attempt to fix parsing of tricky template files

2026-03-23 00:22:43 +00:00 · 2025-07-24 17:42:26 -07:00
1 changed files with 1 additions and 1 deletions
--- a/backend/onyx/file_processing/extract_file_text.py
+++ b/backend/onyx/file_processing/extract_file_text.py
@@ -317,7 +317,7 @@ def docx_to_text_and_images(

    try:
        doc = docx.Document(file)
-    except BadZipFile as e:
+    except (BadZipFile, ValueError) as e:
        logger.warning(
            f"Failed to extract docx {file_name or 'docx file'}: {e}. Attempting to read as text file."
        )