feat: Support nested collection types (Array/Set of Array/Set) (#5947)

Add support for 2-level nested collection types: Array(Array(T)), Array(Set(T)), Set(Array(T)), and Set(Set(T)). - Add 4 generic ValueType enums (LIST_LIST, LIST_SET, SET_LIST, SET_SET) backed by RepeatedValue proto messages - Persist inner type info in Field tags (feast:nested_inner_type), following the existing Struct schema tag pattern - Handle edge cases: empty inner collections, Set dedup at inner level, depth limit enforcement (2 levels max) - Add proto/JSON/remote transport serialization support - Add 25 unit tests covering all combinations and edge cases Signed-off-by: Soojin Lee <lsjin0602@gmail.com> Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: soojin <soojin@dable.io>
feast-dev · franciscojavierarceo · Apr 2, 2026 · Mar 17, 2026 · Mar 18, 2026 · Mar 18, 2026
commit 5425a9299da9178f07863fd2f25d64de1623abf4
@@ -63,6 +63,10 @@ message ValueType {
     TIME_UUID_LIST = 39;
     UUID_SET = 40;
     TIME_UUID_SET = 41;
+    LIST_LIST = 42;
+    LIST_SET = 43;
+    SET_LIST = 44;
+    SET_SET = 45;
   }
 }
 
@@ -108,6 +112,10 @@ message Value {
     StringList time_uuid_list_val = 39;
     StringSet uuid_set_val = 40;
     StringSet time_uuid_set_val = 41;
+    RepeatedValue list_list_val = 42;
+    RepeatedValue list_set_val = 43;
+    RepeatedValue set_list_val = 44;
+    RepeatedValue set_set_val = 45;
   }
 }
 

@@ -23,6 +23,7 @@
 from feast.value_type import ValueType
 
 STRUCT_SCHEMA_TAG = "feast:struct_schema"
+NESTED_COLLECTION_INNER_TYPE_TAG = "feast:nested_inner_type"
 
 
 @typechecked
@@ -118,7 +119,7 @@ def __str__(self):
 
     def to_proto(self) -> FieldProto:
         """Converts a Field object to its protobuf representation."""
-        from feast.types import Array
+        from feast.types import Array, Set
 
         value_type = self.dtype.to_value_type()
         vector_search_metric = self.vector_search_metric or ""
@@ -128,6 +129,11 @@ def to_proto(self) -> FieldProto:
             tags[STRUCT_SCHEMA_TAG] = _serialize_struct_schema(self.dtype)
         elif isinstance(self.dtype, Array) and isinstance(self.dtype.base_type, Struct):
             tags[STRUCT_SCHEMA_TAG] = _serialize_struct_schema(self.dtype.base_type)
+        # Persist nested collection type info in tags
+        if isinstance(self.dtype, (Array, Set)) and isinstance(
+            self.dtype.base_type, (Array, Set)
+        ):
+            tags[NESTED_COLLECTION_INNER_TYPE_TAG] = _feast_type_to_str(self.dtype)
         return FieldProto(
             name=self.name,
             value_type=value_type.value,
@@ -155,17 +161,30 @@ def from_proto(cls, field_proto: FieldProto):
         # Reconstruct Struct type from persisted schema in tags
         from feast.types import Array
 
+        internal_tags = {STRUCT_SCHEMA_TAG, NESTED_COLLECTION_INNER_TYPE_TAG}
         dtype: FeastType
         if value_type == ValueType.STRUCT and STRUCT_SCHEMA_TAG in tags:
             dtype = _deserialize_struct_schema(tags[STRUCT_SCHEMA_TAG])
-            user_tags = {k: v for k, v in tags.items() if k != STRUCT_SCHEMA_TAG}
+            user_tags = {k: v for k, v in tags.items() if k not in internal_tags}
         elif value_type == ValueType.STRUCT_LIST and STRUCT_SCHEMA_TAG in tags:
             inner_struct = _deserialize_struct_schema(tags[STRUCT_SCHEMA_TAG])
             dtype = Array(inner_struct)
-            user_tags = {k: v for k, v in tags.items() if k != STRUCT_SCHEMA_TAG}
+            user_tags = {k: v for k, v in tags.items() if k not in internal_tags}
+        elif (
+            value_type
+            in (
+                ValueType.LIST_LIST,
+                ValueType.LIST_SET,
+                ValueType.SET_LIST,
+                ValueType.SET_SET,
+            )
+            and NESTED_COLLECTION_INNER_TYPE_TAG in tags
+        ):
+            dtype = _str_to_feast_type(tags[NESTED_COLLECTION_INNER_TYPE_TAG])
+            user_tags = {k: v for k, v in tags.items() if k not in internal_tags}
         else:
             dtype = from_value_type(value_type=value_type)
-            user_tags = tags
+            user_tags = {k: v for k, v in tags.items() if k not in internal_tags}
 
         return cls(
             name=field_proto.name,
@@ -198,6 +217,7 @@ def _feast_type_to_str(feast_type: FeastType) -> str:
     from feast.types import (
         Array,
         PrimitiveFeastType,
+        Set,
     )
 
     if isinstance(feast_type, PrimitiveFeastType):
@@ -209,6 +229,8 @@ def _feast_type_to_str(feast_type: FeastType) -> str:
         return json.dumps({"__struct__": nested})
     elif isinstance(feast_type, Array):
         return f"Array({_feast_type_to_str(feast_type.base_type)})"
+    elif isinstance(feast_type, Set):
+        return f"Set({_feast_type_to_str(feast_type.base_type)})"
     else:
         return str(feast_type)
 
@@ -218,6 +240,7 @@ def _str_to_feast_type(type_str: str) -> FeastType:
     from feast.types import (
         Array,
         PrimitiveFeastType,
+        Set,
     )
 
     # Check if it's an Array type
@@ -226,6 +249,12 @@ def _str_to_feast_type(type_str: str) -> FeastType:
         base_type = _str_to_feast_type(inner)
         return Array(base_type)
 
+    # Check if it's a Set type
+    if type_str.startswith("Set(") and type_str.endswith(")"):
+        inner = type_str[4:-1]
+        base_type = _str_to_feast_type(inner)
+        return Set(base_type)
+
     # Check if it's a nested Struct (JSON encoded)
     if type_str.startswith("{"):
         try:

@@ -106,6 +106,11 @@ def _proto_value_to_transport_value(proto_value: ValueProto) -> Any:
         if val_attr == "json_list_val":
             return list(getattr(proto_value, val_attr).val)
 
+        # Nested collection types use feast_value_type_to_python_type
+        # which handles recursive conversion of RepeatedValue protos.
+        if val_attr in ("list_list_val", "list_set_val", "set_list_val", "set_set_val"):
+            return feast_value_type_to_python_type(proto_value)
+
         # Map/Struct types are converted to Python dicts by
         # feast_value_type_to_python_type.  Serialise them to JSON strings
         # so the server-side DataFrame gets VARCHAR columns instead of

@@ -63,6 +63,12 @@ def to_json_object(printer: _Printer, message: ProtoMessage) -> JsonObject:
         # to JSON. The parse back result will be different from original message.
         if which is None or which == "null_val":
             return None
+        elif which in ("list_list_val", "list_set_val", "set_list_val", "set_set_val"):
+            # Nested collection: RepeatedValue containing Values
+            repeated = getattr(message, which)
+            value = [
+                printer._MessageToJsonObject(inner_val) for inner_val in repeated.val
+            ]
         elif "_list_" in which:
             value = list(getattr(message, which).val)
         else: