Files
md-vector-db/pyproject.toml
T
Serendipity 3b8b585f31 feat: 添加 EPUBSplitter — ebooklib 提取章节文字后分块
- 新增 splitters/epub.py: ebooklib 读取 EPUB → BeautifulSoup 去标签 → TextSplitter 分块
- epub 作为可选依赖: uv sync --extra epub
- registry 新增 .epub 映射, ingest_file 处理 EPUB 二进制文件
- 测试: 3 个 EPUBSplitter 测试 (含空 EPUB/Protocol 合规)

Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-10 14:32:41 +08:00

41 lines
959 B
TOML

[project]
name = "md-vector-db"
version = "0.1.0"
description = "Markdown 文档向量数据库,支持语义检索"
requires-python = ">=3.13"
dependencies = [
"chromadb>=0.5.0",
"sentence-transformers>=3.0.0",
"fastapi>=0.115.0",
"uvicorn[standard]>=0.30.0",
"pyyaml>=6.0",
"markdown-it-py>=3.0.0",
"typer>=0.12.0",
"python-dotenv>=1.2.2",
]
[project.scripts]
md-vector-db = "src.cli.main:app"
[project.optional-dependencies]
dev = ["pytest>=8.0", "httpx>=0.27.0"]
pdf = ["pymupdf>=1.24.0"]
html = ["beautifulsoup4>=4.12.0"]
epub = ["ebooklib>=0.18"]
all = ["md-vector-db[pdf,html,epub]", "requests>=2.31.0", "openai>=1.0.0"]
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
packages = ["src/"]
[tool.uv]
find-links = ["D:/settings/Language/Python/库"]
index-strategy = "unsafe-best-match"
[tool.pytest.ini_options]
testpaths = ["tests"]
pythonpath = ["src"]