fix page content is empty

2024-03-19 20:29:02 +08:00
1 changed files with 3 additions and 2 deletions
--- a/api/core/rag/index_processor/processor/paragraph_index_processor.py
+++ b/api/core/rag/index_processor/processor/paragraph_index_processor.py
@ -48,8 +48,9 @@ class ParagraphIndexProcessor(BaseIndexProcessor):
                        page_content = page_content[1:]
                    else:
                        page_content = page_content
-                    document_node.page_content = page_content
-                    split_documents.append(document_node)
+                    if page_content:
+                        document_node.page_content = page_content
+                        split_documents.append(document_node)
            all_documents.extend(split_documents)
        return all_documents