Merge remote-tracking branch 'upstream/master'

Author: dchourasia

docs/getting-started/faq.md

@@ -39,7 +39,16 @@ Yes, this is possible. For example, you can use BigQuery as an offline store and
 
 ### How do I run `get_historical_features` without providing an entity dataframe?
 
-Feast does not provide a way to do this right now. This is an area we're actively interested in contributions for. See [GitHub issue](https://github.com/feast-dev/feast/issues/1611)
+Feast does supports fetching historical features without passing an entity dataframe with the request. 
+- As of today, only `postgres offline feature store` is supported for entity dataframe less retrieval. Remaining offline stores would be gradually updated to support the entity df less retrieval. The stores would be selected based on priorities and user base/request. 
+- The retrieval is based on `start_date` and `end_date` parameters to the function. Here are some combinations supported.
+  - Both params are given, Returns data during the given start to end timerange.
+  - Only start_date param is given, Returns data from the start date to `now` time.
+  - Only end_date param is given, Returns data during the end_date minus TTL time in feature view.
+  - Both params are `not` given, Returns data during the TTL time in feature view to now time.
+- When multiple features are requested from multiple feature-views it is required to have entity ids in both of them for `JOIN` so that 
+
+This is an area we're actively interested in contributions for. See [GitHub issue](https://github.com/feast-dev/feast/issues/1611)
 
 ### Does Feast provide security or access control?
 

sdk/python/feast/cli/features.py

@@ -1,4 +1,5 @@
 import json
+from datetime import datetime
 from typing import List
 
 import click
@@ -140,37 +141,69 @@ def get_online_features(ctx: click.Context, entities: List[str], features: List[
     "--dataframe",
     "-d",
     type=str,
-    required=True,
     help='JSON string containing entities and timestamps. Example: \'[{"event_timestamp": "2025-03-29T12:00:00", "driver_id": 1001}]\'',
 )
 @click.option(
     "--features",
     "-f",
     multiple=True,
-    required=True,
     help="Features to retrieve. feature-view:feature-name ex: driver_hourly_stats:conv_rate",
 )
+@click.option(
+    "--start-date",
+    "-s",
+    type=str,
+    help="Start date for historical feature retrieval. Format: YYYY-MM-DD HH:MM:SS",
+)
+@click.option(
+    "--end-date",
+    "-e",
+    type=str,
+    help="End date for historical feature retrieval. Format: YYYY-MM-DD HH:MM:SS",
+)
 @click.pass_context
-def get_historical_features(ctx: click.Context, dataframe: str, features: List[str]):
+def get_historical_features(
+    ctx: click.Context,
+    dataframe: str,
+    features: List[str],
+    start_date: str,
+    end_date: str,
+):
     """
     Fetch historical feature values for a given entity ID
     """
     store = create_feature_store(ctx)
-    try:
-        entity_list = json.loads(dataframe)
-        if not isinstance(entity_list, list):
-            raise ValueError("Entities must be a list of dictionaries.")
-
-        entity_df = pd.DataFrame(entity_list)
-        entity_df["event_timestamp"] = pd.to_datetime(entity_df["event_timestamp"])
+    if not dataframe and not start_date and not end_date:
+        click.echo(
+            "Either --dataframe or --start-date and/or --end-date must be provided."
+        )
+        return
 
-    except Exception as e:
-        click.echo(f"Error parsing entities JSON: {e}", err=True)
+    if dataframe and (start_date or end_date):
+        click.echo("Cannot specify both --dataframe and --start-date/--end-date.")
         return
 
+    entity_df = None
+    if dataframe:
+        try:
+            entity_list = json.loads(dataframe)
+            if not isinstance(entity_list, list):
+                raise ValueError("Entities must be a list of dictionaries.")
+
+            entity_df = pd.DataFrame(entity_list)
+            entity_df["event_timestamp"] = pd.to_datetime(entity_df["event_timestamp"])
+
+        except Exception as e:
+            click.echo(f"Error parsing entities JSON: {e}", err=True)
+            return
+
     feature_vector = store.get_historical_features(
         entity_df=entity_df,
         features=list(features),
+        start_date=datetime.strptime(start_date, "%Y-%m-%d %H:%M:%S")
+        if start_date
+        else None,
+        end_date=datetime.strptime(end_date, "%Y-%m-%d %H:%M:%S") if end_date else None,
     ).to_df()
 
     click.echo(feature_vector.to_json(orient="records", indent=4))

sdk/python/feast/feature_store.py

@@ -1087,14 +1087,17 @@ def teardown(self):
 
     def get_historical_features(
         self,
-        entity_df: Union[pd.DataFrame, str],
-        features: Union[List[str], FeatureService],
+        entity_df: Optional[Union[pd.DataFrame, str]] = None,
+        features: Union[List[str], FeatureService] = [],
         full_feature_names: bool = False,
+        start_date: Optional[datetime] = None,
+        end_date: Optional[datetime] = None,
     ) -> RetrievalJob:
         """Enrich an entity dataframe with historical feature values for either training or batch scoring.
 
         This method joins historical feature data from one or more feature views to an entity dataframe by using a time
-        travel join.
+        travel join. Alternatively, features can be retrieved for a specific timestamp range without requiring an entity
+        dataframe.
 
         Each feature view is joined to the entity dataframe using all entities configured for the respective feature
         view. All configured entities must be available in the entity dataframe. Therefore, the entity dataframe must
@@ -1105,16 +1108,21 @@ def get_historical_features(
         TTL may result in null values being returned.
 
         Args:
-            entity_df (Union[pd.DataFrame, str]): An entity dataframe is a collection of rows containing all entity
-                columns (e.g., customer_id, driver_id) on which features need to be joined, as well as a event_timestamp
-                column used to ensure point-in-time correctness. Either a Pandas DataFrame can be provided or a string
-                SQL query. The query must be of a format supported by the configured offline store (e.g., BigQuery)
             features: The list of features that should be retrieved from the offline store. These features can be
                 specified either as a list of string feature references or as a feature service. String feature
                 references must have format "feature_view:feature", e.g. "customer_fv:daily_transactions".
+            entity_df (Optional[Union[pd.DataFrame, str]]): An entity dataframe is a collection of rows containing all entity
+                columns (e.g., customer_id, driver_id) on which features need to be joined, as well as a event_timestamp
+                column used to ensure point-in-time correctness. Either a Pandas DataFrame can be provided or a string
+                SQL query. The query must be of a format supported by the configured offline store (e.g., BigQuery).
+                If not provided, features will be retrieved for the specified timestamp range without entity joins.
             full_feature_names: If True, feature names will be prefixed with the corresponding feature view name,
                 changing them from the format "feature" to "feature_view__feature" (e.g. "daily_transactions"
                 changes to "customer_fv__daily_transactions").
+            start_date (Optional[datetime]): Start date for the timestamp range when retrieving features without entity_df.
+                Required when entity_df is not provided.
+            end_date (Optional[datetime]): End date for the timestamp range when retrieving features without entity_df.
+                Required when entity_df is not provided. By default, the current time is used.
 
         Returns:
             RetrievalJob which can be used to materialize the results.
@@ -1147,6 +1155,15 @@ def get_historical_features(
             ... )
             >>> feature_data = retrieval_job.to_df()
         """
+
+        if entity_df is not None and (start_date is not None or end_date is not None):
+            raise ValueError(
+                "Cannot specify both entity_df and start_date/end_date. Use either entity_df for entity-based retrieval or start_date/end_date for timestamp range retrieval."
+            )
+
+        if entity_df is None and end_date is None:
+            end_date = datetime.now()
+
         _feature_refs = utils._get_features(self._registry, self.project, features)
         (
             all_feature_views,
@@ -1180,6 +1197,13 @@ def get_historical_features(
         utils._validate_feature_refs(_feature_refs, full_feature_names)
         provider = self._get_provider()
 
+        # Optional kwargs
+        kwargs = {}
+        if start_date is not None:
+            kwargs["start_date"] = start_date
+        if end_date is not None:
+            kwargs["end_date"] = end_date
+
         job = provider.get_historical_features(
             self.config,
             feature_views,
@@ -1188,6 +1212,7 @@ def get_historical_features(
             self._registry,
             self.project,
             full_feature_names,
+            **kwargs,
         )
 
         return job