-
Notifications
You must be signed in to change notification settings - Fork 7
Expand file tree
/
Copy pathpyproject.toml
More file actions
205 lines (175 loc) · 5.31 KB
/
pyproject.toml
File metadata and controls
205 lines (175 loc) · 5.31 KB
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
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
[build-system]
requires = ["setuptools>=70.0.0", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "arbiter-ai"
version = "0.2.0"
description = "Native PydanticAI evaluation with automatic cost tracking"
authors = [{name = "Evan Volgas", email = "evan.volgas@gmail.com"}]
license = "MIT"
readme = "README.md"
requires-python = ">=3.11,<3.15"
keywords = ["ai", "llm", "evaluation", "testing", "metrics", "pydantic-ai", "cost-tracking"]
classifiers = [
"Development Status :: 4 - Beta",
"Intended Audience :: Developers",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: 3.13",
"Programming Language :: Python :: 3.14",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Software Development :: Testing",
"Typing :: Typed",
]
# Core dependencies - minimal for basic functionality
dependencies = [
"pydantic>=2.12.0",
"pydantic-ai>=1.14.0", # Latest PydanticAI with current API
"httpx>=0.28.0",
"openai>=2.0.0", # Latest OpenAI SDK
"python-dotenv>=1.0.1",
"aiofiles>=25.0.0",
"logfire>=4.0.0",
"numpy>=2.0.0", # For vector operations
"typing-extensions>=4.0.0",
"litellm>=1.50.0", # Bundled pricing database - consistent with Conduit
]
[project.scripts]
arbiter = "arbiter_ai.cli:main"
[project.urls]
Homepage = "https://github.com/ashita-ai/arbiter"
Documentation = "https://github.com/ashita-ai/arbiter#readme"
Repository = "https://github.com/ashita-ai/arbiter"
Issues = "https://github.com/ashita-ai/arbiter/issues"
Changelog = "https://github.com/ashita-ai/arbiter/releases"
[project.optional-dependencies]
# Model providers
anthropic = ["anthropic>=0.72.0"]
gemini = ["google-generativeai>=0.8.5"]
mistral = ["mistralai>=1.0.0"]
cohere = ["cohere>=5.0.0"]
# Scale features - optional fast backends
scale = [
"faiss-cpu>=1.7.4", # Fast in-memory vector similarity (CPU-only, no GPU required)
"sentence-transformers>=2.2.0", # Local embeddings (free, offline, deterministic)
"pymilvus>=2.6.0", # Optional Milvus for v2.0+ (enterprise scale)
]
# Storage backends
postgres = ["asyncpg>=0.29.0", "alembic>=1.13.0", "sqlalchemy>=2.0.0", "psycopg2-binary>=2.9.0"]
redis = ["redis>=5.0.0"]
storage = ["arbiter-ai[postgres,redis]"] # All storage backends
# Fact verification plugins
verifiers = ["tavily-python>=0.5.0"] # SearchVerifier for web search verification
# Command-line interface
cli = ["typer>=0.15.0", "rich>=14.0.0"]
# Development tools
dev = [
# Testing
"pytest>=9.0.0",
"pytest-cov>=7.0.0",
"pytest-asyncio>=1.0.0",
"pytest-mock>=3.15.0",
"pytest-xdist>=3.8.0", # Parallel test execution
# Code quality
"black>=25.0.0",
"mypy>=1.18.0",
"ruff>=0.14.0",
"types-redis>=4.6.0",
"types-aiofiles>=25.0.0",
# Interactive development
"rich>=14.0.0",
# Documentation
"mkdocs>=1.6.0",
"mkdocs-material>=9.7.0",
"mkdocstrings[python]>=0.30.0",
# Development utilities
"pre-commit>=4.0.0",
"watchdog>=6.0.0",
"psutil>=7.0.0",
"setuptools>=80.0.0",
# Publishing
"build>=1.0.0",
"twine>=6.0.0",
]
# All features
all = ["arbiter-ai[anthropic,gemini,mistral,cohere,scale,storage,verifiers,cli,dev]"]
[tool.setuptools.packages.find]
where = ["."]
include = ["arbiter_ai*"]
[tool.setuptools.package-data]
arbiter_ai = ["py.typed"]
[tool.black]
line-length = 88
target-version = ['py311', 'py312', 'py313', 'py314']
[tool.ruff]
line-length = 88
target-version = "py311"
[tool.ruff.lint]
select = [
"E", # pycodestyle errors
"W", # pycodestyle warnings
"F", # pyflakes
"I", # isort
]
ignore = [
"E501", # line too long (handled by formatter)
]
fixable = ["ALL"]
unfixable = []
[tool.ruff.lint.isort]
known-first-party = ["arbiter_ai"]
combine-as-imports = true
[tool.ruff.format]
quote-style = "double"
indent-style = "space"
skip-magic-trailing-comma = false
line-ending = "auto"
[tool.pytest.ini_options]
minversion = "8.0"
addopts = ["--strict-markers", "--cov=arbiter_ai", "--cov-report=term-missing"]
testpaths = ["tests"]
asyncio_mode = "auto"
markers = [
"slow: marks tests as slow",
"integration: marks tests as integration tests",
"performance: marks tests as performance tests"
]
[tool.coverage.run]
omit = [
"arbiter_ai/storage/__init__.py",
"arbiter_ai/tools/__init__.py",
]
[tool.mypy]
python_version = "3.11"
strict = true
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
check_untyped_defs = true
no_implicit_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
show_error_codes = true
pretty = true
disallow_any_generics = true
disallow_subclassing_any = true
disallow_untyped_calls = true
disallow_incomplete_defs = true
disallow_untyped_decorators = true
no_implicit_reexport = true
strict_optional = true
strict_equality = true
warn_no_return = true
warn_unreachable = true
[[tool.mypy.overrides]]
module = "tests.*"
disallow_untyped_defs = false
[[tool.mypy.overrides]]
module = ["pymilvus", "pymilvus.*", "logfire", "faiss", "sentence_transformers", "sentence_transformers.*", "asyncpg", "asyncpg.*", "typer", "typer.*", "rich", "rich.*"]
ignore_missing_imports = true
[dependency-groups]
dev = [
"pytest>=9.0.1",
"pytest-cov>=7.0.0",
]