estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix: support mdx files close #11557 (#11565)

Browse Source 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
This commit is contained in:
yihong
2024-12-12 13:37:56 +08:00
committed by GitHub
parent e565ecdaef
commit 36cb25b341
5 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
api/constants/__init__.py
View File

@@ -14,11 +14,11 @@ 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 = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls"]
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"]
DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]
DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])

4
api/core/rag/extractor/extract_processor.py
View File

@@ -103,7 +103,7 @@ class ExtractProcessor:
extractor = ExcelExtractor(file_path)
elif file_extension == ".pdf":
extractor = PdfExtractor(file_path)
elif file_extension in {".md", ".markdown"}:
elif file_extension in {".md", ".markdown", ".mdx"}:
extractor = (
UnstructuredMarkdownExtractor(file_path, unstructured_api_url, unstructured_api_key)
if is_automatic
@@ -141,7 +141,7 @@ class ExtractProcessor:
extractor = ExcelExtractor(file_path)
elif file_extension == ".pdf":
extractor = PdfExtractor(file_path)
elif file_extension in {".md", ".markdown"}:
elif file_extension in {".md", ".markdown", ".mdx"}:
extractor = MarkdownExtractor(file_path, autodetect_encoding=True)
elif file_extension in {".htm", ".html"}:
extractor = HtmlExtractor(file_path)