AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-12 10:48:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

del doc support (#2494)

Browse Source 
Co-authored-by: jyong <jyong@dify.ai>
This commit is contained in:
Jyong 2024-02-20 16:05:09 +08:00 committed by GitHub
parent 207080babc
commit 20b932da97
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
api/core/data_loader/file_extractor.py
View File

@ -69,7 +69,7 @@ class FileExtractor:
else MarkdownLoader(file_path, autodetect_encoding=True) else MarkdownLoader(file_path, autodetect_encoding=True)
elif file_extension in ['.htm', '.html']: elif file_extension in ['.htm', '.html']:
loader = HTMLLoader(file_path) loader = HTMLLoader(file_path)
elif file_extension in ['.docx', '.doc']: elif file_extension in ['.docx']:
loader = Docx2txtLoader(file_path) loader = Docx2txtLoader(file_path)
elif file_extension == '.csv': elif file_extension == '.csv':
loader = CSVLoader(file_path, autodetect_encoding=True) loader = CSVLoader(file_path, autodetect_encoding=True)
@ -96,7 +96,7 @@ class FileExtractor:
loader = MarkdownLoader(file_path, autodetect_encoding=True) loader = MarkdownLoader(file_path, autodetect_encoding=True)
elif file_extension in ['.htm', '.html']: elif file_extension in ['.htm', '.html']:
loader = HTMLLoader(file_path) loader = HTMLLoader(file_path)
elif file_extension in ['.docx', '.doc']: elif file_extension in ['.docx']:
loader = Docx2txtLoader(file_path) loader = Docx2txtLoader(file_path)
elif file_extension == '.csv': elif file_extension == '.csv':
loader = CSVLoader(file_path, autodetect_encoding=True) loader = CSVLoader(file_path, autodetect_encoding=True)

4
api/services/file_service.py
View File

@ -20,9 +20,9 @@ from services.errors.file import FileTooLargeError, UnsupportedFileTypeError
IMAGE_EXTENSIONS = ['jpg', 'jpeg', 'png', 'webp', 'gif', 'svg'] IMAGE_EXTENSIONS = ['jpg', 'jpeg', 'png', 'webp', 'gif', 'svg']
IMAGE_EXTENSIONS.extend([ext.upper() for ext in IMAGE_EXTENSIONS]) IMAGE_EXTENSIONS.extend([ext.upper() for ext in IMAGE_EXTENSIONS])
ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx', 'docx', 'doc', 'csv'] + IMAGE_EXTENSIONS ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx', 'docx', 'csv'] + IMAGE_EXTENSIONS
UNSTRUSTURED_ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx', UNSTRUSTURED_ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx',
'docx', 'doc', 'csv', 'eml', 'msg', 'pptx', 'ppt', 'xml'] + IMAGE_EXTENSIONS 'docx', 'csv', 'eml', 'msg', 'pptx', 'ppt', 'xml'] + IMAGE_EXTENSIONS
PREVIEW_WORDS_LIMIT = 3000 PREVIEW_WORDS_LIMIT = 3000