pyproject.toml

[tool.poetry]
name = "surya-ocr"
version = "0.5.0"
description = "OCR, layout, reading order, and line detection in 90+ languages"
authors = ["Vik Paruchuri <vik.paruchuri@gmail.com>"]
readme = "README.md"
license = "GPL-3.0-or-later"
repository = "https://github.com/VikParuchuri/surya"
keywords = ["ocr", "pdf", "text detection", "text recognition"]
packages = [
    {include = "surya"}
]
include = [
    "detect_text.py",
    "ocr_text.py",
    "ocr_app.py",
    "run_ocr_app.py",
    "detect_layout.py",
    "reading_order.py",
]

[tool.poetry.dependencies]
python = ">=3.9,<3.13,!=3.9.7"
transformers = "^4.41.0"
torch = "^2.3.0"
pydantic = "^2.5.3"
pydantic-settings = "^2.1.0"
python-dotenv = "^1.0.0"
pillow = "^10.2.0"
pypdfium2 = "^4.25.0"
opencv-python = "^4.9.0.80"
tabulate = "^0.9.0"
filetype = "^1.2.0"
ftfy = "^6.1.3"
pdftext = "^0.3.10"

[tool.poetry.group.dev.dependencies]
jupyter = "^1.0.0"
pytesseract = "^0.3.10"
pymupdf = "^1.23.8"
snakeviz = "^2.2.0"
datasets = "^2.16.1"
rapidfuzz = "^3.6.1"
arabic-reshaper = "^3.0.0"
streamlit = "^1.31.0"
playwright = "^1.41.2"

[tool.poetry.scripts]
surya_detect = "detect_text:main"
surya_ocr = "ocr_text:main"
surya_layout = "detect_layout:main"
surya_gui = "run_ocr_app:run_app"
surya_order = "reading_order:main"

[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"