simba/pyproject.toml at main · GitHamza0206/simba · 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
[project]
name = "simba-core"
version = "0.5.0"
description = "Customer Service Assistant - AI-powered support that answers fast and accurately"
authors = [{name = "GitHamza0206", email = "zeroualihamza0206@gmail.com"}]
readme = "README.md"
license = {text = "Apache-2.0"}
requires-python = ">=3.11,<3.13"
keywords = ["customer-service", "ai", "langchain", "rag", "chatbot"]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
]

dependencies = [
    # Web framework
    "fastapi>=0.115.0",
    "uvicorn[standard]>=0.34.0",
    "python-multipart>=0.0.20",
    # LangChain ecosystem (latest)
    "langchain>=0.3.14",
    "langchain-core>=0.3.29",
    "langchain-community>=0.3.14",
    "langchain-openai>=0.3.0",
    "langgraph>=0.2.60",
    "langgraph-checkpoint-postgres>=2.0.0",
    "psycopg[binary,pool]>=3.2.0", # Required for async postgres checkpointer
    # Database
    "sqlalchemy>=2.0.40",
    "psycopg2-binary>=2.9.10",
    # Vector store & embeddings
    "qdrant-client>=1.9.0",
    "fastembed>=0.4.0",
    "sentence-transformers>=3.4.0", # For cross-encoder reranking
    # Object storage
    "minio>=7.2.0",
    # Document parsing (default: Docling)
    "docling>=2.15.0",
    # Optional parsers installed via extras: mistral, unstructured
    # Task queue
    "celery>=5.4.0",
    "redis>=5.2.0",
    # Utilities
    "pydantic>=2.10.0",
    "pydantic-settings>=2.7.0",
    "python-dotenv>=1.0.1",
    # Observability
    "prometheus_client>=0.21.0",
    "cachetools>=5.5.0",
    "mistralai>=1.10.0",
    "langchain-groq>=1.1.1",
]

[project.optional-dependencies]
dev = [
    "pytest>=8.3.0",
    "pytest-asyncio>=0.25.0",
    "pytest-cov>=6.0.0",
    "ruff>=0.8.0",
    "mypy>=1.15.0",
    "pre-commit>=4.1.0",
]

# Optional: Additional embedding models
ml = [
    "langchain-huggingface>=0.1.2",
]

# Optional: Alternative document parsers (use PARSER_BACKEND env var to select)
mistral = [
    "mistralai>=1.0.0",
]
unstructured = [
    "unstructured[all-docs]>=0.16.0",
]

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

[project.urls]
Homepage = "https://github.com/GitHamza0206/simba"
Repository = "https://github.com/GitHamza0206/simba"

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

[tool.hatch.build.targets.wheel]
packages = ["simba"]

[tool.ruff]
line-length = 100
target-version = "py311"

[tool.ruff.lint]
select = ["E", "F", "I", "N", "W", "UP"]
ignore = ["E501"]

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

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

[tool.pytest.ini_options]
asyncio_mode = "auto"
testpaths = ["tests"]

[tool.uv]
# Use CPU-only PyTorch to reduce Docker image size by ~4GB
# This avoids pulling NVIDIA CUDA libraries in containerized environments

[[tool.uv.index]]
name = "pytorch-cpu"
url = "https://download.pytorch.org/whl/cpu"
explicit = true

[tool.uv.sources]
torch = { index = "pytorch-cpu" }
torchvision = { index = "pytorch-cpu" }
torchaudio = { index = "pytorch-cpu" }

[dependency-groups]
dev = [
    "pre-commit>=4.5.1",
    "ruff>=0.14.10",
]