fix document extractor node incorrectly processing doc and ppt files (#12902)

This commit is contained in:
AugNSo
2025-02-12 18:04:28 +08:00
committed by GitHub
parent 6529240da6
commit 2b86465d4c
4 changed files with 59 additions and 14 deletions

View File

@@ -15,7 +15,7 @@ AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
if dify_config.ETL_TYPE == "Unstructured":
DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls"]
DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
DOCUMENT_EXTENSIONS.extend(("doc", "docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
if dify_config.UNSTRUCTURED_API_URL:
DOCUMENT_EXTENSIONS.append("ppt")
DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])