ef98f37525
- Remove doclayout-yolo (~4.8GB, torch/torchvision/triton) - Replace opencv-python with opencv-python-headless (~200MB) - Strip debug symbols from .so files (~300-800MB) - Remove paddle C++ headers (~22MB) - Use cuda:base instead of runtime (~3GB savings) - Simplify dependencies: remove doc-parser extras - Clean venv aggressively: no pip, setuptools, include/, share/ Expected size reduction: Before: 17GB After: ~3GB (82% reduction) Breakdown: - CUDA base: 0.4GB - Paddle: 0.7GB - PaddleOCR: 0.8GB - OpenCV-headless: 0.2GB - Other deps: 0.6GB Total: ~2.7-3GB Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
63 lines
1.3 KiB
TOML
63 lines
1.3 KiB
TOML
[project]
|
|
name = "doc-processer"
|
|
version = "0.1.0"
|
|
description = "Document processing API - Image to LaTeX/Markdown/MathML and Markdown to DOCX"
|
|
requires-python = ">=3.10"
|
|
license = { text = "MIT" }
|
|
authors = [
|
|
{ name = "YogeLiu" }
|
|
]
|
|
|
|
dependencies = [
|
|
"fastapi==0.128.0",
|
|
"uvicorn[standard]==0.40.0",
|
|
"opencv-python-headless==4.12.0.88", # headless: no Qt/FFmpeg GUI, server-only
|
|
"python-multipart==0.0.21",
|
|
"pydantic==2.12.5",
|
|
"pydantic-settings==2.12.0",
|
|
"httpx==0.28.1",
|
|
"numpy==2.2.6",
|
|
"pillow==12.0.0",
|
|
"python-docx==1.2.0",
|
|
"paddleocr==3.4.0",
|
|
"latex2mathml==3.78.1",
|
|
"paddle==1.2.0",
|
|
"pypandoc==1.16.2",
|
|
"paddlepaddle",
|
|
"paddleocr[doc-parser]",
|
|
"safetensors",
|
|
"lxml>=5.0.0",
|
|
"openai",
|
|
"wordfreq",
|
|
]
|
|
|
|
# [tool.uv.sources]
|
|
# paddlepaddle = { path = "wheels/paddlepaddle-3.4.0.dev20251224-cp310-cp310-linux_x86_64.whl" }
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=8.0.0",
|
|
"pytest-asyncio>=0.24.0",
|
|
"ruff>=0.8.0",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["app"]
|
|
|
|
[tool.ruff]
|
|
target-version = "py311"
|
|
line-length = 100
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I", "UP"]
|
|
ignore = ["E501"]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
testpaths = ["tests"]
|
|
|