docs2db/pyproject.toml at main · rhel-lightspeed/docs2db · 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
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
[project]
name = "docs2db"
version = "0.4.4"
description = "Repository of docling documents for RAG"
readme = "README.md"
authors = [{ name = "Ellis Low", email = "elow@redhat.com" }]
license = { text = "Apache-2.0" }
requires-python = ">=3.12,<3.13"
keywords = [
    "rag",
    "document-processing",
    "embeddings",
    "docling",
    "contextual-retrieval",
    "semantic-search",
    "vector-database",
    "pgvector",
    "postgresql",
    "llm",
]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.12",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Topic :: Text Processing :: General",
]
dependencies = [
    "cachetools>=7.1.4",
    "docling>=2.95.0",
    "httpx>=0.28.1",
    "pgvector>=0.4.2",
    "psycopg[binary]>=3.3.4",
    "psycopg-pool>=3.3.1",
    "pydantic-settings>=2.14.1",
    "pyyaml>=6.0.3",
    "rich>=15.0.0",
    "structlog>=25.5.0",
    "torch>=2.7.1",
    "torchvision>=0.23.0",
    "tqdm>=4.67.3",
    "typer>=0.21.2",
    "xxhash>=3.7.0",
]

[project.optional-dependencies]
watsonx = [
    "ibm-watsonx-ai>=1.5.12",
]

[project.scripts]
docs2db = "docs2db.docs2db:app"

[project.urls]
Homepage = "https://github.com/rhel-lightspeed/docs2db"
Documentation = "https://github.com/rhel-lightspeed/docs2db#readme"
Repository = "https://github.com/rhel-lightspeed/docs2db"
Issues = "https://github.com/rhel-lightspeed/docs2db/issues"
Changelog = "https://github.com/rhel-lightspeed/docs2db/blob/main/CHANGELOG.md"

[build-system]
requires = ["uv_build>=0.11.16,<0.11.17"]
build-backend = "uv_build"

[tool.uv.sources]
torch = { index = "pytorch-cpu" }
torchvision = { index = "pytorch-cpu" }

[[tool.uv.index]]
name = "pytorch-cpu"
url = "https://download.pytorch.org/whl/cpu"
explicit = true

[dependency-groups]
dev = [
    "datamodel-code-generator>=0.57.0",
    "ipython>=9.13.0",
    "pre-commit>=4.6.0",
    "pyright>=1.1.409",
    "pytest>=9.0.3",
    "pytest-cov>=7.1.0",
    "pytest-httpx>=0.36.2",
    "pytest-randomly>=4.1.0",
    "pytest-sugar>=1.1.1",
    "python-gitlab>=8.3.0",
    "ruff>=0.15.14",
    "tox>=4.54.0",
    "types-cachetools>=7.0.0.20260518",
    "types-tqdm>=4.67.3.20260518",
]

[tool.pytest.ini_options]
addopts = [
    "--cov=docs2db",
    "--cov-report=term-missing",
    "--cov-report=html",
    "--cov-report=xml",
    "--cov-branch",
    "--color=yes",
]
# Having problems with tests? Uncomment the following line to see more output.
# log_cli = false
# log_level = "DEBUG"
log_format = "%(asctime)s %(levelname)s %(message)s"
log_date_format = "%Y-%m-%d %H:%M:%S"
testpaths = ["tests"]
markers = [
    "no_ci: marks tests that should not run in CI (require external services, podman, etc.)"
]

[tool.pyright]
venvPath = "."
venv = ".venv"

[tool.ruff]
line-length = 120

[tool.ruff.lint]
select = [
    "E",      # pycodestyle errors
    "F",      # pyflakes
    "W",      # pycodestyle warnings
    "I",      # isort
    "UP",     # pyupgrade
    "S",      # bandit (security)
    "B",      # flake8-bugbear
    "A",      # flake8-builtins
    "C4",     # flake8-comprehensions
    "SIM",    # flake8-simplify
    "TID252", # flake8-tidy-imports (relative imports)
    "RUF100", # flag unnecessary noqa comments
]
ignore = [
    "B9",     # flake8-bugbear opinionated rules (B901-B911)
]

[tool.ruff.lint.per-file-ignores]
"tests/**" = ["S101", "S104"]

[tool.ruff.lint.isort]
case-sensitive = false
force-single-line = true
lines-after-imports = 2
lines-between-types = 1
order-by-type = false