pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-30 00:32:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add MDX file support (#12261)

Browse Source 
Feat: add MDX file support  #12057 
### What problem does this PR solve?

<img width="1055" height="270" alt="image"
src="https://github.com/user-attachments/assets/a0ab49f9-7806-41cd-8a96-f593591ab36b"
/>

The page states that MDX files are supported, but uploading fails with
the error: "x.mdx: This type of file has not been supported yet!"
<img width="381" height="110" alt="image"
src="https://github.com/user-attachments/assets/4bbb7d08-cb47-416a-95fc-bc90b90fcc39"
/>


### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
lys1313013
2025-12-29 12:54:31 +08:00
committed by GitHub
parent 8d3f9d61da
commit 37e4485415
15 changed files with 41 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
rag/app/naive.py
View File

@ -823,7 +823,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", ca
parser_config.get("delimiter", "\n!?;。；！？"))
callback(0.8, "Finish parsing.")
elif re.search(r"\.(md|markdown)$", filename, re.IGNORECASE):
elif re.search(r"\.(md|markdown|mdx)$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
markdown_parser = Markdown(int(parser_config.get("chunk_token_num", 128)))
sections, tables, section_images = markdown_parser(

2
rag/app/one.py
View File

@ -128,7 +128,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
excel_parser = ExcelParser()
sections = excel_parser.html(binary, 1000000000)
elif re.search(r"\.(txt|md|markdown)$", filename, re.IGNORECASE):
elif re.search(r"\.(txt|md|markdown|mdx)$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
txt = get_text(filename, binary)
sections = txt.split("\n")

2
rag/app/qa.py
View File

@ -421,7 +421,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", ca
res.append(beAdocPdf(deepcopy(doc), q, a, eng, image, poss))
return res
elif re.search(r"\.(md|markdown)$", filename, re.IGNORECASE):
elif re.search(r"\.(md|markdown|mdx)$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
txt = get_text(filename, binary)
lines = txt.split("\n")