Skip to content

fix: 修复导入的文档删除部分的分段后，字符数不会重新计算 #421 #454

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
May 15, 2024
Merged

fix: 修复导入的文档删除部分的分段后，字符数不会重新计算 #421 #454

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
5 changes: 4 additions & 1 deletion apps/dataset/serializers/paragraph_serializers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
from rest_framework import serializers

from common.db.search import page_search
from common.event.listener_manage import ListenerManagement, UpdateEmbeddingDocumentIdArgs, UpdateEmbeddingDatasetIdArgs
from common.event.listener_manage import ListenerManagement, UpdateEmbeddingDocumentIdArgs
from common.exception.app_exception import AppApiException
from common.mixins.api_mixin import ApiMixin
from common.util.common import post
Expand Down Expand Up @@ -284,6 +284,7 @@ def batch_delete(self, instance: Dict, with_valid=True):
paragraph_id_list = instance.get("id_list")
QuerySet(Paragraph).filter(id__in=paragraph_id_list).delete()
QuerySet(ProblemParagraphMapping).filter(paragraph_id__in=paragraph_id_list).delete()
update_document_char_length(self.data.get('document_id'))
# 删除向量库
ListenerManagement.delete_embedding_by_paragraph_ids(paragraph_id_list)
return True
Expand Down Expand Up @@ -370,6 +371,7 @@ def migrate(self, with_valid=True):
target_document_id, target_dataset_id))
# 修改段落信息
paragraph_list.update(dataset_id=target_dataset_id, document_id=target_document_id)
update_document_char_length(document_id)

@staticmethod
def update_problem_paragraph_mapping(target_document_id: str, problem_paragraph_mapping):
Expand Down Expand Up @@ -527,6 +529,7 @@ def delete(self, with_valid=False):
paragraph_id = self.data.get('paragraph_id')
QuerySet(Paragraph).filter(id=paragraph_id).delete()
QuerySet(ProblemParagraphMapping).filter(paragraph_id=paragraph_id).delete()
update_document_char_length(self.data.get('document_id'))
ListenerManagement.delete_embedding_by_paragraph_signal.send(paragraph_id)

@staticmethod
Expand Down
Loading