Merge branch 'feat/support-parent-child-chunk' into deploy/dev

langgenius · Dec 23, 2024 · aa589d4 · aa589d4
2 parents a4b356a + f3095c7
commit aa589d4
Showing 1 changed file with 3 additions and 1 deletion.
diff --git a/api/core/rag/extractor/word_extractor.py b/api/core/rag/extractor/word_extractor.py
@@ -261,8 +261,10 @@ def parse_paragraph(paragraph):
                 if isinstance(element.tag, str) and element.tag.endswith("p"):  # paragraph
                     para = paragraphs.pop(0)
                     parsed_paragraph = parse_paragraph(para)
-                    if parsed_paragraph:
+                    if parsed_paragraph.strip():
                         content.append(parsed_paragraph)
+                    else:
+                        content.append("\n")
                 elif isinstance(element.tag, str) and element.tag.endswith("tbl"):  # table
                     table = tables.pop(0)
                     content.append(self._table_to_markdown(table, image_map))