pyproject.toml

[build-system]
requires = ["poetry-core>=1.5.0"]
build-backend = "poetry.core.masonry.api"

[tool.poetry]
name = "llmdataparser"
version = "1.0.0"
description = "A collection of parsers for LLM benchmark datasets like MMLU, MMLU-Pro, GSM8k, and more."
authors = ["Jeff Yang <jeff52415@gmail.com>"]
license = "MIT"
readme = "README.md"
homepage = "https://github.com/jeff52415/LLMDataParser"
repository = "https://github.com/jeff52415/LLMDataParser"
keywords = ["LLM", "benchmark", "dataset", "parser", "NLP", "machine learning"]
classifiers = [
    "Programming Language :: Python :: 3",
    "License :: OSI Approved :: MIT License",
    "Operating System :: OS Independent",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Intended Audience :: Developers"
]

packages = [
    { include = "llmdataparser" }
]

[tool.poetry.scripts]
start = "llmdataparser.app:main"

[tool.poetry.dependencies]
python = ">=3.12"
pandas = "^2.0.3"
datasets = "^2.14.4"
typing-extensions = "^4.8.0"
ipywidgets = "^8.1.1"
gradio = "^4.19.2"
pyyaml = "^6.0.1"   # Add this for configuration handling
tqdm = "^4.66.1"    # Add this for progress bars
numpy = "^1.24.0"   # Add this for numerical operations

[tool.poetry.group.dev.dependencies]
pytest = "^7.0.0"
flake8 = "^6.1.0"
isort = "^5.12.0"
mypy = "^1.5.1"
pre-commit = "^3.4.0"
types-python-dateutil = "^2.8.19.14"
ipykernel = "^6.7.0"
coverage = "^7.4.1"
pytest-cov = "^4.1.0"
evaluate = "^0.4.0"

[tool.ruff]
line-length = 88

[tool.ruff.lint]
select = ["E", "F", "I"]
ignore = ["E501"]


[tool.isort]
profile = "black"
multi_line_output = 3
line_length = 88

[tool.mypy]
python_version = "3.12"
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
check_untyped_defs = true

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = ["test_*.py"]
addopts = "-ra -q --cov=llmdataparser --cov-report=term-missing"