pyproject.toml

[project]
name = "sonic-o1"
version = "0.1.0"
description = "SONIC-O1: A SOcial Natural Interaction Corpus for Omnimodal Video Understanding"
readme = "README.md"
authors = [{name = "Ahmed Radwan", email = "ahmed.radwan@vectorinstitute.ai"}]
license = "MIT"
requires-python = ">=3.10,<3.13"
dependencies = [
    # Core dependencies
    "numpy>=1.19,<2.0.0",
    "pandas>=2.0.0",
    "requests>=2.31.0",
    "pyyaml>=6.0.0",
    "tqdm>=4.65.0",
    "omegaconf>=2.3.0",
    # AI/ML APIs
    "openai>=1.0.0",
    "anthropic>=0.7.0",
    "google-genai>=1.36.06",
    # HuggingFace ecosystem - FIXED for transformers 4.57.3
    "datasets[vision,audio]>=3.4.0,<4.0.0",
    "transformers>=4.57.3,<4.58.0",
    "huggingface-hub>=0.16.0,<1.0.0",
    "tokenizers>=0.15.0,<1.0.0",
    "accelerate>=0.20.0",
    "qwen-omni-utils[decord]>=0.0.8",
    # PyTorch 2.5.x (stable)
    "torch>=2.5.0,<2.6.0",
    "torchvision>=0.20.0,<0.21.0",
    "torchaudio>=2.5.0,<2.6.0",
    # PyTorch Video
    "pytorchvideo",
    # Video/Audio downloading
    "yt-dlp>=2023.1.0",
    # Data handling
    "pyarrow>=12.0.0,<16.0.0",
    "fsspec[http]>=2023.10.0,<2025.0.0",
    "multiprocess>=0.70.15,<1.0.0",
    "dill>=0.3.7,<1.0.0",
    "xxhash>=3.0.0,<4.0.0",
    "aiohttp>=3.9.0,<4.0.0",
    # Video processing
    "av==12.3.0",
    "imageio>=2.25.0,<2.35.0",
    "imageio-ffmpeg>=0.4.7,<0.5.0",
    "moviepy>=1.0.3,<1.1.0",
    "decord>=0.6.0,<0.7.0",
    # Image/Video processing
    "pillow>=9.0.0,<11.0.0",
    "opencv-python-headless>=4.6.0,<4.10.0",
    # Audio processing - REQUIRED for Qwen2.5-Omni
    "librosa>=0.9.2,<0.11.0",
    "soundfile>=0.11.0,<0.13.0",
    "scipy>=1.9.0,<1.14.0",
    # Video codec support
    "ffmpeg-python>=0.2.0",
    # ImageBind dependencies
    "timm",
    "ftfy",
    "regex",
    "einops",
    "iopath",
    "types-regex",
    # Additional ML utilities
    "scikit-learn>=1.1.0,<1.5.0",
    "matplotlib>=3.5.0,<3.9.0",
    "seaborn>=0.11.0,<0.14.0",
    # Video dataset handling
    "webdataset>=0.2.0,<0.3.0",
    # Additional dependencies
    "packaging>=21.0",
    "filelock>=3.12.0",
    "python-dotenv>=1.1.1",
    "google-api-python-client>=2.184.0",
    "youtube-transcript-api>=1.2.2",
    "rouge-score>=0.1.2",
    "pycocoevalcap>=1.2",
    "sentence-transformers>=5.2.0",
    "openpyxl>=3.1.5",
]

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

[dependency-groups]
dev = [
    "pytest>=7.4.0",
    "ruff>=0.9.2",
    "jupyter>=1.0.0",
    "ipython>=8.12.0",
    "ipykernel>=6.0.0",
    "mypy>=1.19.1",
]

[tool.hatch.metadata]
allow-direct-references = true

[tool.uv]
default-groups = ["dev"]
index-strategy = "first-index"

[tool.uv.sources]
pytorchvideo = { git = "https://github.com/facebookresearch/pytorchvideo.git" }

[tool.hatch.build.targets.wheel]
packages = ["sonic-o1"]

[tool.mypy]
follow_imports = "normal"
ignore_missing_imports = false
install_types = true
pretty = true
non_interactive = true
allow_untyped_defs = false
no_implicit_optional = true
check_untyped_defs = true
namespace_packages = true
explicit_package_bases = true
warn_unused_configs = true
allow_subclassing_any = false
allow_untyped_calls = false
allow_incomplete_defs = false
allow_untyped_decorators = false
warn_redundant_casts = true
warn_unused_ignores = true
implicit_reexport = false
strict_equality = true
extra_checks = true
mypy_path = "sonic-o1"

[tool.ruff]
include = ["*.py", "pyproject.toml", "*.ipynb"]
exclude = []
line-length = 88

[tool.ruff.format]
quote-style = "double"
indent-style = "space"
docstring-code-format = true

[tool.ruff.lint]
select = [
    "A", # flake8-builtins
    "B", # flake8-bugbear
    "COM", # flake8-commas
    "C4", # flake8-comprehensions
    "RET", # flake8-return
    "SIM", # flake8-simplify
    "ICN", # flake8-import-conventions
    "Q", # flake8-quotes
    "RSE", # flake8-raise
    "D", # pydocstyle
    "E", # pycodestyle
    "F", # pyflakes
    "I", # isort
    "W", # pycodestyle
    "N", # pep8-naming
    "ERA", # eradicate
    "PL", # pylint
]

fixable = ["A", "B", "COM", "C4", "RET", "SIM", "ICN", "Q", "RSE", "D", "E", "F", "I", "W", "N", "ERA", "PL"]
ignore = [
    "B905", # `zip()` without an explicit `strict=` parameter
    "E501", # line too long
    "D203", # 1 blank line required before class docstring
    "D213", # Multi-line docstring summary should start at the second line
    "PLR2004", # Replace magic number with named constant
    "PLR0913", # Too many arguments
    "COM812", # Missing trailing comma
    "ERA001", # Found commented-out code (too many false positives with math comments)
    "A001", # Ignore variable `input` is shadowing a Python builtin (common for torch)
    "A002", # Ignore variable `input` is shadowing a Python builtin in function (common for torch)
    "D301", # r-strings for docstrings with backslashes
]

# Ignore import violations in all `__init__.py` files.
[tool.ruff.lint.per-file-ignores]
"__init__.py" = ["E402", "F401", "F403", "F811"]

[tool.ruff.lint.pep8-naming]
ignore-names = ["X*", "setUp"]

[tool.ruff.lint.isort]
lines-after-imports = 2

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

[tool.ruff.lint.pycodestyle]
max-doc-length = 88