pyproject.toml

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

[project]
name = "sieves"
readme = "README.md"
description = "Rapid prototyping and robust baselines for information extraction with zero- and few-shot models."
license = { text = "MIT" }
dynamic = ["version", "authors"]
requires-python = ">=3.10"
dependencies = [
    "loguru>=0.7.3"
]
classifiers = [
    "Development Status :: 3 - Alpha",
    "Intended Audience :: Developers",
    "Topic :: Software Development :: Libraries",
    "License :: OSI Approved :: MIT License",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12"
]

[project.optional-dependencies]
all = [
    "chonkie>=0.3",
    "docling>=2",
    "outlines>=0.0.34",
    "dspy-ai>=2,<3",
    "chonkie>=0.3",
    "transformers>=4,<5",
    "loguru>=0.7.3",
    "sentencepiece<1",
    "gliner<1",
    "ollama<1",
    "langchain>=0.3,<0.4",
    "scikit-learn>=1,<2",
    "unstructured[all-docs]>=0.16,<1",
    "unstructured-inference>=0.8,<1",
]
utils = [
    "chonkie>=0.3",
    "docling>=2",
    "unstructured[all-docs]>=0.16,<1",
    "unstructured-inference>=0.8,<1",
    "tesseract>=0.1,<1"
]
engines = [
    "outlines>=0.0.34",
    "dspy-ai>=2,<3",
    "transformers>=4,<5",
    "sentencepiece<1",
    "gliner<1",
    "ollama<1",
    "langchain>=0.3,<0.4",
    "scikit-learn>=1,<2"
]
test = [
    "pytest>=7.4.3",
    "pytest-cov>=4.1.0",
    "pytest-asyncio>=0.21.1",
    "mypy>=1",
    "mypy-extensions>=1",
    "pytest-cov>=6",
    "langchain-anthropic>0.3,<0.4",
    "tesseract>=0.1,<1",
    # For generating documentation.
    "mkdocstrings[python]>=0.27,<1",
    "mkdocs-material>=9.6,<10"
]

[tool.black]
line-length = 120
target-version = ['py310']
include = '\.pyi?$'

[tool.ruff]
line-length = 120
target-version = "py310"

# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)
select = ["E", "F", "I", "UP"]
ignore = []

# Allow autofix for all enabled rules (when `--fix`) is provided.
fixable = ["ALL"]
unfixable = ["F401"]

# Exclude a variety of commonly ignored directories.
exclude = [
    ".bzr",
    ".direnv",
    ".eggs",
    ".git",
    ".git-rewrite",
    ".hg",
    ".mypy_cache",
    ".nox",
    ".pants.d",
    ".pytype",
    ".ruff_cache",
    ".svn",
    ".tox",
    ".venv",
    "__pypackages__",
    "_build",
    "buck-out",
    "build",
    "dist",
    "node_modules",
    "venv",
    ".venv"
]

[tool.ruff.mccabe]
max-complexity = 10

[tool.ruff.isort]
known-first-party = ["sieves"]

[tool.mypy]
python_version = "3.10"
strict = true
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
disallow_untyped_decorators = true
no_implicit_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
warn_no_return = true
warn_unreachable = true
allow_untyped_globals = false
allow_redefinition = false
implicit_reexport = false
strict_equality = true
ignore_missing_imports = true

# Per-module ignores for third-party libraries
[[tool.mypy.overrides]]
module = ["outlines.*", "docling.*", "chonkie.*", "tqdm.*", "dspy.*"]
ignore_missing_imports = true
follow_imports = "skip"

[tool.pytest.ini_options]
markers = [
  "slow: marks tests as slow (deselect with '-m not slow')"
]