chore: Updating quickstart and fixing roadmap + broken links to old alpha docs (#2553)

* chore: Updating quickstart and fixing trailing ) in roadmap + broken link to old alpha docs

Signed-off-by: Danny Chiao <danny@tecton.ai>

* fix

Signed-off-by: Danny Chiao <danny@tecton.ai>

Author: adchia

README.md

@@ -148,7 +148,7 @@ The list below contains the functionality that contributors are planning to deve
   * [x] [Hive (community plugin)](https://github.com/baineng/feast-hive)
   * [x] [Postgres (community plugin)](https://github.com/nossrannug/feast-postgres)
   * [x] [Spark (community plugin)](https://docs.feast.dev/reference/data-sources/spark)
-  * [x] Kafka / Kinesis sources (via [push support into the online store](https://docs.feast.dev/reference/data-sources/push)
+  * [x] Kafka / Kinesis sources (via [push support into the online store](https://docs.feast.dev/reference/data-sources/push))
   * [ ] HTTP source
 * **Offline Stores**
   * [x] [Snowflake](https://docs.feast.dev/reference/offline-stores/snowflake)

docs/SUMMARY.md

@@ -85,7 +85,6 @@
   * [Go-based feature retrieval](reference/feature-servers/go-feature-retrieval.md)
 * [\[Alpha\] Data quality monitoring](reference/dqm.md)
 * [\[Alpha\] On demand feature view](reference/alpha-on-demand-feature-view.md)
-* [\[Alpha\] Stream ingestion](reference/alpha-stream-ingestion.md)
 * [\[Alpha\] AWS Lambda feature server](reference/alpha-aws-lambda-feature-server.md)
 * [Feast CLI reference](reference/feast-cli-commands.md)
 * [Python API reference](http://rtd.feast.dev)

docs/getting-started/third-party-integrations.md

@@ -21,7 +21,7 @@ Don't see your offline store or online store of choice here? Check out our guide
 * [x] [Hive (community plugin)](https://github.com/baineng/feast-hive)
 * [x] [Postgres (community plugin)](https://github.com/nossrannug/feast-postgres)
 * [x] [Spark (community plugin)](https://docs.feast.dev/reference/data-sources/spark)
-* [x] Kafka / Kinesis sources (via [push support into the online store](https://docs.feast.dev/reference/data-sources/push)
+* [x] Kafka / Kinesis sources (via [push support into the online store](https://docs.feast.dev/reference/data-sources/push))
 * [ ] HTTP source
 
 ### Offline Stores

docs/roadmap.md

@@ -16,7 +16,7 @@ The list below contains the functionality that contributors are planning to deve
   * [x] [Hive (community plugin)](https://github.com/baineng/feast-hive)
   * [x] [Postgres (community plugin)](https://github.com/nossrannug/feast-postgres)
   * [x] [Spark (community plugin)](https://docs.feast.dev/reference/data-sources/spark)
-  * [x] Kafka / Kinesis sources (via [push support into the online store](https://docs.feast.dev/reference/data-sources/push)
+  * [x] Kafka / Kinesis sources (via [push support into the online store](https://docs.feast.dev/reference/data-sources/push))
   * [ ] HTTP source
 * **Offline Stores**
   * [x] [Snowflake](https://docs.feast.dev/reference/offline-stores/snowflake)

examples/quickstart/quickstart.ipynb

@@ -8,7 +8,7 @@
 # construction of feature vectors
 driver = Entity(
     # Name of the entity. Must be unique within a project
-    name="driver_id",
+    name="driver",
     # The join key of an entity describes the storage level field/column on which
     # features can be looked up. The join key is also used to join feature
     # tables/views when building feature vectors
@@ -41,7 +41,7 @@
     # The list of entities specifies the keys required for joining or looking
     # up features from this feature view. The reference provided in this field
     # correspond to the name of a defined entity (or entities)
-    entities=["driver_id"],
+    entities=["driver"],
     # The timedelta is the maximum age that each feature value may have
     # relative to its lookup time. For historical features (used in training),
     # TTL is relative to each timestamp provided in the entity dataframe.
@@ -60,7 +60,7 @@
     # Batch sources are used to find feature values. In the case of this feature
     # view we will query a source table on Redshift for driver statistics
     # features
-    batch_source=driver_stats_source,
+    source=driver_stats_source,
     # Tags are user defined key/value pairs that are attached to each
     # feature view
     tags={"team": "driver_performance"},

sdk/python/feast/templates/aws/driver_repo.py

@@ -8,7 +8,7 @@
 # construction of feature vectors
 driver = Entity(
     # Name of the entity. Must be unique within a project
-    name="driver_id",
+    name="driver",
     # The join key of an entity describes the storage level field/column on which
     # features can be looked up. The join key is also used to join feature
     # tables/views when building feature vectors
@@ -39,7 +39,7 @@
     # The list of entities specifies the keys required for joining or looking
     # up features from this feature view. The reference provided in this field
     # correspond to the name of a defined entity (or entities)
-    entities=["driver_id"],
+    entities=["driver"],
     # The timedelta is the maximum age that each feature value may have
     # relative to its lookup time. For historical features (used in training),
     # TTL is relative to each timestamp provided in the entity dataframe.
@@ -58,7 +58,7 @@
     # Batch sources are used to find feature values. In the case of this feature
     # view we will query a source table on BigQuery for driver statistics
     # features
-    batch_source=driver_stats_source,
+    source=driver_stats_source,
     # Tags are user defined key/value pairs that are attached to each
     # feature view
     tags={"team": "driver_performance"},

sdk/python/feast/templates/gcp/driver_repo.py

@@ -16,21 +16,21 @@
 
 # Define an entity for the driver. You can think of entity as a primary key used to
 # fetch features.
-driver = Entity(name="driver_id", value_type=ValueType.INT64, description="driver id",)
+driver = Entity(name="driver", join_key="driver_id", value_type=ValueType.INT64,)
 
 # Our parquet files contain sample data that includes a driver_id column, timestamps and
 # three feature column. Here we define a Feature View that will allow us to serve this
 # data to our model online.
 driver_hourly_stats_view = FeatureView(
     name="driver_hourly_stats",
-    entities=["driver_id"],
+    entities=["driver"],
     ttl=timedelta(days=1),
     schema=[
         Field(name="conv_rate", dtype=Float32),
         Field(name="acc_rate", dtype=Float32),
         Field(name="avg_daily_trips", dtype=Int64),
     ],
     online=True,
-    batch_source=driver_hourly_stats,
+    source=driver_hourly_stats,
     tags={},
 )

sdk/python/feast/templates/local/example.py

@@ -10,7 +10,7 @@
 # construction of feature vectors
 driver = Entity(
     # Name of the entity. Must be unique within a project
-    name="driver_id",
+    name="driver",
     # The join key of an entity describes the storage level field/column on which
     # features can be looked up. The join key is also used to join feature
     # tables/views when building feature vectors
@@ -43,7 +43,7 @@
     # The list of entities specifies the keys required for joining or looking
     # up features from this feature view. The reference provided in this field
     # correspond to the name of a defined entity (or entities)
-    entities=["driver_id"],
+    entities=["driver"],
     # The timedelta is the maximum age that each feature value may have
     # relative to its lookup time. For historical features (used in training),
     # TTL is relative to each timestamp provided in the entity dataframe.

sdk/python/feast/templates/snowflake/driver_repo.py

@@ -16,9 +16,9 @@
 
 
 # Entity definitions
-driver = Entity(name="driver_id", value_type=ValueType.INT64, description="driver id",)
+driver = Entity(name="driver", value_type=ValueType.INT64, description="driver id",)
 customer = Entity(
-    name="customer_id", value_type=ValueType.INT64, description="customer id",
+    name="customer", value_type=ValueType.INT64, description="customer id",
 )
 
 # Sources
@@ -40,27 +40,27 @@
 # Feature Views
 driver_hourly_stats_view = FeatureView(
     name="driver_hourly_stats",
-    entities=["driver_id"],
+    entities=["driver"],
     ttl=timedelta(days=7),
     schema=[
         Field(name="conv_rate", dtype=Float32),
         Field(name="acc_rate", dtype=Float32),
         Field(name="avg_daily_trips", dtype=Int64),
     ],
     online=True,
-    batch_source=driver_hourly_stats,
+    source=driver_hourly_stats,
     tags={},
 )
 customer_daily_profile_view = FeatureView(
     name="customer_daily_profile",
-    entities=["customer_id"],
+    entities=["customer"],
     ttl=timedelta(days=7),
     schema=[
         Field(name="current_balance", dtype=Float32),
         Field(name="avg_passenger_count", dtype=Float32),
         Field(name="lifetime_trip_count", dtype=Int64),
     ],
     online=True,
-    batch_source=customer_daily_profile,
+    source=customer_daily_profile,
     tags={},
 )

sdk/python/feast/templates/spark/example.py

@@ -29,7 +29,7 @@ def create_driver_hourly_stats_feature_view(source):
             Field(name="acc_rate", dtype=Float32),
             Field(name="avg_daily_trips", dtype=Int32),
         ],
-        batch_source=source,
+        source=source,
         ttl=timedelta(hours=2),
     )
     return driver_stats_feature_view