zhuchaowe/maxkb
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: 修复web站点知识库同步状态错误 (#1731)

Browse Source
This commit is contained in:
shaohuzhang1 2024-12-02 13:38:03 +08:00 committed by GitHub
parent a32977094f
commit 2084112d54
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 13 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
apps/dataset/serializers/document_serializers.py
View File

@ -432,6 +432,7 @@ class DocumentSerializers(ApiMixin, serializers.Serializer):
ListenerManagement.update_status(QuerySet(Document).filter(id=document_id), ListenerManagement.update_status(QuerySet(Document).filter(id=document_id),
TaskType.SYNC, TaskType.SYNC,
State.PENDING) State.PENDING)
ListenerManagement.get_aggregation_document_status(document_id)()
source_url = document.meta.get('source_url') source_url = document.meta.get('source_url')
selector_list = document.meta.get('selector').split( selector_list = document.meta.get('selector').split(
" ") if 'selector' in document.meta and document.meta.get('selector') is not None else [] " ") if 'selector' in document.meta and document.meta.get('selector') is not None else []
@ -444,10 +445,10 @@ class DocumentSerializers(ApiMixin, serializers.Serializer):
# 删除向量库 # 删除向量库
delete_embedding_by_document(document_id) delete_embedding_by_document(document_id)
paragraphs = get_split_model('web.md').parse(result.content) paragraphs = get_split_model('web.md').parse(result.content)
document.char_length = reduce(lambda x, y: x + y, char_length = reduce(lambda x, y: x + y,
[len(p.get('content')) for p in paragraphs], [len(p.get('content')) for p in paragraphs],
0) 0)
document.save() QuerySet(Document).filter(id=document_id).update(char_length=char_length)
document_paragraph_model = DocumentSerializers.Create.get_paragraph_model(document, paragraphs) document_paragraph_model = DocumentSerializers.Create.get_paragraph_model(document, paragraphs)
paragraph_model_list = document_paragraph_model.get('paragraph_model_list') paragraph_model_list = document_paragraph_model.get('paragraph_model_list')
@ -464,6 +465,13 @@ class DocumentSerializers(ApiMixin, serializers.Serializer):
# 向量化 # 向量化
if with_embedding: if with_embedding:
embedding_model_id = get_embedding_model_id_by_dataset_id(document.dataset_id) embedding_model_id = get_embedding_model_id_by_dataset_id(document.dataset_id)
ListenerManagement.update_status(QuerySet(Document).filter(id=document_id),
TaskType.EMBEDDING,
State.PENDING)
ListenerManagement.update_status(QuerySet(Paragraph).filter(document_id=document_id),
TaskType.EMBEDDING,
State.PENDING)
ListenerManagement.get_aggregation_document_status(document_id)()
embedding_by_document.delay(document_id, embedding_model_id) embedding_by_document.delay(document_id, embedding_model_id)
else: else:
@ -477,6 +485,7 @@ class DocumentSerializers(ApiMixin, serializers.Serializer):
ListenerManagement.update_status(QuerySet(Paragraph).filter(document_id=document_id), ListenerManagement.update_status(QuerySet(Paragraph).filter(document_id=document_id),
TaskType.SYNC, TaskType.SYNC,
state) state)
ListenerManagement.get_aggregation_document_status(document_id)()
return True return True
class Operate(ApiMixin, serializers.Serializer): class Operate(ApiMixin, serializers.Serializer):