PyPI page
Home page
Author:
None
License:
Apache-2.0
Summary:
A professional PDF parser, extracted from ragflow.deepdoc
Latest version:
0.1.7
Required dependencies:
beartype
|
beautifulsoup4
|
bs4
|
cn2an
|
datasets
|
datrie
|
docx2txt
|
dotenv
|
hanziconv
|
html-text
|
huggingface-hub
|
ipykernel
|
jpype1
|
langchain
|
langchain-community
|
langchain-core
|
langchain-unstructured
|
lxml
|
numpy
|
openai
|
openpyxl
|
pdf2image
|
pdfplumber
|
pi-heif
|
pillow
|
pyclipper
|
pycryptodome
|
pycryptodomex
|
pymupdf
|
python-docx
|
python-pptx
|
ragas
|
readability
|
roman-numbers
|
ruamel-yaml
|
sentence-transformers
|
shapely
|
strenum
|
trio
|
unstructured
|
unstructured-inference
|
unstructured-pytesseract
|
word2number
|
xgboost
Downloads last day:
9
Downloads last week:
38
Downloads last month:
62