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

[project]
name = "eva"
version = "0.1.1"
description = "A New End-to-end Framework for Evaluating Voice Agents (EVA)"
authors = [
    { name = "Tara Bogavelli" },
    { name = "Gabrielle Gauthier Melançon" },
    { name = "Katrina Stankiewicz" },
    { name = "Oluwanifemi Bamgbose" },
    { name = "Hoang Nguyen" },
    { name = "Raghav Mehndiratta" },
    { name = "Hari Subramani" },
]
readme = "README.md"
requires-python = ">=3.11,<3.14"
license = "MIT"
dependencies = [
    "pydantic>=2.0",
    "pydantic-settings>=2.0",
    "pipecat-ai>=0.0.108",
    "elevenlabs>=1.0.0",
    "openai>=1.0.0",
    "anthropic>=0.83.0",
    "litellm>=1.30.0",
    "deepgram-sdk>=6.1.1,<7",
    "onnxruntime>=1.16.0",
    "aioboto3>=12.0.0",
    "google-genai>=1.69.0",
    "google-cloud-speech>=2.0.0",
    "google-cloud-texttospeech>=2.0.0",
    "azure-cognitiveservices-speech>=1.31.0",
    "cartesia>=1.0.0",
    "assemblyai>=0.17.0",
    "setuptools>=65.0.0",
    "fastapi>=0.100.0",
    "uvicorn>=0.23.0",
    "websockets>=12.0",
    "httpx>=0.25.0",
    "pyyaml>=6.0",
    "pandas>=2.0",
    "numpy>=1.24",
    "pydub>=0.25.0",
    "aiofiles>=23.0",
    "structlog>=23.0",
    "tqdm>=4.65",
    "python-dotenv>=1.0.0",
    "jiwer>=3.0.0",
    "inflect>=7.0.0",
    "jaconv>=0.3.0",
    "regex>=2023.0.0",
    "more-itertools>=10.0.0",
]

[project.optional-dependencies]
dev = [
    "pytest>=7.0",
    "pytest-asyncio>=0.21",
    "pytest-cov>=4.0",
    "ruff>=0.1.0",
    "mypy>=1.5",
    "pre-commit>=4.0",
]
apps = [
    "pandas>=2.0",
    "plotly>=5.0",
    "streamlit>=1.56.0",
    "streamlit-diff-viewer>=0.0.2",
]


[project.scripts]
eva = "eva.cli:main"

[tool.hatch.build.targets.wheel]
packages = ["src/eva"]

[tool.pytest.ini_options]
addopts = "--import-mode=importlib"
asyncio_mode = "auto"
testpaths = ["tests"]
python_files = ["test_*.py"]
python_functions = ["test_*"]

[tool.ruff]
line-length = 120
target-version = "py311"

[tool.ruff.lint]
# https://docs.astral.sh/ruff/rules/
# https://docs.astral.sh/ruff/formatter/#conflicting-lint-rules
select = ["A", "B0", "C4", "D2", "D4", "E", "F", "FURB", "I", "PYI", "UP"]
ignore = ["D203", "D206", "D213", "D400", "D401", "D413", "D415", "E1", "E501"]

[tool.eva]
# Bump when simulation pipeline changes (agent, user_simulator, orchestrator,
# simulation prompts, agent configs, tool mocks). Old outputs become stale.
simulation_version = "0.1.0"
# Bump when metrics pipeline changes (metrics code, judge prompts, pricing,
# postprocessor). Old metric results become stale — cheap to recompute.
metrics_version = "0.1.1"

[tool.mypy]
python_version = "3.11"
strict = true