Fix/dataset init (#409)

This commit is contained in:
Jyong 2023-06-19 16:32:03 +08:00 committed by GitHub
parent 82d07ed2a8
commit ce2996e7d4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 12 additions and 1 deletions

View File

@ -85,3 +85,9 @@ SENTRY_DSN=
# DEBUG
DEBUG=false
SQLALCHEMY_ECHO=false
# Notion import configuration, support public and internal
NOTION_INTEGRATION_TYPE=public
NOTION_CLIENT_SECRET=you-client-secret
NOTION_CLIENT_ID=you-client-id
NOTION_INTERNAL_SECRET=you-internal-secret

View File

@ -78,7 +78,7 @@ class DatasetService:
raise DatasetNameDuplicateError(
f'Dataset with name {name} already exists.')
dataset = Dataset(name=name, indexing_technique=indexing_technique, data_source_type='upload_file')
dataset = Dataset(name=name, indexing_technique=indexing_technique)
# dataset = Dataset(name=name, provider=provider, config=config)
dataset.created_by = account.id
dataset.updated_by = account.id
@ -374,6 +374,11 @@ class DocumentService:
def save_document_with_dataset_id(dataset: Dataset, document_data: dict,
account: Account, dataset_process_rule: Optional[DatasetProcessRule] = None,
created_from: str = 'web'):
# if dataset is empty, update dataset data_source_type
if not dataset.data_source_type:
dataset.data_source_type = document_data["data_source"]["type"]
db.session.commit()
if not dataset.indexing_technique:
if 'indexing_technique' not in document_data \
or document_data['indexing_technique'] not in Dataset.INDEXING_TECHNIQUE_LIST: