memorylayer/memorylayer-embed-server/pyproject.toml at main · scitrera/memorylayer · 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
[project]
name = "memorylayer-embed-server"
version = "0.1.23"
description = "MemoryLayer.ai Embed Server - Stateless transcription and embedding GPU server"
readme = "README.md"
requires-python = ">=3.12"
license = { text = "Apache 2.0" }
authors = [
    { name = "scitrera.ai", email = "open-source-team@scitrera.com" }
]
keywords = ["ai", "memory", "embedding", "transcription", "gpu", "glm-ocr", "vllm", "colpali"]
classifiers = [
    "Development Status :: 3 - Alpha",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.12",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
]

dependencies = [
    "memorylayer-server==0.1.22",
    "fastapi==0.136.1",
    "uvicorn[standard]==0.46.0",
    "pydantic==2.13.4",
    "click==8.3.3",
    "numpy>2.0.0",
    "Pillow>=10.0.0",
]

[project.optional-dependencies]
ocr = ["transformers>=5.5.0", "torch>=2.11.0,<2.12.0", "accelerate>=0.26.0", "addict", 'matplotlib']
vllm = ["vllm>=0.19.0", "instanttensor"]
colpali = ["colpali-engine>=0.3.0", "torch>=2.11.0,<2.12.0"]
google = ["google-genai>=2.3.0"]
# Observability: Prometheus /metrics endpoint + OpenTelemetry SDK / OTLP
# exporter. The Prometheus exposition is the simplest OTel-compatible
# integration point — an OTel collector can scrape /metrics and forward
# anywhere; auto-instrumentation for FastAPI / httpx provides traces.
observability = [
    "prometheus-client>=0.20.0",
    "opentelemetry-sdk>=1.27.0",
    "opentelemetry-exporter-otlp-proto-grpc>=1.27.0",
    "opentelemetry-instrumentation-fastapi>=0.48b0",
    "opentelemetry-instrumentation-httpx>=0.48b0",
]
gpu = ["memorylayer-embed-server[ocr,vllm,colpali]"]
all = ["memorylayer-embed-server[gpu,google,observability]"]
# Visual-tokenizer (Qwen3.5) lives in the proprietary
# memorylayer-embed-server-enterprise package; install that separately.
dev = [
    "pytest>=9.0.2",
    "pytest-asyncio>=1.3.0",
    "pytest-cov>=7.0.0",
    "ruff>=0.15.0",
]

[project.scripts]
memorylayer-embed = "memorylayer_embed_server.cli:cli"

[project.urls]
Homepage = "https://memorylayer.ai"
Documentation = "https://docs.memorylayer.ai"

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

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

[tool.hatch.build.targets.sdist]
include = ["src/memorylayer_embed_server"]

[tool.ruff]
line-length = 140
target-version = "py312"

[tool.ruff.lint]
select = ["E", "F", "I", "N", "W", "UP"]

[tool.pytest.ini_options]
asyncio_mode = "auto"
testpaths = ["tests"]
# Default selection excludes slow + integration; opt-in with `-m slow` or
# `-m integration` to run real-model and docker chain tests.
addopts = "-m 'not slow and not integration'"
markers = [
    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
    "integration: marks tests as integration tests (deselect with '-m \"not integration\"')",
]

[tool.mypy]
python_version = "3.12"
strict = false
warn_return_any = true
warn_unused_configs = true