structx/pyproject.toml at master · Blacksuan19/structx · 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
[build-system]
requires = ["setuptools>=45", "wheel", "pip>=21.0"]
build-backend = "setuptools.build_meta"

[project]
name = "structx"
version = "0.6.5"
description = "Structured data extraction from text using LLMs and dynamic model generation"
authors = [{ name = "blacksuan19", email = "py@aolabs.dev" }]
license-files = ["LICENSE"]
readme = "README.md"
requires-python = ">=3.10"
classifiers = [
    "Development Status :: 5 - Production/Stable",
    "Framework :: AsyncIO",
    "Framework :: Pydantic",
    "Intended Audience :: Developers",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3",
    "Topic :: Database",
    "Topic :: Documentation",
    "Topic :: Internet :: WWW/HTTP :: Dynamic Content",
    "Topic :: Office/Business",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Scientific/Engineering :: Information Analysis",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Topic :: Software Development :: Libraries",
    "Topic :: Text Processing :: Linguistic",
    "Topic :: Text Processing :: Markup",
    "Topic :: Text Processing",
    "Topic :: Utilities",
    "Typing :: Typed",
]

dependencies = [
    "instructor>=1.15.4",
    "litellm>=1.91.1",
    "loguru>=0.7.3",
    "openpyxl>=3.1.5",
    "pandas>=2.2.3",
    "pydantic>=2.11.7",
    "pydantic-settings[yaml]>=2.14.2",
    "tabulate>=0.9.0", # required for pandas .to_markdown()
    "tenacity>=9.1.2",
    "tqdm>=4.68.4",
]

[project.optional-dependencies]
dev = [
    "black>=25.1.0",
    "bumpver>=2024.1130",
    "pip-tools>=7.4.1",
    "pytest>=9.1.1",
    "wheel>=0.45.1",
]

# Optional document processing support. Kept out of the base install because
# Docling's local model pipeline requires PyTorch.
# The format-pdf extra is still needed because DocumentConverter imports its
# PDF backend dependencies even when existing PDFs are passed through directly.
docs = [
    "docling-slim[convert-core,format-docx,format-html,format-latex,format-markdown,format-opendocument,format-pdf,format-pptx,format-web,models-local]>=2.111.0",
    "torch>=2.13.0",
    "torchvision>=0.28.0",
    "weasyprint>=69.0",
]

# Optional standalone document measurement (structx.measurement). Independent
# of extraction: it estimates page and text counts for callers that need a
# size estimate before running an extraction.
measurement = [
    "pypdfium2>=5.12.1",
]

# Local OCR for measuring pages that have no embedded text layer.
measurement-ocr = [
    "pypdfium2>=5.12.1",
    "rapidocr>=3.9.0",
    "onnxruntime>=1.22.0",
]

# Documentation site tooling.
mkdocs = [
    "mkdocs>=1.6.1",
    "mkdocs-material>=9.7.6",
    "mkdocstrings[python]>=0.29.1",
    "mkdocs-git-revision-date-localized-plugin>=1.4.5",
    "mkdocs-material[imaging]>=9.7.6",
    "mkdocs-mermaid2-plugin>=1.2.3",
]

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

[tool.uv.sources]
torch = [
    { index = "pytorch-cpu", marker = "sys_platform == 'linux'" },
]
torchvision = [
    { index = "pytorch-cpu", marker = "sys_platform == 'linux'" },
]

[tool.bumpver]
current_version = "0.6.5"
version_pattern = "MAJOR.MINOR.PATCH"
commit_message = "chore(release): bump version {old_version} -> {new_version}"
commit = true
tag = true
push = true


[tool.bumpver.file_patterns]
"pyproject.toml" = ['current_version = "{version}"', 'version = "{version}"']
"structx/__init__.py" = ['__version__ = "{version}"']
"README.md" = ["PyPi-{version}"]

[tool.setuptools.packages.find]
# Only package the library code under structx; exclude MkDocs overrides and others
include = ["structx*"]

[tool.pytest.ini_options]
filterwarnings = [
    "ignore:There is no current event loop:DeprecationWarning:litellm\\._service_logger",
    "ignore:This field is deprecated.*:DeprecationWarning:docling\\.pipeline\\.standard_pdf_pipeline",
    "ignore:torch\\.ao\\.quantization is deprecated.*:DeprecationWarning:torch\\.ao\\.quantization\\.quantize",
    "ignore:torch\\.quantize_per_tensor.*:UserWarning:torch\\.ao\\.nn\\.quantized\\.dynamic\\.modules\\.rnn",
]
pythonpath = ["."]
testpaths = ["tests"]