feast-dev
@@ -75,6 +75,7 @@ class GetOnlineFeaturesRequest(BaseModel):
     features: Optional[List[str]] = None
     full_feature_names: bool = False
     query_embedding: Optional[List[float]] = None
+    query_string: Optional[str] = None
 
 
 def _get_features(request: GetOnlineFeaturesRequest, store: "feast.FeatureStore"):
@@ -195,6 +196,7 @@ async def retrieve_online_documents(
             entity_rows=request.entities,
             full_feature_names=request.full_feature_names,
             query=request.query_embedding,
+            query_string=request.query_string,
         )
 
         response = await run_in_threadpool(

@@ -1867,6 +1867,7 @@ def retrieve_online_documents_v2(
         top_k: int,
         features: List[str],
         distance_metric: Optional[str] = "L2",
+        query_string: Optional[str] = None,
     ) -> OnlineResponse:
         """
         Retrieves the top k closest document features. Note, embeddings are a subset of features.
@@ -1878,6 +1879,7 @@ def retrieve_online_documents_v2(
             query: The query to retrieve the closest document features for.
             top_k: The number of closest document features to retrieve.
             distance_metric: The distance metric to use for retrieval.
+            query_string: The query string to retrieve the closest document features using keyword search (bm25).
         """
         if isinstance(query, str):
             raise ValueError(
@@ -1919,6 +1921,7 @@ def retrieve_online_documents_v2(
             query,
             top_k,
             distance_metric,
+            query_string,
         )
 
     def _retrieve_from_online_store(
@@ -1988,6 +1991,7 @@ def _retrieve_from_online_store_v2(
         query: List[float],
         top_k: int,
         distance_metric: Optional[str],
+        query_string: Optional[str],
     ) -> OnlineResponse:
         """
         Search and return document features from the online document store.
@@ -2003,6 +2007,7 @@ def _retrieve_from_online_store_v2(
             query=query,
             top_k=top_k,
             distance_metric=distance_metric,
+            query_string=query_string,
         )
 
         entity_key_dict: Dict[str, List[ValueProto]] = {}

@@ -191,6 +191,10 @@ def __init__(
             else:
                 features.append(field)
 
+        assert len([f for f in features if f.vector_index]) < 2, (
+            f"Only one vector feature is allowed per feature view. Please update {self.name}."
+        )
+
         # TODO(felixwang9817): Add more robust validation of features.
         cols = [field.name for field in schema]
         for col in cols:

@@ -463,6 +463,7 @@ def retrieve_online_documents_v2(
         embedding: List[float],
         top_k: int,
         distance_metric: Optional[str] = None,
+        query_string: Optional[str] = None,
     ) -> List[
         Tuple[
             Optional[datetime],

@@ -439,6 +439,7 @@ def retrieve_online_documents_v2(
         embedding: List[float],
         top_k: int,
         distance_metric: Optional[str] = None,
+        query_string: Optional[str] = None,
     ) -> List[
         Tuple[
             Optional[datetime],
@@ -456,6 +457,7 @@ def retrieve_online_documents_v2(
             requested_features: The list of features whose embeddings should be used for retrieval.
             embedding: The embeddings to use for retrieval.
             top_k: The number of documents to retrieve.
+            query_string: The query string to search for using keyword search (bm25) (optional)
 
         Returns:
             object: A list of top k closest documents to the specified embedding. Each item in the list is a tuple