diff --git a/litellm/proxy/rag_endpoints/endpoints.py b/litellm/proxy/rag_endpoints/endpoints.py
index 470372f1476..f9e0b724cb4 100644
--- a/litellm/proxy/rag_endpoints/endpoints.py
+++ b/litellm/proxy/rag_endpoints/endpoints.py
@@ -51,7 +51,17 @@ async def _save_vector_store_to_db_from_rag_ingest(
         create_vector_store_in_db,
     )
 
-    vector_store_id = response.get("vector_store_id")
+    # Handle both dict and object responses
+    if hasattr(response, "get"):
+        vector_store_id = response.get("vector_store_id")
+    elif hasattr(response, "vector_store_id"):
+        vector_store_id = response.vector_store_id
+    else:
+        verbose_proxy_logger.warning(
+            f"Unable to extract vector_store_id from response type: {type(response)}"
+        )
+        return
+
     if vector_store_id is None or not isinstance(vector_store_id, str):
         verbose_proxy_logger.warning(
             "Vector store ID is None or not a string, skipping database save"
@@ -81,16 +91,18 @@ async def _save_vector_store_to_db_from_rag_ingest(
                 prisma_client=prisma_client,
                 vector_store_name=f"RAG Vector Store - {vector_store_id[:8]}",
                 vector_store_description="Created via RAG ingest endpoint",
-                created_by=user_api_key_dict.user_id,
-                updated_by=user_api_key_dict.user_id,
             )
 
             verbose_proxy_logger.info(
                 f"Vector store {vector_store_id} saved to database successfully"
             )
+        else:
+            verbose_proxy_logger.info(
+                f"Vector store {vector_store_id} already exists in database, skipping creation"
+            )
     except Exception as db_error:
         # Log the error but don't fail the request since ingestion succeeded
-        verbose_proxy_logger.warning(
+        verbose_proxy_logger.exception(
             f"Failed to save vector store {vector_store_id} to database: {db_error}"
         )
 
@@ -261,18 +273,21 @@ async def rag_ingest(
         )
 
         # Save vector store to database if it was newly created and prisma_client is available
-        if (
-            prisma_client is not None
-            and response is not None
-            and isinstance(response, dict)
-            and response.get("vector_store_id")
-        ):
+        verbose_proxy_logger.debug(
+            f"RAG Ingest - Checking database save conditions: prisma_client={prisma_client is not None}, response={response is not None}, response_type={type(response)}"
+        )
+        
+        if prisma_client is not None and response is not None:
             await _save_vector_store_to_db_from_rag_ingest(
                 response=response,
                 ingest_options=ingest_options,
                 prisma_client=prisma_client,
                 user_api_key_dict=user_api_key_dict,
             )
+        else:
+            verbose_proxy_logger.warning(
+                f"Skipping database save: prisma_client={prisma_client is not None}, response={response is not None}"
+            )
 
         return response
 
diff --git a/litellm/proxy/vector_store_endpoints/management_endpoints.py b/litellm/proxy/vector_store_endpoints/management_endpoints.py
index 47adb8c03ba..f3787e62f4d 100644
--- a/litellm/proxy/vector_store_endpoints/management_endpoints.py
+++ b/litellm/proxy/vector_store_endpoints/management_endpoints.py
@@ -144,8 +144,7 @@ async def create_vector_store_in_db(
     vector_store_description: Optional[str] = None,
     vector_store_metadata: Optional[Dict] = None,
     litellm_params: Optional[Dict] = None,
-    created_by: Optional[str] = None,
-    updated_by: Optional[str] = None,
+    litellm_credential_name: Optional[str] = None,
 ) -> LiteLLM_ManagedVectorStore:
     """
     Helper function to create a vector store in the database.
@@ -190,13 +189,10 @@ async def create_vector_store_in_db(
         data_to_create["vector_store_description"] = vector_store_description
     if vector_store_metadata is not None:
         data_to_create["vector_store_metadata"] = safe_dumps(vector_store_metadata)
-    if created_by is not None:
-        data_to_create["created_by"] = created_by
-    if updated_by is not None:
-        data_to_create["updated_by"] = updated_by
+    if litellm_credential_name is not None:
+        data_to_create["litellm_credential_name"] = litellm_credential_name
     
-    # Handle litellm_params
-    litellm_params_json: Optional[str] = None
+    # Handle litellm_params - always provide at least an empty dict
     if litellm_params:
         # Auto-resolve embedding config if embedding model is provided but config is not
         embedding_model = litellm_params.get("litellm_embedding_model")
@@ -214,9 +210,10 @@ async def create_vector_store_in_db(
         litellm_params_dict = GenericLiteLLMParams(
             **litellm_params
         ).model_dump(exclude_none=True)
-        litellm_params_json = safe_dumps(litellm_params_dict)
-    
-    data_to_create["litellm_params"] = litellm_params_json
+        data_to_create["litellm_params"] = safe_dumps(litellm_params_dict)
+    else:
+        # Provide empty dict if no litellm_params provided
+        data_to_create["litellm_params"] = safe_dumps({})
     
     # Create in database
     _new_vector_store = (
@@ -290,8 +287,7 @@ async def new_vector_store(
             vector_store_description=vector_store.get("vector_store_description"),
             vector_store_metadata=validated_metadata,
             litellm_params=vector_store.get("litellm_params"),
-            created_by=user_api_key_dict.user_id,
-            updated_by=user_api_key_dict.user_id,
+            litellm_credential_name=vector_store.get("litellm_credential_name"),
         )
 
         return {