mirror of
https://github.com/NVIDIA-NeMo/DataDesigner
synced 2026-05-24 09:48:29 +00:00
118 lines
2.8 KiB
TOML
118 lines
2.8 KiB
TOML
[project]
|
|
name = "data-designer"
|
|
dynamic = ["version"]
|
|
description = "General framework for synthetic data generation"
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Science/Research",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
"Topic :: Scientific/Engineering :: Human Machine Interfaces",
|
|
"Topic :: Software Development",
|
|
"License :: Other/Proprietary License",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
]
|
|
|
|
dependencies = [
|
|
"huggingface-hub>=0.34.4",
|
|
"jinja2>=3.1.6,<4",
|
|
"numpy>=1.23.5",
|
|
"pandas>=1.5.3",
|
|
"pyarrow>=19.0.1",
|
|
"pydantic>=2.9.2",
|
|
"pygments>=2.19.2",
|
|
"pyyaml>=6.0.1",
|
|
"python-json-logger==2.0.7",
|
|
"requests<3,>=2.32.2",
|
|
"rich>=13.7.1",
|
|
"anyascii>=0.3.3,<1.0",
|
|
"boto3==1.35.74",
|
|
"datasets>=4.0.0",
|
|
"duckdb==1.1.3",
|
|
"faker==20.1.0",
|
|
"httpx>=0.27.2",
|
|
"httpx-retries>=0.4.2",
|
|
"json-repair==0.48.0",
|
|
"jsonpath-rust-bindings>=1.0",
|
|
"litellm==1.73.6",
|
|
"lxml>=6.0.2",
|
|
"marko==2.1.2",
|
|
"networkx==3.0",
|
|
"pydantic[email]>=2.9.2",
|
|
"scipy>=1.11.0",
|
|
"smart-open==7.0.5",
|
|
"sqlfluff==3.2.0",
|
|
"tiktoken>=0.8.0",
|
|
"ruff==0.12.3",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"jsonpath-ng==1.5.3",
|
|
"pre-commit>=4.0.0",
|
|
"pytest>=8.3.3",
|
|
"pytest-asyncio>=0.24.0",
|
|
"pytest-cov>=7.0.0",
|
|
"pytest-httpx>=0.35.0",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["hatchling", "hatch-vcs"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.version]
|
|
source = "vcs"
|
|
fallback-version = "0.1.0.dev0"
|
|
|
|
[tool.hatch.build.hooks.vcs]
|
|
version-file = "src/data_designer/_version.py"
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
asyncio_default_fixture_loop_scope = "session"
|
|
|
|
[tool.uv]
|
|
package = true
|
|
required-version = ">=0.7.10"
|
|
|
|
[tool.ruff]
|
|
line-length = 120
|
|
indent-width = 4
|
|
|
|
[tool.ruff.lint]
|
|
select = [
|
|
# "E", # pycodestyle errors
|
|
"W", # pycodestyle warnings
|
|
"F", # pyflakes
|
|
"I", # isort (import sorting)
|
|
# "N", # pep8-naming
|
|
# "UP", # pyupgrade (modern Python syntax)
|
|
# "ANN", # flake8-annotations (enforce type hints)
|
|
# "B", # fla e8-bugbear (common bugs)
|
|
# "C4", # flake8-comprehensions
|
|
# "DTZ", # flake8-datetimez (timezone awareness)
|
|
"ICN", # flake8-import-conventions
|
|
"PIE", # flake8-pie (misc lints)
|
|
# "RET", # flake8-return
|
|
# "SIM", # flake8-simplify
|
|
# "PTH", # flake8-use-pathlib
|
|
]
|
|
ignore = [
|
|
"ANN401", # Dynamically typed expressions (Any)
|
|
]
|
|
|
|
[tool.ruff.lint.isort]
|
|
known-first-party = ["data_designer"]
|
|
force-sort-within-sections = true
|
|
|
|
[tool.ruff.format]
|
|
quote-style = "double"
|
|
indent-style = "space"
|
|
skip-magic-trailing-comma = false
|
|
line-ending = "auto"
|