Skip to content

fix: Intelligent segmentation of knowledge base, blank line and carriage return segmentation identification are not effective #4791 #4793

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
shaohuzhang1 merged 1 commit into from
Feb 9, 2026
+3 −4
Merged

fix: Intelligent segmentation of knowledge base, blank line and carriage return segmentation identification are not effective #4791 #4793

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 3 additions & 4 deletions apps/common/utils/split_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,11 +167,10 @@ def parse_level(text, pattern: str):
level_content_list = list(map(to_tree_obj, [r[0:255] for r in re_findall(pattern, text) if r is not None]))
# 过滤掉空标题或只包含#和空白字符的标题
filtered_list = [item for item in level_content_list
if item['content'].strip() and item['content'].replace('#', '').strip()]
if item['content'].strip(' ') and item['content'].replace('#', '').strip(' ')]
return list(map(filter_special_symbol, filtered_list))



def re_findall(pattern, text):
# 检查 pattern 是否为空或无效
if pattern is None:
Expand Down Expand Up @@ -305,8 +304,8 @@ def smart_split_paragraph(content: str, limit: int):
# 优先级:句号 > 感叹号/问号 > 回车
split_chars = [
('。', 0), ('.', 0), # 中英文句号
('!', 0), ('!', 0), # 中英文感叹号
('?', 0), ('?', 0), # 中英文问号
('!', 0), ('!', 0), # 中英文感叹号
('?', 0), ('?', 0), # 中英文问号
]

# 从后往前找分割点
Expand Down