estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Mapped column (#22644)

Browse Source 
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Asuka Minato
2025-07-23 01:39:59 +09:00
committed by GitHub
parent 0f4809b9b8
commit 6d3e198c3c
19 changed files with 745 additions and 716 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
api/services/dataset_service.py
View File

@@ -215,9 +215,9 @@ class DatasetService:
dataset.created_by = account.id
dataset.updated_by = account.id
dataset.tenant_id = tenant_id
dataset.embedding_model_provider = embedding_model.provider if embedding_model else None
dataset.embedding_model = embedding_model.model if embedding_model else None
dataset.retrieval_model = retrieval_model.model_dump() if retrieval_model else None
dataset.embedding_model_provider = embedding_model.provider if embedding_model else None # type: ignore
dataset.embedding_model = embedding_model.model if embedding_model else None # type: ignore
dataset.retrieval_model = retrieval_model.model_dump() if retrieval_model else None # type: ignore
dataset.permission = permission or DatasetPermissionEnum.ONLY_ME
dataset.provider = provider
db.session.add(dataset)
@@ -1540,8 +1540,10 @@ class DocumentService:
db.session.add(document)
db.session.commit()
# update document segment
update_params = {DocumentSegment.status: "re_segment"}
db.session.query(DocumentSegment).filter_by(document_id=document.id).update(update_params)
db.session.query(DocumentSegment).filter_by(document_id=document.id).update(
{DocumentSegment.status: "re_segment"}
) # type: ignore
db.session.commit()
# trigger async task
document_indexing_update_task.delay(document.dataset_id, document.id)
@@ -2226,7 +2228,7 @@ class SegmentService:
# calc embedding use tokens
if document.doc_form == "qa_model":
segment.answer = args.answer
tokens = embedding_model.get_text_embedding_num_tokens(texts=[content + segment.answer])[0]
tokens = embedding_model.get_text_embedding_num_tokens(texts=[content + segment.answer])[0] # type: ignore
else:
tokens = embedding_model.get_text_embedding_num_tokens(texts=[content])[0]
segment.content = content