PyPI page
Home page
Author:
None
License:
Apache-2.0
Summary:
Apache 2.0 document parsing engine: PDF/DOCX/images → Markdown/JSON with tracked-changes (strikethrough) support
Latest version:
3.0.11
Required dependencies:
beautifulsoup4
|
boto3
|
click
|
fast-langdetect
|
fastapi
|
httpx
|
huggingface-hub
|
json-repair
|
loguru
|
lxml
|
magika
|
mammoth
|
mineros
|
mineru-vl-utils
|
modelscope
|
numpy
|
openai
|
opencv-python
|
openpyxl
|
pandas
|
pdfminer.six
|
pdftext
|
pillow
|
pylatexenc
|
pypdf
|
pypdfium2
|
pypptx-with-oxml
|
python-docx
|
python-multipart
|
qwen-vl-utils
|
reportlab
|
requests
|
scikit-image
|
tqdm
|
uvicorn
Optional dependencies:
accelerate
|
albumentations
|
coverage
|
dill
|
ftfy
|
fuzzywuzzy
|
gradio
|
gradio-pdf
|
lmdeploy
|
mineros
|
mlx-vlm
|
omegaconf
|
onnxruntime
|
pyclipper
|
pylint
|
pytest
|
pytest-cov
|
pyyaml
|
ruff
|
shapely
|
torch
|
torchvision
|
transformers
|
unoserver
|
vllm
Downloads last day:
6
Downloads last week:
19
Downloads last month:
514