test_universal_types and \
+            not test_snowflake" \
  	 sdk/python/tests
 
+
+# Note: to use this, you'll need to have Microsoft ODBC 17 installed.
+# See https://docs.microsoft.com/en-us/sql/connect/odbc/linux-mac/install-microsoft-odbc-driver-sql-server-macos?view=sql-server-ver15#17
+test-python-universal-mssql:
+	PYTHONPATH='.' \
+	FULL_REPO_CONFIGS_MODULE=sdk.python.feast.infra.offline_stores.contrib.mssql_repo_configuration \
+	PYTEST_PLUGINS=feast.infra.offline_stores.contrib.mssql_offline_store.tests \
+ 	FEAST_USAGE=False IS_TEST=True \
+	FEAST_LOCAL_ONLINE_CONTAINER=True \
+ 	python -m pytest -n 8 --integration \
+ 	 	-k "not gcs_registry and \
+			not s3_registry and \
+			not test_lambda_materialization and \
+			not test_snowflake" \
+ 	 sdk/python/tests
+
+
 #To use Athena as an offline store, you need to create an Athena database and an S3 bucket on AWS. https://docs.aws.amazon.com/athena/latest/ug/getting-started.html
 #Modify environment variables ATHENA_DATA_SOURCE, ATHENA_DATABASE, ATHENA_S3_BUCKET_NAME if you want to change the data source, database, and bucket name of S3 to use.
 #If tests fail with the pytest -n 8 option, change the number to 1.
@@ -161,7 +181,8 @@ test-python-universal-athena:
 		    not test_historical_features_persisting and \
 		    not test_historical_retrieval_fails_on_validation and \
 			not gcs_registry and \
-			not s3_registry"  \
+			not s3_registry and \
+			not test_snowflake" \
 	sdk/python/tests
 
 test-python-universal-postgres-offline:
@@ -203,7 +224,8 @@ test-python-universal-postgres-online:
 				not test_push_features_to_offline_store and \
 				not gcs_registry and \
 				not s3_registry and \
- 				not test_universal_types" \
+ 				not test_universal_types and \
+				not test_snowflake" \
  			sdk/python/tests
 
 test-python-universal-cassandra:
@@ -230,7 +252,8 @@ test-python-universal-cassandra-no-cloud-providers:
 	  not test_apply_data_source_integration          and \
 	  not test_nullable_online_store				  and \
 	  not gcs_registry 								  and \
-	  not s3_registry" \
+	  not s3_registry								  and \
+	  not test_snowflake" \
 	sdk/python/tests
 
 test-python-universal:

diff --git a/README.md b/README.md
@@ -152,7 +152,7 @@ The list below contains the functionality that contributors are planning to deve
   * [x] [Redshift source](https://docs.feast.dev/reference/data-sources/redshift)
   * [x] [BigQuery source](https://docs.feast.dev/reference/data-sources/bigquery)
   * [x] [Parquet file source](https://docs.feast.dev/reference/data-sources/file)
-  * [x] [Synapse source (community plugin)](https://github.com/Azure/feast-azure)
+  * [x] [Azure Synapse + Azure SQL source (contrib plugin)](https://docs.feast.dev/reference/data-sources/mssql)
   * [x] [Hive (community plugin)](https://github.com/baineng/feast-hive)
   * [x] [Postgres (contrib plugin)](https://docs.feast.dev/reference/data-sources/postgres)
   * [x] [Spark (contrib plugin)](https://docs.feast.dev/reference/data-sources/spark)
@@ -161,7 +161,7 @@ The list below contains the functionality that contributors are planning to deve
   * [x] [Snowflake](https://docs.feast.dev/reference/offline-stores/snowflake)
   * [x] [Redshift](https://docs.feast.dev/reference/offline-stores/redshift)
   * [x] [BigQuery](https://docs.feast.dev/reference/offline-stores/bigquery)
-  * [x] [Synapse (community plugin)](https://github.com/Azure/feast-azure)
+  * [x] [Azure Synapse + Azure SQL (contrib plugin)](https://docs.feast.dev/reference/offline-stores/mssql.md)
   * [x] [Hive (community plugin)](https://github.com/baineng/feast-hive)
   * [x] [Postgres (contrib plugin)](https://docs.feast.dev/reference/offline-stores/postgres)
   * [x] [Trino (contrib plugin)](https://github.com/Shopify/feast-trino)

diff --git a/docs/SUMMARY.md b/docs/SUMMARY.md
@@ -71,6 +71,7 @@
   * [Spark (contrib)](reference/data-sources/spark.md)
   * [PostgreSQL (contrib)](reference/data-sources/postgres.md)
   * [Trino (contrib)](reference/data-sources/trino.md)
+  * [Azure Synapse + Azure SQL (contrib)](reference/data-sources/mssql.md)
 * [Offline stores](reference/offline-stores/README.md)
   * [Overview](reference/offline-stores/overview.md)
   * [File](reference/offline-stores/file.md)
@@ -80,17 +81,20 @@
   * [Spark (contrib)](reference/offline-stores/spark.md)
   * [PostgreSQL (contrib)](reference/offline-stores/postgres.md)
   * [Trino (contrib)](reference/offline-stores/trino.md)
+  * [Azure Synapse + Azure SQL (contrib)](reference/offline-stores/mssql.md)
 * [Online stores](reference/online-stores/README.md)
   * [SQLite](reference/online-stores/sqlite.md)
   * [Snowflake](reference/online-stores/snowflake.md)
   * [Redis](reference/online-stores/redis.md)
   * [Datastore](reference/online-stores/datastore.md)
   * [DynamoDB](reference/online-stores/dynamodb.md)
   * [PostgreSQL (contrib)](reference/online-stores/postgres.md)
+  * [Cassandra + Astra DB (contrib)](reference/online-stores/cassandra.md) 
 * [Providers](reference/providers/README.md)
   * [Local](reference/providers/local.md)
   * [Google Cloud Platform](reference/providers/google-cloud-platform.md)
   * [Amazon Web Services](reference/providers/amazon-web-services.md)
+  * [Azure](reference/providers/azure.md)
 * [Feature repository](reference/feature-repository/README.md)
   * [feature\_store.yaml](reference/feature-repository/feature-store-yaml.md)
   * [.feastignore](reference/feature-repository/feast-ignore.md)

diff --git a/docs/getting-started/concepts/registry.md b/docs/getting-started/concepts/registry.md
@@ -1,15 +1,15 @@
 # Registry
 
-Feast uses a registry to store all applied Feast objects (e.g. Feature views, entities, etc). The registry exposes 
+Feast uses a registry to store all applied Feast objects (e.g. Feature views, entities, etc). The registry exposes
 methods to apply, list, retrieve and delete these objects, and is an abstraction with multiple implementations.
 
 ### Options for registry implementations
 
 #### File-based registry
-By default, Feast uses a file-based registry implementation, which stores the protobuf representation of the registry as 
-a serialized file. This registry file can be stored in a local file system, or in cloud storage (in, say, S3 or GCS). 
+By default, Feast uses a file-based registry implementation, which stores the protobuf representation of the registry as
+a serialized file. This registry file can be stored in a local file system, or in cloud storage (in, say, S3 or GCS, or Azure).
 
-The quickstart guides that use `feast init` will use a registry on a local file system. To allow Feast to configure 
+The quickstart guides that use `feast init` will use a registry on a local file system. To allow Feast to configure
 a remote file registry, you need to create a GCS / S3 bucket that Feast can understand:
 {% tabs %}
 {% tab title="Example S3 file registry" %}
@@ -35,9 +35,9 @@ offline_store:
 {% endtab %}
 {% endtabs %}
 
-However, there are inherent limitations with a file-based registry, since changing a single field in the registry 
-requires re-writing the whole registry file. With multiple concurrent writers, this presents a risk of data loss, or 
-bottlenecks writes to the registry since all changes have to be serialized (e.g. when running materialization for 
+However, there are inherent limitations with a file-based registry, since changing a single field in the registry
+requires re-writing the whole registry file. With multiple concurrent writers, this presents a risk of data loss, or
+bottlenecks writes to the registry since all changes have to be serialized (e.g. when running materialization for
 multiple feature views or time ranges concurrently).
 
 #### SQL Registry
@@ -47,14 +47,14 @@ This supports any SQLAlchemy compatible database as a backend. The exact schema
 
 ### Updating the registry
 
-We recommend users store their Feast feature definitions in a version controlled repository, which then via CI/CD 
-automatically stays synced with the registry. Users will often also want multiple registries to correspond to 
-different environments (e.g. dev vs staging vs prod), with staging and production registries with locked down write 
+We recommend users store their Feast feature definitions in a version controlled repository, which then via CI/CD
+automatically stays synced with the registry. Users will often also want multiple registries to correspond to
+different environments (e.g. dev vs staging vs prod), with staging and production registries with locked down write
 access since they can impact real user traffic. See [Running Feast in Production](../../how-to-guides/running-feast-in-production.md#1.-automatically-deploying-changes-to-your-feature-definitions) for details on how to set this up.
 
 ### Accessing the registry from clients
 
-Users can specify the registry through a `feature_store.yaml` config file, or programmatically. We often see teams 
+Users can specify the registry through a `feature_store.yaml` config file, or programmatically. We often see teams
 preferring the programmatic approach because it makes notebook driven development very easy:
 
 #### Option 1: programmatically specifying the registry

diff --git a/docs/how-to-guides/adding-or-reusing-tests.md b/docs/how-to-guides/adding-or-reusing-tests.md
@@ -241,7 +241,8 @@ def test_historical_features(environment, universal_data_sources, full_feature_n
     validate_dataframes(
         expected_df,
         table_from_df_entities,
-        keys=[event_timestamp, "order_id", "driver_id", "customer_id"],
+        sort_by=[event_timestamp, "order_id", "driver_id", "customer_id"],
+        event_timestamp = event_timestamp,
     )
     # ... more test code
 ```

diff --git a/docs/reference/data-sources/README.md b/docs/reference/data-sources/README.md
@@ -35,9 +35,13 @@ Please see [Data Source](../../getting-started/concepts/data-ingestion.md) for a
 {% endcontent-ref %}
 
 {% content-ref url="postgres.md" %}
-[postgres.md]([postgres].md)
+[postgres.md](postgres.md)
 {% endcontent-ref %}
 
 {% content-ref url="trino.md" %}
-[trino.md]([trino].md)
+[trino.md](trino.md)
+{% endcontent-ref %}
+
+{% content-ref url="mssql.md" %}
+[mssql.md](mssql.md)
 {% endcontent-ref %}
diff --git a/docs/reference/data-sources/mssql.md b/docs/reference/data-sources/mssql.md
@@ -0,0 +1,29 @@
+# MsSQL source (contrib)
+
+## Description
+
+MsSQL data sources are Microsoft sql table sources.
+These can be specified either by a table reference or a SQL query.
+
+## Disclaimer
+
+The MsSQL data source does not achieve full test coverage.
+Please do not assume complete stability.
+
+## Examples
+
+Defining a MsSQL source:
+
+```python
+from feast.infra.offline_stores.contrib.mssql_offline_store.mssqlserver_source import (
+    MsSqlServerSource,
+)
+
+driver_hourly_table = "driver_hourly"
+
+driver_source = MsSqlServerSource(
+    table_ref=driver_hourly_table,
+    event_timestamp_column="datetime",
+    created_timestamp_column="created",
+)
+```
diff --git a/docs/reference/offline-stores/README.md b/docs/reference/offline-stores/README.md
@@ -35,3 +35,7 @@ Please see [Offline Store](../../getting-started/architecture-and-components/off
 {% content-ref url="trino.md" %}
 [trino.md](trino.md)
 {% endcontent-ref %}
+
+{% content-ref url="mssql.md" %}
+[mssql.md](mssql.md)
+{% endcontent-ref %}
diff --git a/docs/reference/offline-stores/mssql.md b/docs/reference/offline-stores/mssql.md
@@ -0,0 +1,59 @@
+# MsSQL/Synapse offline store (contrib)
+
+## Description
+
+The MsSQL offline store provides support for reading [MsSQL Sources](../data-sources/mssql.md). Specifically, it is developed to read from [Synapse SQL](https://docs.microsoft.com/en-us/azure/synapse-analytics/sql/overview-features) on Microsoft Azure
+
+* Entity dataframes can be provided as a SQL query or can be provided as a Pandas dataframe.
+
+## Disclaimer
+
+The MsSQL offline store does not achieve full test coverage.
+Please do not assume complete stability.
+
+## Example
+
+{% code title="feature_store.yaml" %}
+```yaml
+registry:
+  registry_store_type: AzureRegistryStore
+  path: ${REGISTRY_PATH} # Environment Variable
+project: production
+provider: azure
+online_store:
+    type: redis
+    connection_string: ${REDIS_CONN} # Environment Variable
+offline_store:
+    type: mssql
+    connection_string: ${SQL_CONN}  # Environment Variable
+```
+{% endcode %}
+
+## Functionality Matrix
+
+The set of functionality supported by offline stores is described in detail [here](overview.md#functionality).
+Below is a matrix indicating which functionality is supported by the Spark offline store.
+
+| | MsSql |
+| :-------------------------------- | :-- |
+| `get_historical_features` (point-in-time correct join)             | yes |
+| `pull_latest_from_table_or_query` (retrieve latest feature values) | yes |
+| `pull_all_from_table_or_query` (retrieve a saved dataset)          | yes |
+| `offline_write_batch` (persist dataframes to offline store)        | no  |
+| `write_logged_features` (persist logged features to offline store) | no  |
+
+Below is a matrix indicating which functionality is supported by `MsSqlServerRetrievalJob`.
+
+| | MsSql |
+| --------------------------------- | --- |
+| export to dataframe                                   | yes |
+| export to arrow table                                 | yes |
+| export to arrow batches                               | no  |
+| export to SQL                                         | no  |
+| export to data lake (S3, GCS, etc.)                   | no  |
+| export to data warehouse                              | no  |
+| local execution of Python-based on-demand transforms  | no  |
+| remote execution of Python-based on-demand transforms | no  |
+| persist results in the offline store                  | yes |
+
+To compare this set of functionality against other offline stores, please see the full [functionality matrix](overview.md#functionality-matrix).
diff --git a/docs/reference/online-stores/README.md b/docs/reference/online-stores/README.md
@@ -29,3 +29,4 @@ Please see [Online Store](../../getting-started/architecture-and-components/onli
 {% content-ref url="cassandra.md" %}
 [cassandra.md](cassandra.md)
 {% endcontent-ref %}
+
diff --git a/docs/reference/online-stores/cassandra.md b/docs/reference/online-stores/cassandra.md
@@ -1,4 +1,4 @@
-# Cassandra / Astra DB online store
+# Cassandra + Astra DB online store (contrib)
 
 ## Description
 

diff --git a/docs/reference/providers/README.md b/docs/reference/providers/README.md
@@ -7,3 +7,5 @@ Please see [Provider](../../getting-started/architecture-and-components/provider
 {% page-ref page="google-cloud-platform.md" %}
 
 {% page-ref page="amazon-web-services.md" %}
+
+{% page-ref page="azure.md" %}
diff --git a/docs/reference/providers/azure.md b/docs/reference/providers/azure.md
@@ -0,0 +1,26 @@
+# Azure (contrib)
+
+## Description
+
+* Offline Store: Uses the **MsSql** offline store by default. Also supports File as the offline store.
+* Online Store: Uses the **Redis** online store by default. Also supports Sqlite as an online store.
+
+## Disclaimer
+
+The Azure provider does not achieve full test coverage.
+Please do not assume complete stability.
+
+## Example
+
+{% code title="feature_store.yaml" %}
+```yaml
+registry:
+  registry_store_type: AzureRegistryStore
+  path: ${REGISTRY_PATH} # Environment Variable
+project: production
+provider: azure
+online_store:
+    type: redis
+    connection_string: ${REDIS_CONN} # Environment Variable
+```
+{% endcode %}
diff --git a/docs/roadmap.md b/docs/roadmap.md
@@ -10,7 +10,7 @@ The list below contains the functionality that contributors are planning to deve
   * [x] [Redshift source](https://docs.feast.dev/reference/data-sources/redshift)
   * [x] [BigQuery source](https://docs.feast.dev/reference/data-sources/bigquery)
   * [x] [Parquet file source](https://docs.feast.dev/reference/data-sources/file)
-  * [x] [Synapse source (community plugin)](https://github.com/Azure/feast-azure)
+  * [x] [Azure Synapse + Azure SQL source (contrib plugin)](https://docs.feast.dev/reference/data-sources/mssql)
   * [x] [Hive (community plugin)](https://github.com/baineng/feast-hive)
   * [x] [Postgres (contrib plugin)](https://docs.feast.dev/reference/data-sources/postgres)
   * [x] [Spark (contrib plugin)](https://docs.feast.dev/reference/data-sources/spark)
@@ -19,7 +19,7 @@ The list below contains the functionality that contributors are planning to deve
   * [x] [Snowflake](https://docs.feast.dev/reference/offline-stores/snowflake)
   * [x] [Redshift](https://docs.feast.dev/reference/offline-stores/redshift)
   * [x] [BigQuery](https://docs.feast.dev/reference/offline-stores/bigquery)
-  * [x] [Synapse (community plugin)](https://github.com/Azure/feast-azure)
+  * [x] [Azure Synapse + Azure SQL (contrib plugin)](https://docs.feast.dev/reference/offline-stores/mssql.md)
   * [x] [Hive (community plugin)](https://github.com/baineng/feast-hive)
   * [x] [Postgres (contrib plugin)](https://docs.feast.dev/reference/offline-stores/postgres)
   * [x] [Trino (contrib plugin)](https://github.com/Shopify/feast-trino)