PyPI page
Home page
Author:
None
License:
MIT
Summary:
Document parsing tool for LLM training and Rag
Latest version:
0.1.5
Required dependencies:
albumentations
|
bs4
|
cachetools
|
cn2an
|
datrie
|
effdet
|
hanziconv
|
html-text
|
langdetect
|
layoutparser
|
lxml
|
nltk
|
nougat-ocr
|
onnxruntime
|
opencv-python
|
openpyxl
|
pdfplumber
|
pyclipper
|
pypdf2
|
python-docx
|
python-pptx
|
roman-numbers
|
ruamel.yaml
|
shapely
|
strenum
|
tika
|
tiktoken
|
tokenizers
|
transformers
|
word2number
|
xgboost
Downloads last day:
5
Downloads last week:
21
Downloads last month:
38