diff --git a/apps/application/flow/step_node/document_extract_node/impl/base_document_extract_node.py b/apps/application/flow/step_node/document_extract_node/impl/base_document_extract_node.py
index 4e7b2f660..1802f68d3 100644
--- a/apps/application/flow/step_node/document_extract_node/impl/base_document_extract_node.py
+++ b/apps/application/flow/step_node/document_extract_node/impl/base_document_extract_node.py
@@ -16,7 +16,7 @@ class BaseDocumentExtractNode(IDocumentExtractNode):
         self.context['document_list'] = document
         content = []
         splitter = '\n`-----------------------------------`\n'
-        if document is None:
+        if document is None or not isinstance(document, list):
             return NodeResult({'content': content}, {})
 
         for doc in document:
diff --git a/apps/application/flow/step_node/image_understand_step_node/impl/base_image_understand_node.py b/apps/application/flow/step_node/image_understand_step_node/impl/base_image_understand_node.py
index 813cd3158..cc077a9ca 100644
--- a/apps/application/flow/step_node/image_understand_step_node/impl/base_image_understand_node.py
+++ b/apps/application/flow/step_node/image_understand_step_node/impl/base_image_understand_node.py
@@ -66,6 +66,10 @@ class BaseImageUnderstandNode(IImageUnderstandNode):
     def execute(self, model_id, system, prompt, dialogue_number, dialogue_type, history_chat_record, stream, chat_id, chat_record_id,
                 image,
                 **kwargs) -> NodeResult:
+        # 处理不正确的参数
+        if image is None or not isinstance(image, list):
+            image = []
+
         image_model = get_model_instance_by_model_user_id(model_id, self.flow_params_serializer.data.get('user_id'))
         # 执行详情中的历史消息不需要图片内容
         history_message =self.get_history_message_for_details(history_chat_record, dialogue_number)