pyproject.toml

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "gte-qwen2-7b-instruct-m2v"
version = "0.1.0"
description = "Model2Vec distillation pipeline for gte-Qwen2-7B-instruct"
readme = "README.md"
requires-python = ">=3.12"
dependencies = [
    "accelerate>=1.7.0",
    "beam-client>=0.2.155",
    "boto3>=1.38.23",
    "datasets>=3.6.0",
    "dotenv>=0.9.9",
    "editables>=0.5",
    "einops>=0.8.1",
    "flash-attn>=2.7.4.post1",
    "hatchling>=1.27.0",
    "iso639>=0.1.4",
    "jinja2>=3.0.0",
    "joblib>=1.0.0",
    "kaleido==1.0.0rc13",
    "lightning>=2.5.1.post0",
    "matplotlib>=3.10.3",
    "more-itertools>=10.5.0",
    "mteb>=1.14.15",
    "numpy>=1.26.4",
    "plotly>=6.1.1",
    "psutil>=7.0.0",
    "pydantic>=2.11.5",
    "requests>=2.32.3",
    "rich>=10.0.0",
    "safetensors>=0.3.0",
    "scikit-learn>=1.6.1",
    "seaborn>=0.13.2",
    "sentence-transformers>=4.1.0",
    "setuptools>=80.8.0",
    "skops>=0.11.0",
    "smart-open[s3]>=7.1.0",
    "statsmodels>=0.14.4",
    "tokenizers>=0.20",
    "torch>=2.7.0",
    "transformers<=4.52.1",
    "tqdm>=4.65.0",
    "typer>=0.16.0",
]

[project.scripts]
distiller = "distiller.__main__:app"

[dependency-groups]
dev = [
    "mypy>=1.15.0",
    "ruff>=0.11.6",
]

[tool.hatch.build.targets.wheel]
packages = ["src/distiller"]

[tool.mypy]
exclude = [
    ".git",
    ".ruff_cache",
    ".venv",
    "venv",
    "__pycache__",
    "build",
    "dist",
    "vendor",
]
follow_untyped_imports = true

[tool.ruff]
line-length = 120
target-version = "py312"

# Exclude files/directories
exclude = [
    ".git",
    ".ruff_cache",
    ".venv",
    "venv",
    "__pycache__",
    "build",
    "dist",
    "vendor",
    "src/distiller/model2vec",
    "src/distiller/tokenlearn"
]

[tool.ruff.lint]
# Enable all rules by default, then selectively disable
select = ["ALL"]
ignore = [
    # Rules that conflict with other tools/preferences
    "D203",  # one-blank-line-before-class
    "D212",  # multi-line-summary-first-line
    "FBT001",  # Boolean positional arg in function definition (required for typer)
    "FBT002",  # Boolean default value in function definition (required for typer)
    "C901",  # function too complex
    "PLR0911",  # too many return statements
    "PLR0912",  # too many branches
    "PLR0913",  # too many arguments in function definition
    "PLR0915",  # too many statements
    "TRY300",  # Consider moving this statement to an `else` block
    "COM812",  # Use a constant for the message in a raise statement
    "TC001",  # Move application import into a type-checking block
    "ERA001", # Found commented-out code
    "G004", # Logging statement uses f-string
    "TD003", # Missing link in to-do
    "TRY301", # Abstract raise to an inner function
    # Disable rules that conflict with tab indentation
    "E101",  # Indentation contains mixed spaces and tabs
    "W191",  # indentation contains tabs
    "D206",  # indent with spaces, not tabs
    "PD901", # Avoid using the generic variable name `df` for DataFrames
    "ANN401", # Dynamically typed expressions (typing.Any) are disallowed
    "D103",   # Missing docstring in public function
    "BLE001", # Do not catch blind exception: `Exception`
    "T201", # Use `logger.info` instead of `print`
    "E501", # Line too long
    "PLR2004",
    "RUF001",
    "D100", # Missing docstring in public module
    "D101", # Missing docstring in public class
]

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

[tool.ruff.lint.pylint]
max-args = 5
max-branches = 12
max-statements = 50

[tool.ruff.lint.pydocstyle]
convention = "google"

[tool.ruff.format]
quote-style = "double"
indent-style = "tab"
skip-magic-trailing-comma = false
line-ending = "auto"