pyproject.toml

[tool.poetry]
name = "DataDreamer"
version = "0.46.0"
description = "Prompt. Generate Synthetic Data. Train & Align Models."
license = "MIT"
authors= [
    "Ajay Patel <me@ajayp.app>"
]
maintainers = [
    "Ajay Patel <me@ajayp.app>"
]
readme = "README.md"
homepage = "https://datadreamer.dev/"
repository = "https://github.com/datadreamer-dev/DataDreamer"
documentation = "https://datadreamer.dev/docs/"
keywords = ["python", "nlp", "machine learning", "natural language processing", "deep learning", "transformers", "pytorch", "openai", "alignment", "gpt", "nlp library", "synthetic data", "fine-tuning", "synthetic dataset generation", "llm", "llms", "llmops", "instruction-tuning"]
classifiers = [
    "Development Status :: 5 - Production/Stable",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: MIT License",
    "Operating System :: MacOS :: MacOS X",
    "Operating System :: POSIX :: Linux",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Topic :: Scientific/Engineering :: Artificial Intelligence"
]
packages = [
    {include = "datadreamer"}
]

[tool.poetry.dependencies]
python = ">=3.10,<3.14"

[tool.poetry.group.dev.dependencies]
poetry = "1.4.2"

[tool.ruff]
extend-exclude = ["docs"]

[tool.ruff.format]
skip-magic-trailing-comma = true

[tool.ruff.lint]
select = ["E4", "E7", "E9", "F", "B", "C90"]
ignore = ["E203", "E501"]
unfixable = ["B"]

[tool.ruff.lint.mccabe]
max-complexity = 12

[tool.ruff.lint.isort]
combine-as-imports = true

[tool.pytest.ini_options]
addopts = "-v --cov=src --cov-report term-missing --cov-report json"
filterwarnings = ["ignore::DeprecationWarning:jupyter_client.*:"]

[tool.mypy]
check_untyped_defs = true
warn_unused_ignores = true
mypy_path = "src/_stubs"

[[tool.mypy.overrides]]
module = "click,wandb,wandb.*,click.testing,flaky,tensorflow,torch_xla,jax,datasets.features.features,datasets.iterable_dataset,datasets.fingerprint,datasets.builder,datasets.arrow_writer,datasets.splits,datasets.utils,datasets.utils.version,pyarrow.lib,huggingface_hub,huggingface_hub.utils._headers,huggingface_hub.errors,dill,dill.source,transformers,bitsandbytes,sqlitedict,optimum.bettertransformer,optimum.bettertransformer.models,optimum.utils,transformers.utils.quantization_config,sortedcontainers,peft,psutil,ring,ctransformers,petals,petals.client.inference_session,hivemind.p2p.p2p_daemon_bindings.utils,huggingface_hub.utils,tqdm,ctransformers.transformers,vllm,litellm,litellm.llms.palm,litellm.exceptions,sentence_transformers,faiss,huggingface_hub.utils._validators,evaluate,transformers.trainer_callback,transformers.training_args,trl,guidance,sentence_transformers.models.Transformer,trl.trainer.utils,transformers.trainer_utils,setfit,joblib,setfit.modeling,transformers.utils.notebook,mistralai.models,mistralai.models.chat_completion,accelerate.utils,accelerate.utils.constants,accelerate,transformers.trainer,sentence_transformers.util,Pyro5,Pyro5.server,Pyro5.api,Pyro5,datadreamer,huggingface_hub.repocard,transformers.trainer_pt_utils,traitlets.utils.warnings,orjson,Pyro5.errors,sympy,tqdm.auto,requests.exceptions"
ignore_missing_imports = true

[tool.pyright]
exclude = [".*/"]

[tool.coverage.run]
omit = ["src/__main__.py", "src/project/*", "src/tests/*", "src/utils/hf_structured_decoding_utils.py"]

[tool.coverage.report]
exclude_lines = [
  "@abc.abstractmethod",
  "@abstractmethod",
  "pragma: no cover",
]   

[tool.docs.sh]
docs_author = "Ajay Patel"
docs_author_website = "https://ajayp.app"
autodoc_exclude_paths = "./datadreamer.py ./datasets/[!_]*.py ./steps/[!_]*.py ./errors/[!_]*.py ./llms/[!_]*.py ./embedders/[!_]*.py ./retrievers/[!_]*.py ./task_models/[!_]*.py ./trainers/[!_]*.py ./project/* ./logging/* ./pickling/* ./utils/* ./tests/*" # Space-separated, fnmatch-style