Update app.py

app.py

@@ -2,6 +2,9 @@ import gradio as gr
 from docx import Document
 import os
 
+from docx import Document
+from docx.oxml import CT_P
+
 def split_by_headers(file_path, headers_per_chunk=1):
     doc = Document(file_path)
     chunks = []
@@ -9,8 +12,8 @@ def split_by_headers(file_path, headers_per_chunk=1):
     header_count = 0
     
     for element in doc.element.body:
-        if element.tag.endswith('p'):
-            paragraph = element._element
+        if isinstance(element, CT_P):
+            paragraph = element
             if any(style.val.startswith('Heading') for style in paragraph.xpath('.//w:pStyle')):
                 header_count += 1
                 if header_count > headers_per_chunk: