feat: optimize the format convert

2026-02-04 12:00:06 +08:00
parent 10dbd59161
commit 526c1f3a0d
7 changed files with 571 additions and 187 deletions
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -26,7 +26,8 @@ dependencies = [
    "pypandoc==1.16.2",
    "paddlepaddle",
    "paddleocr[doc-parser]",
-    "safetensors"
+    "safetensors",
+    "lxml>=5.0.0"
 ]

 [tool.uv.sources]