llmsql-benchmark/pyproject.toml at main · LLMSQL/llmsql-benchmark · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
[build-system]
requires = ["pdm-backend"]
build-backend = "pdm.backend"

[project]
name = "llmsql"
version = "0.1.16"
description = "A Text2SQL benchmark for evaluation of Large Language Models"
keywords = ["llm", "sql", "benchmark", "evaluation", "ai", "nlp"]
authors = [
    { name = "Dzmitry Pihulski", email = "dim.pigulsky@gmail.com" },
]
readme = "README.md"
requires-python = ">=3.10"
dependencies = [
    "accelerate>=0.26.0",
    "torch>=1.8",
    "transformers>=4.1",
    "datasets",
    "tqdm",
    "numpy",
    "python-dotenv",
    "pyyaml",
    "rich",
]
scripts = { llmsql = "llmsql.__main__:main" }
classifiers = [
       "Development Status :: 3 - Alpha",
       "Programming Language :: Python :: 3",
       "Programming Language :: Python :: 3.10",
       "Programming Language :: Python :: 3.11",
       "Programming Language :: Python :: 3.12",
       "License :: OSI Approved :: MIT License",
       "Operating System :: OS Independent",
       "Topic :: Scientific/Engineering :: Artificial Intelligence",
   ]
license-files = ["LICENSE"]


[project.urls]
Homepage = "https://llmsql.github.io/llmsql-benchmark/"
Repository = "https://github.com/LLMSQL/llmsql-benchmark"
Documentation = "https://llmsql.github.io/llmsql-benchmark/"
Issues = "https://github.com/LLMSQL/llmsql-benchmark/issues"


[project.optional-dependencies]
dev = [
    "pytest>=8.4.2",
    "pytest-cov>=7.0.0",
    "ruff>=0.13.1",
    "mypy>=1.18.2",
    "pre-commit>=4.3.0",
    "types-tqdm>=4.67.0.20250809",
    "types-PyYAML>=6.0.12.20250915",
    "pytest-asyncio>=1.2.0",
    "sphinx>=8.1.3",
    "sphinx-autodoc-typehints>=3.0.1",
    "furo>=2025.9.25",
    "sphinx-autoapi>=3.6.0",
    "sphinx-autobuild>=2024.10.3",
    "sphinx-copybutton>=0.5.2",
    "pytest-mock>=3.15.1",
    "ipykernel>=7.2.0",
    "ipywidgets>=8.1.8",
]
vllm = [
    "vllm>=0.4.2",
]

[tool.pdm]
distribution = true


[tool.ruff]
target-version = "py310"
line-length = 88

[tool.ruff.lint]
select = [
    "E",  # pycodestyle errors
    "W",  # pycodestyle warnings
    "F",  # pyflakes
    "I",  # isort
    "B",  # flake8-bugbear
    "C4", # flake8-comprehensions
    "UP", # pyupgrade
]
ignore = [
    "E501",  # line too long, handled by black
    "B008",  # do not perform function calls in argument defaults
    "C901",  # too complex
]

[tool.ruff.lint.per-file-ignores]
"__init__.py" = ["F401"]
"tests/**/*" = ["D", "ANN"]

[tool.ruff.lint.isort]
known-first-party = ["llmsql"]
force-sort-within-sections = true

# Type checking
[tool.mypy]
python_version = "3.10"
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
disallow_untyped_decorators = true
no_implicit_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
warn_no_return = true
warn_unreachable = true
strict_equality = true