diff --git a/tests/unit/test_query/test_graph_embeddings_milvus_query.py b/tests/unit/test_query/test_graph_embeddings_milvus_query.py
index 6d856c96..5fbb74d5 100644
--- a/tests/unit/test_query/test_graph_embeddings_milvus_query.py
+++ b/tests/unit/test_query/test_graph_embeddings_milvus_query.py
@@ -443,16 +443,10 @@ class TestMilvusGraphEmbeddingsQueryProcessor:
             limit=0
         )
         
-        # Mock search results
-        mock_results = [
-            {"entity": {"entity": "http://example.com/entity1"}},
-        ]
-        processor.vecstore.search.return_value = mock_results
-        
         result = await processor.query_graph_embeddings(query)
         
-        # Verify search was called with 0 limit
-        processor.vecstore.search.assert_called_once_with([0.1, 0.2, 0.3], limit=0)
+        # Verify no search was called (optimization for zero limit)
+        processor.vecstore.search.assert_not_called()
         
         # Verify empty results due to zero limit
         assert len(result) == 0
diff --git a/trustgraph-flow/trustgraph/query/graph_embeddings/milvus/service.py b/trustgraph-flow/trustgraph/query/graph_embeddings/milvus/service.py
index 498ab483..7603f4d6 100755
--- a/trustgraph-flow/trustgraph/query/graph_embeddings/milvus/service.py
+++ b/trustgraph-flow/trustgraph/query/graph_embeddings/milvus/service.py
@@ -39,6 +39,10 @@ class Processor(GraphEmbeddingsQueryService):
             entity_set = set()
             entities = []
 
+            # Handle zero limit case
+            if msg.limit <= 0:
+                return []
+
             for vec in msg.vectors:
 
                 resp = self.vecstore.search(vec, limit=msg.limit * 2)