PyPI page
Home page
Author:
Artem Kazakov Kozlov
Summary:
Invoice and receipt OCR for Python: extract cited, validated data with local or hosted LLMs
Latest version:
0.5.0
Required dependencies:
httpx
|
pdfplumber
|
pillow
|
pydantic
|
pypdfium2
|
pytesseract
|
python-dotenv
|
scikit-learn
|
tomli
Optional dependencies:
build
|
datasets
|
docket-idp
|
docling
|
factur-x
|
fastapi
|
langfuse
|
lxml
|
mypy
|
opencv-python-headless
|
paddleocr
|
paddlepaddle
|
paddlex
|
psycopg
|
pymupdf
|
pytest
|
python-multipart
|
ruff
|
saxonche
|
sqlalchemy
|
streamlit
|
twine
|
uvicorn
Downloads last day:
2
Downloads last week:
24
Downloads last month:
478
7-day smoothing