opensource/dify
3
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-09-21 13:20:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore: inject more db.session (#38045)

Browse Source 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
Asuka Minato
2026-06-30 06:55:54 +00:00
committed by GitHub
co-authored by autofix-ci[bot]
parent 528bf95d1b
commit 102e1ede6e
51 changed files with 1483 additions and 893 deletions
Download Patch File Download Diff File Expand all files Collapse all files
api/controllers/console/datasets/datasets_document.py
+44 -38
View File
@@ -181,7 +181,7 @@ class DocumentResource(Resource):
def get_document(
self, dataset_id: str, document_id: str, current_user: Account, current_tenant_id: str
) -> Document:
dataset = DatasetService.get_dataset(dataset_id)
dataset = DatasetService.get_dataset(dataset_id, db.session)
if not dataset:
raise NotFound("Dataset not found.")
@@ -190,7 +190,7 @@ class DocumentResource(Resource):
except services.errors.account.NoPermissionError as e:
raise Forbidden(str(e))
document = DocumentService.get_document(dataset_id, document_id)
document = DocumentService.get_document(dataset_id, document_id, session=db.session)
if not document:
raise NotFound("Document not found.")
@@ -201,7 +201,7 @@ class DocumentResource(Resource):
return document
def get_batch_documents(self, dataset_id: str, batch: str, current_user: Account) -> Sequence[Document]:
dataset = DatasetService.get_dataset(dataset_id)
dataset = DatasetService.get_dataset(dataset_id, db.session)
if not dataset:
raise NotFound("Dataset not found.")
@@ -210,7 +210,7 @@ class DocumentResource(Resource):
except services.errors.account.NoPermissionError as e:
raise Forbidden(str(e))
documents = DocumentService.get_batch_documents(dataset_id, batch)
documents = DocumentService.get_batch_documents(dataset_id, batch, db.session)
if not documents:
raise NotFound("Documents not found.")
@@ -241,7 +241,7 @@ class GetProcessRuleApi(Resource):
# get the latest process rule
document = db.get_or_404(Document, document_id)
dataset = DatasetService.get_dataset(document.dataset_id)
dataset = DatasetService.get_dataset(document.dataset_id, db.session)
if not dataset:
raise NotFound("Dataset not found.")
@@ -317,7 +317,7 @@ class DatasetDocumentListApi(Resource):
)
except (ArgumentTypeError, ValueError, Exception):
fetch = False
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
if not dataset:
raise NotFound("Dataset not found.")
@@ -421,7 +421,7 @@ class DatasetDocumentListApi(Resource):
def post(self, current_user: Account, dataset_id: UUID):
dataset_id_str = str(dataset_id)
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
if not dataset:
raise NotFound("Dataset not found.")
@@ -444,8 +444,10 @@ class DatasetDocumentListApi(Resource):
DocumentService.document_create_args_validate(knowledge_config)
try:
documents, batch = DocumentService.save_document_with_dataset_id(dataset, knowledge_config, current_user)
dataset = DatasetService.get_dataset(dataset_id_str)
documents, batch = DocumentService.save_document_with_dataset_id(
dataset, knowledge_config, current_user, session=db.session
)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -464,7 +466,7 @@ class DatasetDocumentListApi(Resource):
@rbac_permission_required(RBACResourceScope.DATASET, RBACPermission.DATASET_EDIT)
def delete(self, dataset_id: UUID):
dataset_id_str = str(dataset_id)
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
if dataset is None:
raise NotFound("Dataset not found.")
# check user's model setting
@@ -472,7 +474,7 @@ class DatasetDocumentListApi(Resource):
try:
document_ids = request.args.getlist("document_id")
DocumentService.delete_documents(dataset, document_ids)
DocumentService.delete_documents(dataset, document_ids, db.session)
except services.errors.document.DocumentIndexingError:
raise DocumentIndexingError("Cannot delete document during indexing.")
@@ -531,6 +533,7 @@ class DatasetInitApi(Resource):
tenant_id=current_tenant_id,
knowledge_config=knowledge_config,
account=current_user,
session=db.session,
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -867,7 +870,7 @@ class DocumentApi(DocumentResource):
if metadata == "only":
response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata_details}
elif metadata == "without":
dataset_process_rules = DatasetService.get_process_rules(dataset_id_str)
dataset_process_rules = DatasetService.get_process_rules(dataset_id_str, db.session)
document_process_rules = document.dataset_process_rule.to_dict() if document.dataset_process_rule else {}
response = {
"id": document.id,
@@ -901,7 +904,7 @@ class DocumentApi(DocumentResource):
"need_summary": document.need_summary if document.need_summary is not None else False,
}
else:
dataset_process_rules = DatasetService.get_process_rules(dataset_id_str)
dataset_process_rules = DatasetService.get_process_rules(dataset_id_str, db.session)
document_process_rules = document.dataset_process_rule.to_dict() if document.dataset_process_rule else {}
response = {
"id": document.id,
@@ -950,7 +953,7 @@ class DocumentApi(DocumentResource):
def delete(self, current_tenant_id: str, current_user: Account, dataset_id: UUID, document_id: UUID):
dataset_id_str = str(dataset_id)
document_id_str = str(document_id)
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
if dataset is None:
raise NotFound("Dataset not found.")
# check user's model setting
@@ -959,7 +962,7 @@ class DocumentApi(DocumentResource):
document = self.get_document(dataset_id_str, document_id_str, current_user, current_tenant_id)
try:
DocumentService.delete_document(document)
DocumentService.delete_document(document, db.session)
except services.errors.document.DocumentIndexingError:
raise DocumentIndexingError("Cannot delete document during indexing.")
@@ -983,7 +986,7 @@ class DocumentDownloadApi(DocumentResource):
def get(self, current_tenant_id: str, current_user: Account, dataset_id: UUID, document_id: UUID) -> dict[str, Any]:
# Reuse the shared permission/tenant checks implemented in DocumentResource.
document = self.get_document(str(dataset_id), str(document_id), current_user, current_tenant_id)
return {"url": DocumentService.get_document_download_url(document)}
return {"url": DocumentService.get_document_download_url(document, db.session)}
@console_ns.route("/datasets/<uuid:dataset_id>/documents/download-zip")
@@ -1013,6 +1016,7 @@ class DocumentBatchDownloadZipApi(DocumentResource):
document_ids=document_ids,
tenant_id=current_tenant_id,
current_user=current_user,
session=db.session,
)
# Delegate ZIP packing to FileService, but keep Flask response+cleanup in the route.
@@ -1161,7 +1165,7 @@ class DocumentStatusApi(DocumentResource):
self, current_user: Account, dataset_id: UUID, action: Literal["enable", "disable", "archive", "un_archive"]
):
dataset_id_str = str(dataset_id)
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
if dataset is None:
raise NotFound("Dataset not found.")
@@ -1178,7 +1182,7 @@ class DocumentStatusApi(DocumentResource):
document_ids = request.args.getlist("document_id")
try:
DocumentService.batch_update_document_status(dataset, document_ids, action, current_user)
DocumentService.batch_update_document_status(dataset, document_ids, action, current_user, db.session)
except services.errors.document.DocumentIndexingError as e:
raise InvalidActionError(str(e))
except ValueError as e:
@@ -1202,11 +1206,11 @@ class DocumentPauseApi(DocumentResource):
dataset_id_str = str(dataset_id)
document_id_str = str(document_id)
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
if not dataset:
raise NotFound("Dataset not found.")
document = DocumentService.get_document(dataset.id, document_id_str)
document = DocumentService.get_document(dataset.id, document_id_str, session=db.session)
# 404 if document not found
if document is None:
@@ -1218,7 +1222,7 @@ class DocumentPauseApi(DocumentResource):
try:
# pause document
DocumentService.pause_document(document)
DocumentService.pause_document(document, db.session)
except services.errors.document.DocumentIndexingError:
raise DocumentIndexingError("Cannot pause completed document.")
@@ -1237,10 +1241,10 @@ class DocumentRecoverApi(DocumentResource):
"""recover document."""
dataset_id_str = str(dataset_id)
document_id_str = str(document_id)
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
if not dataset:
raise NotFound("Dataset not found.")
document = DocumentService.get_document(dataset.id, document_id_str)
document = DocumentService.get_document(dataset.id, document_id_str, session=db.session)
# 404 if document not found
if document is None:
@@ -1251,7 +1255,7 @@ class DocumentRecoverApi(DocumentResource):
raise ArchivedDocumentImmutableError()
try:
# pause document
DocumentService.recover_document(document)
DocumentService.recover_document(document, db.session)
except services.errors.document.DocumentIndexingError:
raise DocumentIndexingError("Document is not in paused status.")
@@ -1271,13 +1275,13 @@ class DocumentRetryApi(DocumentResource):
"""retry document."""
payload = DocumentRetryPayload.model_validate(console_ns.payload or {})
dataset_id_str = str(dataset_id)
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
retry_documents = []
if not dataset:
raise NotFound("Dataset not found.")
for document_id in payload.document_ids:
try:
document = DocumentService.get_document(dataset.id, document_id)
document = DocumentService.get_document(dataset.id, document_id, session=db.session)
# 404 if document not found
if document is None:
@@ -1295,7 +1299,7 @@ class DocumentRetryApi(DocumentResource):
logger.exception("Failed to retry document, document id: %s", document_id)
continue
# retry document
DocumentService.retry_document(dataset_id_str, retry_documents)
DocumentService.retry_document(dataset_id_str, retry_documents, db.session)
return "", 204
@@ -1313,14 +1317,14 @@ class DocumentRenameApi(DocumentResource):
# The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
if not current_user.is_dataset_editor:
raise Forbidden()
dataset = DatasetService.get_dataset(dataset_id)
dataset = DatasetService.get_dataset(dataset_id, db.session)
if not dataset:
raise NotFound("Dataset not found.")
DatasetService.check_dataset_operator_permission(current_user, dataset)
DatasetService.check_dataset_operator_permission(current_user, dataset, session=db.session)
payload = DocumentRenamePayload.model_validate(console_ns.payload or {})
try:
document = DocumentService.rename_document(str(dataset_id), str(document_id), payload.name)
document = DocumentService.rename_document(str(dataset_id), str(document_id), payload.name, db.session)
except services.errors.document.DocumentIndexingError:
raise DocumentIndexingError("Cannot delete document during indexing.")
@@ -1338,11 +1342,11 @@ class WebsiteDocumentSyncApi(DocumentResource):
def get(self, current_tenant_id: str, dataset_id: UUID, document_id: UUID):
"""sync website document."""
dataset_id_str = str(dataset_id)
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
if not dataset:
raise NotFound("Dataset not found.")
document_id_str = str(document_id)
document = DocumentService.get_document(dataset.id, document_id_str)
document = DocumentService.get_document(dataset.id, document_id_str, session=db.session)
if not document:
raise NotFound("Document not found.")
if document.tenant_id != current_tenant_id:
@@ -1353,7 +1357,7 @@ class WebsiteDocumentSyncApi(DocumentResource):
if DocumentService.check_archived(document):
raise ArchivedDocumentImmutableError()
# sync document
DocumentService.sync_website_document(dataset_id_str, document)
DocumentService.sync_website_document(dataset_id_str, document, db.session)
return {"result": "success"}, 200
@@ -1373,10 +1377,10 @@ class DocumentPipelineExecutionLogApi(DocumentResource):
dataset_id_str = str(dataset_id)
document_id_str = str(document_id)
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
if not dataset:
raise NotFound("Dataset not found.")
document = DocumentService.get_document(dataset.id, document_id_str)
document = DocumentService.get_document(dataset.id, document_id_str, session=db.session)
if not document:
raise NotFound("Document not found.")
log = db.session.scalar(
@@ -1431,7 +1435,7 @@ class DocumentGenerateSummaryApi(Resource):
dataset_id_str = str(dataset_id)
# Get dataset
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
if not dataset:
raise NotFound("Dataset not found.")
@@ -1465,7 +1469,7 @@ class DocumentGenerateSummaryApi(Resource):
raise ValueError("Summary index is not enabled for this dataset. Please enable it in the dataset settings.")
# Verify all documents exist and belong to the dataset
documents = DocumentService.get_documents_by_ids(dataset_id_str, document_list)
documents = DocumentService.get_documents_by_ids(dataset_id_str, document_list, db.session)
if len(documents) != len(document_list):
found_ids = {doc.id for doc in documents}
@@ -1481,6 +1485,7 @@ class DocumentGenerateSummaryApi(Resource):
DocumentService.update_documents_need_summary(
dataset_id=dataset_id_str,
document_ids=document_ids_to_update,
session=db.session,
need_summary=True,
)
@@ -1531,7 +1536,7 @@ class DocumentSummaryStatusApi(DocumentResource):
document_id_str = str(document_id)
# Get dataset
dataset = DatasetService.get_dataset(dataset_id_str)
dataset = DatasetService.get_dataset(dataset_id_str, db.session)
if not dataset:
raise NotFound("Dataset not found.")
@@ -1547,6 +1552,7 @@ class DocumentSummaryStatusApi(DocumentResource):
result = SummaryIndexService.get_document_summary_status_detail(
document_id=document_id_str,
dataset_id=dataset_id_str,
session=db.session,
)
return result, 200