Skip to content

fix: Knowledge base retrieval segmentation sorted by relevance #2791

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
merged 1 commit into from
Apr 3, 2025
Merged

fix: Knowledge base retrieval segmentation sorted by relevance #2791

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
2 changes: 1 addition & 1 deletion apps/application/flow/step_node/search_dataset_node/impl/base_search_dataset_node.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,7 @@ def execute(self, dataset_id_list, dataset_setting, question,
'is_hit_handling_method_list': [row for row in result if row.get('is_hit_handling_method')],
'data': '\n'.join(
[f"{reset_title(paragraph.get('title', ''))}{paragraph.get('content')}" for paragraph in
paragraph_list])[0:dataset_setting.get('max_paragraph_char_number', 5000)],
result])[0:dataset_setting.get('max_paragraph_char_number', 5000)],
'directly_return': '\n'.join(
[paragraph.get('content') for paragraph in
result if
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There are two minor issues in the given code:

  1. At line 86, there is an extra closing parenthesis } after 'is_hit_handling_method' which seems unintended.

  2. In line 94, you have another unexpected closing parenthesis { at the end of the list comprehension for extracting paragraphs.

To fix these, modify lines 86 and 94 as follows:

'directly_return': ''.join(
                [paragraph.get('content') for paragraph in result if
                 paragraph.get('hit_status', 'False') == 'True']),

These changes ensure that both conditions are tested before appending to the final string, and they also corrects syntax errors due to unnecessary parentheses. This should improve readability and possibly function correctly depending on how result is structured. However, please review the rest of your code to ensure it addresses all functionality requirements without introducing additional bugs or inefficiencies.

Expand Down