PyPI page
Home page
Author:
None
Summary:
A practical document parsing tool for converting PDF, images, DOCX, PPTX, and XLSX into Markdown and JSON
Latest version:
4.0.0.dev2026070601
Required dependencies:
aiosqlite
|
beautifulsoup4
|
click
|
fast-langdetect
|
fastapi
|
httpx
|
huggingface-hub
|
jieba
|
json-repair
|
lmdeploy
|
loguru
|
lxml
|
magika
|
mammoth
|
mineru
|
mineru-vl-utils
|
mlx
|
mlx-vlm
|
modelscope
|
numpy
|
onnxruntime
|
openai
|
opencv-python
|
openpyxl
|
packaging
|
pdftext
|
pillow
|
pydantic
|
pylatexenc
|
pypdf
|
pypdfium2
|
pypptx-with-oxml
|
python-docx
|
python-multipart
|
pyyaml
|
qwen-vl-utils
|
reportlab
|
requests
|
rich
|
tomli
|
tqdm
|
typer
|
uvicorn
|
vllm
|
watchfiles
Optional dependencies:
accelerate
|
coverage
|
ftfy
|
fuzzywuzzy
|
gradio
|
gradio-pdf
|
lmdeploy
|
lxml-stubs
|
mineru
|
mlx
|
mlx-vlm
|
pyclipper
|
pytest
|
pytest-cov
|
qwen-vl-utils
|
safetensors
|
shapely
|
six
|
torch
|
torchvision
|
transformers
|
vllm
Downloads last day:
154
Downloads last week:
442
Downloads last month:
635