feat: 添加 PDFSplitter — pymupdf 提取文字后分块

2026-07-10 14:20:53 +08:00
parent cde4ae7ddc
commit 69fb8cac9f
3 changed files with 62 additions and 0 deletions
@@ -22,6 +22,17 @@ dev = [
    "pytest>=8.0",
    "httpx>=0.27.0",
 ]
+pdf = [
+    "pymupdf>=1.24.0",
+]
+html = [
+    "beautifulsoup4>=4.12.0",
+]
+all = [
+    "md-vector-db[pdf,html]",
+    "requests>=2.31.0",
+    "openai>=1.0.0",
+]

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