plexe/pyproject.toml at main · plexe-ai/plexe · 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
[tool.poetry]
name = "plexe"
version = "1.4.4"
description = "An agentic framework for building ML models from natural language"
authors = [
    "Marcello De Bernardi <mdebernardi@plexe.ai>",
    "Vaibhav Dubey <vdubey@plexe.ai>"
]
license = "Apache-2.0"
readme = "README.md"
repository = "https://github.com/plexe-ai/plexe"
homepage = "https://github.com/plexe-ai/plexe"
packages = [{ include = "plexe" }]
classifiers = [
    "Development Status :: 3 - Alpha",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "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"
]
keywords = ["agent", "custom ai", "llm", "machine learning", "data generation"]

[tool.poetry.scripts]
plexe = "plexe.main:main"

[tool.poetry.dependencies]
python = ">=3.10,<3.13"

# Python version-specific numpy (numpy 2.x requires Python 3.11+)
numpy = [
    { version = ">=1.26.0,<2.0.0", python = "~3.10" },
    { version = ">=2.3.4,<2.4.0", python = ">=3.11" }
]

# Core ML libraries - tensorflow 2.20.0 supports Python 3.10+ (no version split needed!)
tensorflow = ">=2.20.0,<2.21.0"
keras = ">=3.12.0,<3.13.0"

# Data processing
pandas = ">=2.3.3,<2.4.0"
xgboost = ">=3.1.1,<3.2.0"
pyarrow = ">=22.0.0,<23.0.0"
datasets = ">=4.4.1,<5.0.0"
scikit-learn = ">=1.7.2,<1.8.0"

# AI/LLM frameworks
smolagents = ">=1.22.0,<2.0.0"
litellm = ">=1.79.3,<2.0.0"
langchain = "0.3.27"

# Observability (compatible with protobuf 5.28+)
openinference-instrumentation-smolagents = ">=0.1.19,<0.2.0"
opentelemetry-sdk = ">=1.30.0,<2.0.0"
opentelemetry-exporter-otlp-proto-http = ">=1.30.0,<2.0.0"

# Utilities
joblib = ">=1.5.2,<2.0.0"
cloudpickle = ">=3.1.2,<3.2.0"
dataclasses-json = ">=0.6.7,<0.7.0"
pyyaml = ">=6.0.0,<7.0.0"
pydantic = ">=2.7.4,<3.0.0"
pydantic-settings = ">=2.0.0,<3.0.0"

# Optional dependencies
pyspark = { version = ">=4.0.1,<4.1.0", optional = true }
databricks-connect = { version = ">=17.3.1,<18.0.0", python = "3.12", optional = true }
boto3 = { version = ">=1.35.0,<2.0.0", optional = true }
torch = { version = ">=2.7.1,<2.8.0", optional = true }
catboost = { version = ">=1.2.0,<1.3.0", optional = true }
lightgbm = { version = ">=4.6.0,<4.7.0", optional = true }

[tool.poetry.extras]
pyspark = ["pyspark"]
databricks = ["databricks-connect"]
aws = ["boto3"]
pytorch = ["torch"]
catboost = ["catboost"]
lightgbm = ["lightgbm"]
tabular = ["catboost", "lightgbm"]
vision = ["torch"]

[tool.poetry.group.dev.dependencies]
pytest = "^8.3.4"
pytest-xdist = "^3.8.0"
pre-commit = "^4.0.1"
ruff = "^0.14.9"
black = ">=23.0.0"
streamlit = ">=1.52.1,<2.0.0"
plotly = ">=6.5.0,<7.0.0"
boto3 = "^1.42.44"

[tool.pytest.ini_options]
markers = [
    "integration_seed: stage 1 integration tests that build reusable checkpoints through phase 3",
    "integration_search: stage 2 integration tests that resume from seeds and pause after phase 4",
    "integration_eval: stage 3 integration tests that resume from search checkpoints and run evaluation + packaging",
]

[tool.semantic_release]
version_variables = ["pyproject.toml:version"]
commit_parser = "angular"
build_command = "poetry build"

[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"

[tool.black]
line-length = 120
target-version = ["py312"]
exclude = '''
/(
    \.git
  | \.venv
  | __pycache__
  | build
  | dist
)/
'''

[tool.ruff]
line-length = 120
target-version = "py312"

[tool.ruff.lint]
# Note: we enforce docstrings because scripts/generate_code_index.py relies on them to produce good documentation
extend-select = [
    "D100", # Missing docstring in public module
    "D101", # Missing docstring in public class
#    "D102", # Missing docstring in public method  TODO: enable gradually
#    "D103", # Missing docstring in public function  TODO: enable gradually
]
ignore = [
    "E203", # Whitespace before ':'
    "E501", # Line length
    "E402", # Imports not at top of file
]