diff --git a/embedchain/embedchain.py b/embedchain/embedchain.py
index 153b64d9..47fd2aa4 100644
--- a/embedchain/embedchain.py
+++ b/embedchain/embedchain.py
@@ -565,7 +565,7 @@ class EmbedChain(JSONSerializable):
         dry_run=False,
         where: Optional[Dict[str, str]] = None,
         **kwargs: Dict[str, Any],
-    ) -> str:
+    ) -> Union[Tuple[str, List[Tuple[str, str, str]]], str]:
         """
         Queries the vector database on the given input query.
         Gets relevant doc based on the query and then passes it to an
@@ -590,13 +590,10 @@ class EmbedChain(JSONSerializable):
         or the dry run result
         :rtype: str, if citations is False, otherwise Tuple[str,List[Tuple[str,str,str]]]
         """
-        if "citations" in kwargs:
-            citations = kwargs.pop("citations")
-        else:
-            citations = False
-
+        citations = kwargs.get("citations", False)
+        db_kwargs = {key: value for key, value in kwargs.items() if key != "citations"}
         contexts = self._retrieve_from_database(
-            input_query=input_query, config=config, where=where, citations=citations, **kwargs
+            input_query=input_query, config=config, where=where, citations=citations, **db_kwargs
         )
         if citations and len(contexts) > 0 and isinstance(contexts[0], tuple):
             contexts_data_for_llm_query = list(map(lambda x: x[0], contexts))
diff --git a/pyproject.toml b/pyproject.toml
index dd6e3b21..f5d998ff 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "embedchain"
-version = "0.1.27"
+version = "0.1.28"
 description = "Data platform for LLMs - Load, index, retrieve and sync any unstructured data"
 authors = [
     "Taranjeet Singh <taranjeet@embedchain.ai>",