pyproject.toml

[build-system]
requires = ["setuptools"]
build-backend = "setuptools.build_meta"

[project]
name = "text_extract_api"
version = "0.2.0"
description = "Images and documents (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown"
authors = [
]
license = { text = "MIT License" }
readme = "README.md"
requires-python = ">=3.8"
dependencies = [
    "fastapi",
    "easyocr",
    "celery",
    "redis",
    "opencv-python-headless",
    "pdf2image",
    "ollama",
    "uvicorn[standard]",
    "requests",
    "python-multipart",
    "pdftext",
    "argparse",
    "google-api-python-client",
    "google-auth-httplib2",
    "google-auth-oauthlib",
    "transformers",
    "boto3",
    "Pillow",
    "python-magic==0.4.27",
    "maker",
    "setuptools",
    "PyYAML",
    "botocore",
    "protobuf",
    "opencv-python",
    "numpy",
    "pydantic",
    "python-dotenv",
]
[project.optional-dependencies]
dev = [
    "pytest",
    "black",
    "isort",
    "flake8",
]

[tool.black]
line-length = 88

[tool.isort]
profile = "black"
multi_line_output = 3

[tool.pytest]
testpaths = ["tests"]
python_files = ["test_*.py"]

[tool.flake8]
max-line-length = 88
exclude = ["venv", "__pycache__", ".git", ".mypy_cache"]

[tool.setuptools.packages.find]
where = ["text_extract_api"]
include = ["text_extract_api.*"]