data-tools/pyproject.toml at main · samvk12/data-tools · 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
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"

[project]
name = "intugle"
version = "1.2.0"
authors = [
    { name="Intugle", email="hello@intugle.ai" },
]
description = "A GenAI-powered Python library for building semantic layers."
readme = "README.md"
keywords = ["data", "semantic layer", "genai", "llm", "data profiling", "link prediction", "sql generation"]
requires-python = ">=3.10"
license = { text = "Apache-2.0" }
classifiers = [
    "Programming Language :: Python :: 3",
    "License :: OSI Approved :: Apache Software License",
    "Operating System :: OS Independent",
    "Development Status :: 3 - Alpha",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Software Development :: Libraries :: Python Modules"
]

dependencies = [
    "langchain-community>=0.3.21,<1.0.0",
    "langchain-openai>=0.3.28,<1.0.0",
    "langgraph>=0.6.9,<1.0.0",
    "nltk>=3.9.1",
    "numpy<=2.3.0",
    "asyncpg>=0.30.0",
    "fastapi[standard]>=0.116.1",
    "matplotlib>=3.10.5",
    "mcp[cli]>=1.12.4",
    "networkx>=3.4.2",
    "pandas>=2.2.2",
    "pyaml>=25.7.0",
    "pydantic>=2.11.7",
    "pydantic-settings>=2.10.1",
    "pyfunctional>=1.5.0",
    "python-dotenv>=1.1.1",
    "symspellpy>=6.9.0",
    "trieregex>=1.0.0",
    "xgboost>=3.0.4",
    "pyyaml>=6.0.2",
    "duckdb>=1.3.2",
    "scikit-learn==1.7.1",
    "langchain[anthropic,google-genai,openai]>=0.3.27,<1.0.0",
    "qdrant-client>=1.15.1",
    "rich>=14.1.0",
    "aiohttp>=3.9.5",
    "aiofiles>=23.2.1",
    "tavily-python>=0.1.11",
]

[project.optional-dependencies]
snowflake = [
    "snowflake-snowpark-python[pandas]>=1.12.0",
    "sqlglot>=27.20.0",
]
databricks = [
    "databricks-sql-connector>=4.1.3",
    "pyspark>=3.5.0,<4.0.0",
    "sqlglot>=27.20.0",
]
postgres = [
    "asyncpg>=0.30.0",
    "sqlglot>=27.20.0",
]
sqlserver = [
    "mssql-python>=0.13.1",
    "sqlglot>=27.20.0",
]

streamlit = [
    "streamlit==1.50.0",
    "pyngrok==7.4.0",
    "python-dotenv==1.1.1",
    "xlsxwriter==3.2.9",
    "plotly",
    "graphviz"
]


[project.urls]
"Homepage" = "https://github.com/Intugle/data-tools"
"Bug Tracker" = "https://github.com/Intugle/data-tools/issues"

[project.scripts]
intugle-mcp = "intugle.mcp.server:main"
intugle-streamlit = "intugle.cli:run_streamlit_app"

[dependency-groups]
test = [
    "langchain-core>=0.3.74",
    "langchain-mcp-adapters>=0.1.9",
    "pytest",
    "pytest-asyncio>=1.1.0",
    "pytest-mock",
    "sqlglot>=27.20.0",
]
lint = ["ruff"]
dev = [
    "asyncpg>=0.30.0",
    "databricks-sql-connector>=4.1.3",
    "ipykernel>=6.30.1",
    "langfuse==2.60.4",
    "mssql-python>=0.13.1",
    "pysonar>=1.2.0.2419",
    "pyspark>=3.5.0,<4.0.0",
    "pytest>=8.4.1",
    "pytest-asyncio>=1.1.0",
    "pytest-cov>=6.2.1",
    "pytest-mock>=3.15.1",
    "ruff>=0.13.2",
    "snowflake-snowpark-python[pandas]>=1.39.1",
    "sqlglot>=27.20.0",
    "twine>=6.1.0",
]

[tool.ruff]
src = ["src"]

[tool.setuptools.packages.find]
where = ["src"]

[tool.setuptools.package-data]
"intugle" = ["**/*.yaml", "**/*.txt", "**/*.pkl", "mcp/semantic_layer/prompts/*.md", "streamlit_app/**/*"]

[tool.pytest.ini_options]
markers = [
    "mcp: marks tests that require the MCP server to be running",
]

[tool.sonar]
projectKey = "Intugle-Data-Tools"
projectName = "Intugle Data Tools"
sources = "src"
python.version = "3.10"
python.coverage.reportPaths = "coverage.xml"