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

[project]
name = "soup-cli"
version = "0.53.10"
description = "Fine-tune LLMs in one command. No SSH, no config hell."
readme = "README.md"
license = "Apache-2.0"
requires-python = ">=3.9"
authors = [
    { name = "Soup Team" },
]
keywords = ["llm", "fine-tuning", "lora", "qlora", "machine-learning"]
classifiers = [
    "Development Status :: 3 - Alpha",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
]
dependencies = [
    "typer>=0.9.0,<0.21.0",
    "rich>=13.0.0",
    "pydantic>=2.0.0",
    "pyyaml>=6.0",
    "torch>=2.0.0",
    "transformers>=4.36.0,<5.0.0",
    "peft>=0.7.0",
    "trl>=0.7.0",
    "datasets>=2.14.0",
    "bitsandbytes>=0.41.0",
    "accelerate>=0.25.0",
    "huggingface-hub>=0.16.0",
    "plotext>=5.2.0",
]

[project.optional-dependencies]
eval = ["lm-eval>=0.4.0"]
data = ["datasketch>=1.6.0"]
wandb = ["wandb>=0.15.0,<0.18.0"]
dev = ["pytest>=7.0", "ruff>=0.1.0", "pytest-cov>=4.0", "httpx>=0.24.0"]
ui = ["fastapi>=0.104.0", "uvicorn>=0.24.0"]
serve = ["fastapi>=0.104.0", "uvicorn>=0.24.0"]
serve-fast = ["vllm>=0.4.0", "fastapi>=0.104.0", "uvicorn>=0.24.0"]
generate = ["httpx>=0.24.0"]
deepspeed = ["deepspeed>=0.12.0"]
fast = ["unsloth>=2024.8"]
vision = ["Pillow>=9.0.0"]
qat = ["torchao>=0.4.0"]
liger = ["liger-kernel>=0.3.0"]
ring-attn = ["ring-flash-attn>=0.1.0"]
onnx = ["optimum[onnxruntime]>=1.16.0"]
tensorrt = ["tensorrt_llm>=0.9.0"]
audio = ["librosa>=0.10.0", "soundfile>=0.12.0"]
awq = ["autoawq>=0.2.0"]
gptq = ["auto-gptq>=0.7.0"]
sglang = ["sglang>=0.2.0", "fastapi>=0.104.0", "uvicorn>=0.24.0"]
mlx = ["mlx>=0.20.0", "mlx-lm>=0.20.0"]
cce = ["cut-cross-entropy>=24.10.0"]
tui = ["textual>=0.50.0"]
# v0.53.8 #89 — bundle MLflow / SwanLab / Trackio for `--tracker` users.
trackers = ["mlflow>=2.0.0", "swanlab>=0.3.0", "trackio>=0.0.1"]
# v0.53.8 #85 — fsspec backends for remote dataset loading (s3 / gs / az / oci).
remote = ["fsspec>=2024.1.0", "s3fs>=2024.1.0", "gcsfs>=2024.1.0", "adlfs>=2024.1.0"]
# v0.53.10 #150 — bundle scikit-optimize so `soup data mix --optimize` runs the
# Bayesian-style loop instead of falling back to the v0.48.0 Dirichlet sampler.
mix = ["scikit-optimize>=0.9.0"]
# v0.53.10 #113 — production-grade data quality: langdetect (language) +
# presidio-analyzer (PII). Llama-Guard-3-1B is documented as a manual recipe
# (license + ~600 MB weight blob too large to bundle by default).
data-pro = ["langdetect>=1.0.9", "presidio-analyzer>=2.2.0"]

[project.scripts]
soup = "soup_cli.cli:run"

[project.urls]
Homepage = "https://github.com/MakazhanAlpamys/Soup"
Repository = "https://github.com/MakazhanAlpamys/Soup"
Issues = "https://github.com/MakazhanAlpamys/Soup/issues"

[tool.hatch.build.targets.wheel]
packages = ["soup_cli"]
# v0.53.8 #93 — include bundled fixture JSONLs as package data so
# `soup data demo` works in zipapp / namespace-package installs.
# Hatchling's ``packages = ["soup_cli"]`` already recurses into the
# package directory, so we use the artifacts directive (NOT
# force-include, which double-shipped the files in v0.53.8 and produced
# a "duplicate filename in local headers" 400 from PyPI upload).
artifacts = ["soup_cli/data/_fixtures/*.jsonl"]

[tool.ruff]
target-version = "py39"
line-length = 100

[tool.ruff.lint]
select = ["E", "F", "I", "N", "W"]

[tool.pytest.ini_options]
testpaths = ["tests"]
markers = ["smoke: slow smoke tests that download models and run training (run with: pytest -m smoke)"]
addopts = "-m 'not smoke' --cov=soup_cli --cov-fail-under=50 --cov-report=term-missing:skip-covered"