nltk security issue and upgrade unstructured (#9558)

This commit is contained in:
Jyong
2024-10-23 16:23:55 +08:00
committed by GitHub
parent ecc8beef3f
commit 3e9d271b52
13 changed files with 1664 additions and 781 deletions

View File

@@ -15,7 +15,9 @@ AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
if dify_config.ETL_TYPE == "Unstructured":
DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls"]
DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "ppt", "xml", "epub"))
DOCUMENT_EXTENSIONS.extend(("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])
else:
DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]