PyPI page
Home page
Author:
None
Summary:
A practical document parsing tool for converting PDF, OFD, EPUB, HTML, images, CSV, RTF, OOXML, and OpenDocument files into Markdown and JSON
Latest version:
4.0.10
Required dependencies:
aiosqlite
|
beautifulsoup4
|
click
|
docvortex
|
fastapi
|
filelock
|
ftfy
|
gradio
|
httpx
|
huggingface-hub
|
jieba
|
json-repair
|
lmdeploy
|
loguru
|
mineru
|
mineru-llama-cpp
|
mineru-vl-utils
|
modelscope
|
numpy
|
onnxruntime
|
openai
|
opencv-python
|
packaging
|
pillow
|
pyclipper
|
pydantic
|
pypdfium2
|
python-multipart
|
pyyaml
|
qwen-vl-utils
|
requests
|
rich
|
shapely
|
tinycss2
|
tokenizers
|
tomli
|
tqdm
|
typer
|
typing_extensions
|
uvicorn
|
vllm
|
watchfiles
Optional dependencies:
accelerate
|
coverage
|
fuzzywuzzy
|
lxml
|
lxml-stubs
|
mineru
|
pypdf
|
pytest
|
pytest-cov
|
reportlab
|
safetensors
|
torch
|
torchvision
|
transformers
Downloads last day:
3,471
Downloads last week:
27,666
Downloads last month:
96,874