Files
daily-paper/pyproject.toml
T
Rain-Bus 18f44ac244 feat: improve PDF image extraction with caption-based labeling and fallback matching
- Enhance pdf_image_extractor with caption text extraction near images/tables
- Add figure/table type correction based on caption content
- Implement sequential numbering fallback for unmatched items
- Improve figure linking in pages with manifest ID matching and fallback strategies
- Remove docling dependency, add dev dependency group
2026-06-09 14:07:21 +08:00

42 lines
822 B
TOML

[project]
name = "hf-daily-papers"
version = "0.1.0"
description = "HuggingFace Daily Papers — 中文论文导览站"
requires-python = ">=3.12"
dependencies = [
"fastapi>=0.115",
"uvicorn[standard]>=0.34",
"sqlalchemy>=2.0",
"httpx>=0.28",
"jinja2>=3.1",
"python-multipart>=0.0.18",
"pydantic>=2.0",
"pydantic-settings>=2.0",
"typer>=0.15",
"python-dotenv>=1.0",
"apscheduler>=3.10",
"chromadb>=1.0",
"pymupdf>=1.25",
"itsdangerous>=2.2.0",
"bleach>=6.4.0",
]
[project.optional-dependencies]
dev = [
"pytest>=8.0",
"pytest-asyncio>=0.24",
]
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
packages = ["app"]
[dependency-groups]
dev = [
"pytest>=9.0.3",
"pytest-asyncio>=1.4.0",
]