fix: preserve Postgres vector search filter SQL

python/semantic_kernel/connectors/postgres.py

@@ -795,9 +795,11 @@ def _construct_vector_query(
 
         if where_clauses := self._build_filter(options.filter):  # type: ignore
             query += (
-                sql.SQL("WHERE {clause}").format(clause=sql.SQL(" AND ").join(where_clauses))
+                sql.SQL(" WHERE {clause}").format(
+                    clause=sql.SQL(" AND ").join(sql.SQL(clause) for clause in where_clauses)
+                )
                 if isinstance(where_clauses, list)
-                else sql.SQL("WHERE {clause}").format(clause=where_clauses)
+                else sql.SQL(" WHERE {clause}").format(clause=sql.SQL(where_clauses))
             )
 
         query += sql.SQL(" ORDER BY {dist_col} LIMIT {limit}").format(

python/tests/unit/connectors/memory/test_postgres_store.py

@@ -17,7 +17,7 @@
     PostgresSettings,
     PostgresStore,
 )
-from semantic_kernel.data.vector import DistanceFunction, IndexKind, VectorStoreField, vectorstoremodel
+from semantic_kernel.data.vector import DistanceFunction, IndexKind, VectorSearchOptions, VectorStoreField, vectorstoremodel
 
 
 @fixture(scope="function")
@@ -322,6 +322,41 @@ def model_post_init(self, context: Any) -> None:
     assert statement_str == expected_statement
 
 
+async def test_vector_search_filter_is_emitted_as_sql(vector_store: PostgresStore) -> None:
+    @vectorstoremodel
+    @dataclass
+    class FilterDataModel:
+        id: Annotated[int, VectorStoreField("key")]
+        name: Annotated[str, VectorStoreField("data")]
+        embedding: Annotated[
+            list[float],
+            VectorStoreField(
+                "vector",
+                index_kind=IndexKind.HNSW,
+                dimensions=3,
+                distance_function=DistanceFunction.COSINE_DISTANCE,
+                type="float",
+            ),
+        ]
+
+    collection = vector_store.get_collection(collection_name="test_collection", record_type=FilterDataModel)
+    options = VectorSearchOptions(filter="lambda x: x.name == 'test'")
+
+    query, _, _ = collection._construct_vector_query([1.0, 2.0, 3.0], options)
+
+    assert ' WHERE "name" = \'test\'' in query.as_string()
+
+    options = VectorSearchOptions(filter=["lambda x: x.name == 'test'", "lambda x: x.id > 0"])
+    query, _, _ = collection._construct_vector_query([1.0, 2.0, 3.0], options)
+
+    assert ' WHERE "name" = \'test\' AND "id" > 0' in query.as_string()
+
+    options = VectorSearchOptions(filter=lambda x: x.name == "test")
+    query, _, _ = collection._construct_vector_query([1.0, 2.0, 3.0], options)
+
+    assert ' WHERE "name" = \'test\'' in query.as_string()
+
+
 async def test_model_post_init_conflicting_distance_column_name(vector_store: PostgresStore) -> None:
     @vectorstoremodel
     @dataclass