binary_semantic_cache/pyproject.toml at main · matte1782/binary_semantic_cache · 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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
[build-system]
requires = ["maturin>=1.4,<2.0"]
build-backend = "maturin"

[project]
name = "binary-semantic-cache"
version = "1.0.1"
description = "High-performance semantic caching for LLM APIs using binary embeddings"
readme = "README.md"
license = "MIT"
requires-python = ">=3.10"
authors = [
    { name = "Matteo Panzeri", email = "matteo1782@gmail.com" }
]
maintainers = [
    { name = "Matteo Panzeri", email = "matteo1782@gmail.com" }
]
keywords = [
    "llm",
    "cache",
    "semantic",
    "binary",
    "embeddings",
    "openai",
    "api",
]
classifiers = [
    "Development Status :: 5 - Production/Stable",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: MIT License",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Rust",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Typing :: Typed",
]

dependencies = [
    "numpy>=1.24",
    "numba>=0.58",
    "pydantic>=2.0",
    "pydantic-settings>=2.0",
]

[project.optional-dependencies]
proxy = [
    "fastapi>=0.100",
    "uvicorn>=0.23",
    "httpx>=0.25",
]
openai = [
    "openai>=1.0",
    "tiktoken>=0.5",
    "tenacity>=8.0",
]
local = [
    "sentence-transformers>=2.2",
]
dev = [
    "pytest>=7.0",
    "pytest-asyncio>=0.21",
    "pytest-cov>=4.0",
    "mypy>=1.5",
    "ruff>=0.1",
    "black>=23.0",
    "maturin>=1.4",
]
all = [
    "binary-semantic-cache[proxy,openai,local,dev]",
]

[project.urls]
Homepage = "https://github.com/matte1782/binary_semantic_cache"
Documentation = "https://github.com/matte1782/binary_semantic_cache#readme"
Repository = "https://github.com/matte1782/binary_semantic_cache.git"

[project.scripts]
bsc-server = "binary_semantic_cache.proxy.server:main"

# Maturin configuration for mixed Rust/Python builds
[tool.maturin]
# Path to the Rust extension source
manifest-path = "src/binary_semantic_cache_rs/Cargo.toml"
# Python source directory
python-source = "src"
# Module name for the Rust extension
module-name = "binary_semantic_cache.binary_semantic_cache_rs"
# Build features
features = ["pyo3/extension-module"]
# Include license file in the source distribution
include = ["LICENSE"]
# Strip debug symbols in release builds
strip = true

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = ["test_*.py"]
python_functions = ["test_*"]
addopts = "-v --tb=short"
asyncio_mode = "auto"
filterwarnings = [
    # Suppress expected deprecation warnings from our own code (v0.2.0 deprecated methods)
    "ignore:save\\(\\) is deprecated:DeprecationWarning",
    "ignore:load\\(\\) is deprecated:DeprecationWarning",
]
markers = [
    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
    "resource_intensive: marks tests as resource intensive",
    "external: marks tests that require external services (e.g., OpenAI API)",
]

[tool.mypy]
python_version = "3.10"
strict = true
warn_return_any = true
warn_unused_ignores = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
no_implicit_optional = true
warn_redundant_casts = true

[[tool.mypy.overrides]]
module = [
    "numba",
    "numba.*",
    "sentence_transformers",
    "sentence_transformers.*",
]
ignore_missing_imports = true

[tool.ruff]
target-version = "py310"
line-length = 88
select = [
    "E",   # pycodestyle errors
    "W",   # pycodestyle warnings
    "F",   # pyflakes
    "I",   # isort
    "B",   # flake8-bugbear
    "C4",  # flake8-comprehensions
    "UP",  # pyupgrade
]
ignore = [
    "E501",  # line too long (handled by black)
    "B008",  # do not perform function calls in argument defaults
    "C901",  # too complex
]

[tool.ruff.isort]
known-first-party = ["binary_semantic_cache"]

[tool.black]
target-version = ["py310"]
line-length = 88

[tool.coverage.run]
source = ["src/binary_semantic_cache"]
branch = true

[tool.coverage.report]
exclude_lines = [
    "pragma: no cover",
    "def __repr__",
    "raise NotImplementedError",
    "if TYPE_CHECKING:",
]