Contextifier/pyproject.toml at main · CocoRoF/Contextifier · 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
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "contextifier"
version = "0.2.6"
description = "Convert raw documents into AI-understandable context with intelligent text extraction, table detection, and semantic chunking"
readme = "README.md"
requires-python = ">=3.12"
license = {text = "Apache-2.0"}
authors = [
    {name = "CocoRoF", email = "gkfua00@gmail.com"},
]
maintainers = [
    {name = "CocoRoF", email = "gkfua00@gmail.com"},
]
keywords = [
    "document-processing",
    "pdf",
    "ocr",
    "text-extraction",
    "chunking",
    "ai",
    "llm",
    "langchain",
    "hwp",
    "docx",
    "xlsx",
]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Programming Language :: Python :: 3.14",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Topic :: Text Processing",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
]
dependencies = [
    # Core
    "beautifulsoup4>=4.12.0",
    "chardet>=5.0.0",
    "langchain-text-splitters>=1.0.0",
    # PDF
    "pdfplumber>=0.11.0",
    "pdfminer.six>=20231228",
    "pdf2image>=1.17.0",
    # Office — DOCX / PPTX / Excel
    "python-docx>=1.1.0",
    "docx2pdf>=0.1.8",
    "python-pptx>=1.0.0",
    "openpyxl>=3.1.0",
    "xlrd>=2.0.0",
    # HWP
    "pyhwp>=0.1b15",
    "olefile>=0.47",
    # RTF
    "striprtf>=0.0.29",
    # Image & OCR
    "pi-heif>=1.0.0",
    "pytesseract>=0.3.10",
]

[project.optional-dependencies]
# PDF — PyMuPDF is AGPL-3.0; install explicitly to acknowledge license terms
pdf = ["pymupdf>=1.24.0"]
# These are ecosystem integrations, not core functionality
langchain = [
    "langchain>=1.0.0",
    "langchain-aws>=1.0.0",
    "langchain-community>=0.4.0",
    "langchain-core>=1.0.0",
    "langchain-openai>=1.0.0",
    "langchain-anthropic>=1.0.0",
    "langchain-google-genai>=4.0.0",
    "langgraph>=1.0.0",
    "langsmith>=0.6.0",
]
server = [
    "pydantic>=2.12.0",
    "pydantic-settings>=2.12.0",
    "python-dotenv>=1.0.0",
    "python-multipart>=0.0.20",
    "orjson>=3.10.0",
    "psutil>=7.0.0",
]
all = [
    "contextifier[pdf,langchain,server]",
    "pandas>=2.2.0",
    "cachetools>=5.3.0",
]

[project.urls]
Homepage = "https://github.com/CocoRoF/Contextifier"
Documentation = "https://github.com/CocoRoF/Contextifier#readme"
Repository = "https://github.com/CocoRoF/Contextifier.git"
Issues = "https://github.com/CocoRoF/Contextifier/issues"
Changelog = "https://github.com/CocoRoF/Contextifier/releases"

[tool.hatch.build.targets.wheel]
packages = ["contextifier"]

[tool.hatch.build.targets.sdist]
include = [
    "contextifier/",
    "README.md",
    "LICENSE",
    "pyproject.toml",
]
exclude = [
    "/.git",
    "/.venv",
    "/__pycache__",
    "*.pyc",
    "test/",
    "temp/",
    "libs/",
]