Dirk Riemann
a418969251
Our client code imports surya.foundation (added in 0.17). The earlier cu124 torch pin forced uv to downgrade surya to 0.14.1, which doesn't have that module and depends on a transformers version that lacks QuantizedCacheConfig. Net: ocr: fail at /healthz. Drop the cu124 index pin. surya 0.17.1 needs torch >= 2.7, which the default pypi torch (2.11) satisfies. The deploy host's CUDA 12.4 driver doesn't match torch 2.11's cu13 wheels, so CUDA init warns and the GPU isn't available — torch + Surya transparently fall back to CPU. Slower than GPU but correct for MVP. A host driver upgrade later will unlock GPU with no code changes. Unit suite stays green. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
80 lines
1.9 KiB
TOML
80 lines
1.9 KiB
TOML
[project]
|
|
name = "infoxtractor"
|
|
version = "0.1.0"
|
|
description = "Async on-prem LLM-powered structured information extraction microservice"
|
|
readme = "README.md"
|
|
requires-python = ">=3.12"
|
|
license = { text = "MIT" }
|
|
authors = [{ name = "goldstein" }]
|
|
|
|
dependencies = [
|
|
# Web / async
|
|
"fastapi>=0.115",
|
|
"uvicorn[standard]>=0.32",
|
|
"httpx>=0.27",
|
|
|
|
# Data
|
|
"pydantic>=2.9",
|
|
"pydantic-settings>=2.6",
|
|
|
|
# Database
|
|
"sqlalchemy[asyncio]>=2.0.36",
|
|
"asyncpg>=0.30",
|
|
"alembic>=1.14",
|
|
|
|
# Document processing
|
|
"pymupdf>=1.25",
|
|
"pillow>=10.2,<11.0",
|
|
"python-magic>=0.4.27",
|
|
"python-dateutil>=2.9",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
ocr = [
|
|
# Real OCR engine. Kept optional so CI (no GPU) can install the base
|
|
# package without the model deps.
|
|
# surya >= 0.17 is required: the client code uses the
|
|
# `surya.foundation` module, which older releases don't expose.
|
|
"surya-ocr>=0.17,<0.18",
|
|
"torch>=2.7",
|
|
]
|
|
dev = [
|
|
"pytest>=8.3",
|
|
"pytest-asyncio>=0.24",
|
|
"pytest-httpx>=0.32",
|
|
"ruff>=0.8",
|
|
"mypy>=1.13",
|
|
]
|
|
|
|
# Note: the default pypi torch ships cu13 wheels, which emit a
|
|
# UserWarning and fall back to CPU against the deploy host's CUDA 12.4
|
|
# driver. Surya then runs on CPU — slower but correct for MVP. A future
|
|
# driver upgrade unlocks GPU Surya with no code changes.
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["src/ix"]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
testpaths = ["tests"]
|
|
addopts = "-ra --strict-markers"
|
|
markers = [
|
|
"live: requires live Ollama/Surya (IX_TEST_OLLAMA=1 to enable)",
|
|
]
|
|
|
|
[tool.ruff]
|
|
line-length = 100
|
|
target-version = "py312"
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "W", "I", "UP", "B", "SIM", "RUF"]
|
|
ignore = ["E501"] # line length handled by formatter
|
|
|
|
[tool.mypy]
|
|
python_version = "3.12"
|
|
strict = true
|
|
plugins = ["pydantic.mypy"]
|