youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-06 02:18:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

Knowledge base API supports status updates #18147 (#18235)

Browse Source
This commit is contained in:
GuanMu
2025-06-21 11:18:48 +08:00
committed by GitHub
parent ef20f694b2
commit 870e73c03b
6 changed files with 329 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

80
api/controllers/console/datasets/datasets_document.py
View File

@ -43,7 +43,6 @@ from core.model_runtime.errors.invoke import InvokeAuthorizationError
from core.plugin.impl.exc import PluginDaemonClientSideError
from core.rag.extractor.entity.extract_setting import ExtractSetting
from extensions.ext_database import db
from extensions.ext_redis import redis_client
from fields.document_fields import (
dataset_and_document_fields,
document_fields,
@ -54,8 +53,6 @@ from libs.login import login_required
from models import Dataset, DatasetProcessRule, Document, DocumentSegment, UploadFile
from services.dataset_service import DatasetService, DocumentService
from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig
from tasks.add_document_to_index_task import add_document_to_index_task
from tasks.remove_document_from_index_task import remove_document_from_index_task
class DocumentResource(Resource):
@ -862,77 +859,16 @@ class DocumentStatusApi(DocumentResource):
DatasetService.check_dataset_permission(dataset, current_user)
document_ids = request.args.getlist("document_id")
for document_id in document_ids:
document = self.get_document(dataset_id, document_id)
indexing_cache_key = "document_{}_indexing".format(document.id)
cache_result = redis_client.get(indexing_cache_key)
if cache_result is not None:
raise InvalidActionError(f"Document:{document.name} is being indexed, please try again later")
try:
DocumentService.batch_update_document_status(dataset, document_ids, action, current_user)
except services.errors.document.DocumentIndexingError as e:
raise InvalidActionError(str(e))
except ValueError as e:
raise InvalidActionError(str(e))
except NotFound as e:
raise NotFound(str(e))
if action == "enable":
if document.enabled:
continue
document.enabled = True
document.disabled_at = None
document.disabled_by = None
document.updated_at = datetime.now(UTC).replace(tzinfo=None)
db.session.commit()
# Set cache to prevent indexing the same document multiple times
redis_client.setex(indexing_cache_key, 600, 1)
add_document_to_index_task.delay(document_id)
elif action == "disable":
if not document.completed_at or document.indexing_status != "completed":
raise InvalidActionError(f"Document: {document.name} is not completed.")
if not document.enabled:
continue
document.enabled = False
document.disabled_at = datetime.now(UTC).replace(tzinfo=None)
document.disabled_by = current_user.id
document.updated_at = datetime.now(UTC).replace(tzinfo=None)
db.session.commit()
# Set cache to prevent indexing the same document multiple times
redis_client.setex(indexing_cache_key, 600, 1)
remove_document_from_index_task.delay(document_id)
elif action == "archive":
if document.archived:
continue
document.archived = True
document.archived_at = datetime.now(UTC).replace(tzinfo=None)
document.archived_by = current_user.id
document.updated_at = datetime.now(UTC).replace(tzinfo=None)
db.session.commit()
if document.enabled:
# Set cache to prevent indexing the same document multiple times
redis_client.setex(indexing_cache_key, 600, 1)
remove_document_from_index_task.delay(document_id)
elif action == "un_archive":
if not document.archived:
continue
document.archived = False
document.archived_at = None
document.archived_by = None
document.updated_at = datetime.now(UTC).replace(tzinfo=None)
db.session.commit()
# Set cache to prevent indexing the same document multiple times
redis_client.setex(indexing_cache_key, 600, 1)
add_document_to_index_task.delay(document_id)
else:
raise InvalidActionError()
return {"result": "success"}, 200

55
api/controllers/service_api/dataset/dataset.py
View File

@ -4,7 +4,7 @@ from werkzeug.exceptions import Forbidden, NotFound
import services.dataset_service
from controllers.service_api import api
from controllers.service_api.dataset.error import DatasetInUseError, DatasetNameDuplicateError
from controllers.service_api.dataset.error import DatasetInUseError, DatasetNameDuplicateError, InvalidActionError
from controllers.service_api.wraps import (
DatasetApiResource,
cloud_edition_billing_rate_limit_check,
@ -17,7 +17,7 @@ from fields.dataset_fields import dataset_detail_fields
from fields.tag_fields import tag_fields
from libs.login import current_user
from models.dataset import Dataset, DatasetPermissionEnum
from services.dataset_service import DatasetPermissionService, DatasetService
from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
from services.entities.knowledge_entities.knowledge_entities import RetrievalModel
from services.tag_service import TagService
@ -329,6 +329,56 @@ class DatasetApi(DatasetApiResource):
raise DatasetInUseError()
class DocumentStatusApi(DatasetApiResource):
"""Resource for batch document status operations."""
def patch(self, tenant_id, dataset_id, action):
"""
Batch update document status.
Args:
tenant_id: tenant id
dataset_id: dataset id
action: action to perform (enable, disable, archive, un_archive)
Returns:
dict: A dictionary with a key 'result' and a value 'success'
int: HTTP status code 200 indicating that the operation was successful.
Raises:
NotFound: If the dataset with the given ID does not exist.
Forbidden: If the user does not have permission.
InvalidActionError: If the action is invalid or cannot be performed.
"""
dataset_id_str = str(dataset_id)
dataset = DatasetService.get_dataset(dataset_id_str)
if dataset is None:
raise NotFound("Dataset not found.")
# Check user's permission
try:
DatasetService.check_dataset_permission(dataset, current_user)
except services.errors.account.NoPermissionError as e:
raise Forbidden(str(e))
# Check dataset model setting
DatasetService.check_dataset_model_setting(dataset)
# Get document IDs from request body
data = request.get_json()
document_ids = data.get("document_ids", [])
try:
DocumentService.batch_update_document_status(dataset, document_ids, action, current_user)
except services.errors.document.DocumentIndexingError as e:
raise InvalidActionError(str(e))
except ValueError as e:
raise InvalidActionError(str(e))
return {"result": "success"}, 200
class DatasetTagsApi(DatasetApiResource):
@validate_dataset_token
@marshal_with(tag_fields)
@ -457,6 +507,7 @@ class DatasetTagsBindingStatusApi(DatasetApiResource):
api.add_resource(DatasetListApi, "/datasets")
api.add_resource(DatasetApi, "/datasets/<uuid:dataset_id>")
api.add_resource(DocumentStatusApi, "/datasets/<uuid:dataset_id>/documents/status/<string:action>")
api.add_resource(DatasetTagsApi, "/datasets/tags")
api.add_resource(DatasetTagBindingApi, "/datasets/tags/binding")
api.add_resource(DatasetTagUnbindingApi, "/datasets/tags/unbinding")