Skip to content

fix: Application The reference segmentation of the knowledge base retrieval node in the loop body is displayed as 0 #4466

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
Dec 8, 2025
Merged

fix: Application The reference segmentation of the knowledge base retrieval node in the loop body is displayed as 0 #4466

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
13 changes: 12 additions & 1 deletion apps/application/serializers/application_chat_record.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,6 +110,16 @@ def list(self, with_valid=True):
return [ChatRecordSerializerModel(chat_record).data for chat_record in
QuerySet(ChatRecord).filter(chat_id=self.data.get('chat_id')).order_by(order_by)]

@staticmethod
def get_loop_workflow_node(details):
result = []
for item in details.values():
if item.get('type') == 'loop-node':
for loop_item in item.get('loop_node_data') or []:
for inner_item in loop_item.values():
result.append(inner_item)
return result

@staticmethod
def reset_chat_record(chat_record, show_source, show_exec):
knowledge_list = []
Expand All @@ -119,7 +129,8 @@ def reset_chat_record(chat_record, show_source, show_exec):
paragraph_list = chat_record.details.get('search_step').get(
'paragraph_list')

for item in chat_record.details.values():
for item in [*chat_record.details.values(),
*ApplicationChatRecordQuerySerializers.get_loop_workflow_node(chat_record.details)]:
if item.get('type') == 'search-knowledge-node' and item.get('show_knowledge', False):
paragraph_list = paragraph_list + (item.get(
'paragraph_list') or [])
Copy link
Contributor Author

@shaohuzhang1 shaohuzhang1 Dec 8, 2025

Choose a reason for hiding this comment

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

There are a few optimizations and improvements that can be made to enhance the code's performance and readability:

  1. Avoid Reversing Loop Order: In get_loop_workflow_node, reversing the loops (outer for -> inner for) is unnecessary. This should not affect the output but might make it harder to understand.

  2. Use Set instead of List for Result Accumulation: If you expect duplicates in loop_node_data, using a set could reduce memory usage compared to a list, although this doesn't make sense in this specific context where order does matter.

  3. Consistent Naming Conventions: Ensure consistent naming conventions throughout the codebase. The use of single underscores (_) for local variables and class methods might improve readability, especially when working in larger projects.

  4. Remove Redundant Code from Serializer Creation:

    # Remove redundant line
# return query_set.filter(chat_id=self.data.get('chat_id')).order_by(order_by)).all()

  5. Optimize Query Construction:

    

    6. 



Optimized version of fetching chat records


def list(self, with_valid=True):

qs = (

ChatRecord.objects

.filter(chat_id=self.data.get('chat_id'))

.order_by(order_by)

)

if not with_valid:

qs = qs.exclude(is_valid=False)

return [ChatRecordSerializerModel(rec).data for rec in qs]


This changes the logic to avoid querying more data than necessary by directly filtering based on `with_valid`.

These suggestions focus on improving efficiency and clarity while maintaining the original functionality.


    

  
  




    


        

      
  
  

    
  
    
    

  

  

  



          

      
    








    


  









  


    


  		



  

    
          
            
          
          Expand Down
    
    
  



                
              


          


    

  



  



    

  
  
    
      Loading