feat: 新增 DocxSplitter — 支持 .docx 文档入库

2026-07-11 19:55:03 +08:00
parent 04f2f8a8a8
commit d9b03ab5f0
7 changed files with 231 additions and 10 deletions
@@ -23,7 +23,8 @@ dev = ["pytest>=8.0", "httpx>=0.27.0", "pytest-cov>=5.0", "ruff>=0.8.0", "mypy>=
 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"]
+docx = ["markitdown>=0.1.0"]
+all = ["md-vector-db[pdf,html,epub,docx]", "requests>=2.31.0", "openai>=1.0.0"]

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