Merge branch 'main' into feat/r2

# Conflicts:
#	api/core/plugin/impl/oauth.py
#	api/core/workflow/entities/variable_pool.py
#	api/models/workflow.py
#	api/services/dataset_service.py
This commit is contained in:
jyong
2025-06-25 14:35:23 +08:00
419 changed files with 17049 additions and 3831 deletions

View File

@ -63,6 +63,7 @@ from .app import (
statistic,
workflow,
workflow_app_log,
workflow_draft_variable,
workflow_run,
workflow_statistic,
)

View File

@ -56,8 +56,7 @@ class InsertExploreAppListApi(Resource):
parser.add_argument("position", type=int, required=True, nullable=False, location="json")
args = parser.parse_args()
with Session(db.engine) as session:
app = session.execute(select(App).filter(App.id == args["app_id"])).scalar_one_or_none()
app = db.session.execute(select(App).filter(App.id == args["app_id"])).scalar_one_or_none()
if not app:
raise NotFound(f"App '{args['app_id']}' is not found")
@ -78,38 +77,38 @@ class InsertExploreAppListApi(Resource):
select(RecommendedApp).filter(RecommendedApp.app_id == args["app_id"])
).scalar_one_or_none()
if not recommended_app:
recommended_app = RecommendedApp(
app_id=app.id,
description=desc,
copyright=copy_right,
privacy_policy=privacy_policy,
custom_disclaimer=custom_disclaimer,
language=args["language"],
category=args["category"],
position=args["position"],
)
if not recommended_app:
recommended_app = RecommendedApp(
app_id=app.id,
description=desc,
copyright=copy_right,
privacy_policy=privacy_policy,
custom_disclaimer=custom_disclaimer,
language=args["language"],
category=args["category"],
position=args["position"],
)
db.session.add(recommended_app)
db.session.add(recommended_app)
app.is_public = True
db.session.commit()
app.is_public = True
db.session.commit()
return {"result": "success"}, 201
else:
recommended_app.description = desc
recommended_app.copyright = copy_right
recommended_app.privacy_policy = privacy_policy
recommended_app.custom_disclaimer = custom_disclaimer
recommended_app.language = args["language"]
recommended_app.category = args["category"]
recommended_app.position = args["position"]
return {"result": "success"}, 201
else:
recommended_app.description = desc
recommended_app.copyright = copy_right
recommended_app.privacy_policy = privacy_policy
recommended_app.custom_disclaimer = custom_disclaimer
recommended_app.language = args["language"]
recommended_app.category = args["category"]
recommended_app.position = args["position"]
app.is_public = True
app.is_public = True
db.session.commit()
db.session.commit()
return {"result": "success"}, 200
return {"result": "success"}, 200
class InsertExploreAppApi(Resource):

View File

@ -17,6 +17,8 @@ from libs.login import login_required
from models import Account
from models.model import App
from services.app_dsl_service import AppDslService, ImportStatus
from services.enterprise.enterprise_service import EnterpriseService
from services.feature_service import FeatureService
class AppImportApi(Resource):
@ -60,7 +62,9 @@ class AppImportApi(Resource):
app_id=args.get("app_id"),
)
session.commit()
if result.app_id and FeatureService.get_system_features().webapp_auth.enabled:
# update web app setting as private
EnterpriseService.WebAppAuth.update_app_access_mode(result.app_id, "private")
# Return appropriate status code based on result
status = result.status
if status == ImportStatus.FAILED.value:

View File

@ -1,5 +1,6 @@
import json
import logging
from collections.abc import Sequence
from typing import cast
from flask import abort, request
@ -18,10 +19,12 @@ from controllers.console.app.error import (
from controllers.console.app.wraps import get_app_model
from controllers.console.wraps import account_initialization_required, setup_required
from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.entities.app_invoke_entities import InvokeFrom
from core.file.models import File
from extensions.ext_database import db
from factories import variable_factory
from factories import file_factory, variable_factory
from fields.workflow_fields import workflow_fields, workflow_pagination_fields
from fields.workflow_run_fields import workflow_run_node_execution_fields
from libs import helper
@ -30,6 +33,7 @@ from libs.login import current_user, login_required
from models import App
from models.account import Account
from models.model import AppMode
from models.workflow import Workflow
from services.app_generate_service import AppGenerateService
from services.errors.app import WorkflowHashNotEqualError
from services.errors.llm import InvokeRateLimitError
@ -38,6 +42,24 @@ from services.workflow_service import DraftWorkflowDeletionError, WorkflowInUseE
logger = logging.getLogger(__name__)
# TODO(QuantumGhost): Refactor existing node run API to handle file parameter parsing
# at the controller level rather than in the workflow logic. This would improve separation
# of concerns and make the code more maintainable.
def _parse_file(workflow: Workflow, files: list[dict] | None = None) -> Sequence[File]:
files = files or []
file_extra_config = FileUploadConfigManager.convert(workflow.features_dict, is_vision=False)
file_objs: Sequence[File] = []
if file_extra_config is None:
return file_objs
file_objs = file_factory.build_from_mappings(
mappings=files,
tenant_id=workflow.tenant_id,
config=file_extra_config,
)
return file_objs
class DraftWorkflowApi(Resource):
@setup_required
@login_required
@ -402,15 +424,30 @@ class DraftWorkflowNodeRunApi(Resource):
parser = reqparse.RequestParser()
parser.add_argument("inputs", type=dict, required=True, nullable=False, location="json")
parser.add_argument("query", type=str, required=False, location="json", default="")
parser.add_argument("files", type=list, location="json", default=[])
args = parser.parse_args()
inputs = args.get("inputs")
if inputs == None:
user_inputs = args.get("inputs")
if user_inputs is None:
raise ValueError("missing inputs")
workflow_srv = WorkflowService()
# fetch draft workflow by app_model
draft_workflow = workflow_srv.get_draft_workflow(app_model=app_model)
if not draft_workflow:
raise ValueError("Workflow not initialized")
files = _parse_file(draft_workflow, args.get("files"))
workflow_service = WorkflowService()
workflow_node_execution = workflow_service.run_draft_workflow_node(
app_model=app_model, node_id=node_id, user_inputs=inputs, account=current_user
app_model=app_model,
draft_workflow=draft_workflow,
node_id=node_id,
user_inputs=user_inputs,
account=current_user,
query=args.get("query", ""),
files=files,
)
return workflow_node_execution
@ -731,6 +768,27 @@ class WorkflowByIdApi(Resource):
return None, 204
class DraftWorkflowNodeLastRunApi(Resource):
@setup_required
@login_required
@account_initialization_required
@get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
@marshal_with(workflow_run_node_execution_fields)
def get(self, app_model: App, node_id: str):
srv = WorkflowService()
workflow = srv.get_draft_workflow(app_model)
if not workflow:
raise NotFound("Workflow not found")
node_exec = srv.get_node_last_run(
app_model=app_model,
workflow=workflow,
node_id=node_id,
)
if node_exec is None:
raise NotFound("last run not found")
return node_exec
api.add_resource(
DraftWorkflowApi,
"/apps/<uuid:app_id>/workflows/draft",
@ -795,3 +853,7 @@ api.add_resource(
WorkflowByIdApi,
"/apps/<uuid:app_id>/workflows/<string:workflow_id>",
)
api.add_resource(
DraftWorkflowNodeLastRunApi,
"/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/last-run",
)

View File

@ -0,0 +1,421 @@
import logging
from typing import Any, NoReturn
from flask import Response
from flask_restful import Resource, fields, inputs, marshal, marshal_with, reqparse
from sqlalchemy.orm import Session
from werkzeug.exceptions import Forbidden
from controllers.console import api
from controllers.console.app.error import (
DraftWorkflowNotExist,
)
from controllers.console.app.wraps import get_app_model
from controllers.console.wraps import account_initialization_required, setup_required
from controllers.web.error import InvalidArgumentError, NotFoundError
from core.variables.segment_group import SegmentGroup
from core.variables.segments import ArrayFileSegment, FileSegment, Segment
from core.variables.types import SegmentType
from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
from factories.file_factory import build_from_mapping, build_from_mappings
from factories.variable_factory import build_segment_with_type
from libs.login import current_user, login_required
from models import App, AppMode, db
from models.workflow import WorkflowDraftVariable
from services.workflow_draft_variable_service import WorkflowDraftVariableList, WorkflowDraftVariableService
from services.workflow_service import WorkflowService
logger = logging.getLogger(__name__)
def _convert_values_to_json_serializable_object(value: Segment) -> Any:
if isinstance(value, FileSegment):
return value.value.model_dump()
elif isinstance(value, ArrayFileSegment):
return [i.model_dump() for i in value.value]
elif isinstance(value, SegmentGroup):
return [_convert_values_to_json_serializable_object(i) for i in value.value]
else:
return value.value
def _serialize_var_value(variable: WorkflowDraftVariable) -> Any:
value = variable.get_value()
# create a copy of the value to avoid affecting the model cache.
value = value.model_copy(deep=True)
# Refresh the url signature before returning it to client.
if isinstance(value, FileSegment):
file = value.value
file.remote_url = file.generate_url()
elif isinstance(value, ArrayFileSegment):
files = value.value
for file in files:
file.remote_url = file.generate_url()
return _convert_values_to_json_serializable_object(value)
def _create_pagination_parser():
parser = reqparse.RequestParser()
parser.add_argument(
"page",
type=inputs.int_range(1, 100_000),
required=False,
default=1,
location="args",
help="the page of data requested",
)
parser.add_argument("limit", type=inputs.int_range(1, 100), required=False, default=20, location="args")
return parser
_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS = {
"id": fields.String,
"type": fields.String(attribute=lambda model: model.get_variable_type()),
"name": fields.String,
"description": fields.String,
"selector": fields.List(fields.String, attribute=lambda model: model.get_selector()),
"value_type": fields.String,
"edited": fields.Boolean(attribute=lambda model: model.edited),
"visible": fields.Boolean,
}
_WORKFLOW_DRAFT_VARIABLE_FIELDS = dict(
_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,
value=fields.Raw(attribute=_serialize_var_value),
)
_WORKFLOW_DRAFT_ENV_VARIABLE_FIELDS = {
"id": fields.String,
"type": fields.String(attribute=lambda _: "env"),
"name": fields.String,
"description": fields.String,
"selector": fields.List(fields.String, attribute=lambda model: model.get_selector()),
"value_type": fields.String,
"edited": fields.Boolean(attribute=lambda model: model.edited),
"visible": fields.Boolean,
}
_WORKFLOW_DRAFT_ENV_VARIABLE_LIST_FIELDS = {
"items": fields.List(fields.Nested(_WORKFLOW_DRAFT_ENV_VARIABLE_FIELDS)),
}
def _get_items(var_list: WorkflowDraftVariableList) -> list[WorkflowDraftVariable]:
return var_list.variables
_WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS = {
"items": fields.List(fields.Nested(_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS), attribute=_get_items),
"total": fields.Raw(),
}
_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS = {
"items": fields.List(fields.Nested(_WORKFLOW_DRAFT_VARIABLE_FIELDS), attribute=_get_items),
}
def _api_prerequisite(f):
"""Common prerequisites for all draft workflow variable APIs.
It ensures the following conditions are satisfied:
- Dify has been property setup.
- The request user has logged in and initialized.
- The requested app is a workflow or a chat flow.
- The request user has the edit permission for the app.
"""
@setup_required
@login_required
@account_initialization_required
@get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
def wrapper(*args, **kwargs):
if not current_user.is_editor:
raise Forbidden()
return f(*args, **kwargs)
return wrapper
class WorkflowVariableCollectionApi(Resource):
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS)
def get(self, app_model: App):
"""
Get draft workflow
"""
parser = _create_pagination_parser()
args = parser.parse_args()
# fetch draft workflow by app_model
workflow_service = WorkflowService()
workflow_exist = workflow_service.is_workflow_exist(app_model=app_model)
if not workflow_exist:
raise DraftWorkflowNotExist()
# fetch draft workflow by app_model
with Session(bind=db.engine, expire_on_commit=False) as session:
draft_var_srv = WorkflowDraftVariableService(
session=session,
)
workflow_vars = draft_var_srv.list_variables_without_values(
app_id=app_model.id,
page=args.page,
limit=args.limit,
)
return workflow_vars
@_api_prerequisite
def delete(self, app_model: App):
draft_var_srv = WorkflowDraftVariableService(
session=db.session(),
)
draft_var_srv.delete_workflow_variables(app_model.id)
db.session.commit()
return Response("", 204)
def validate_node_id(node_id: str) -> NoReturn | None:
if node_id in [
CONVERSATION_VARIABLE_NODE_ID,
SYSTEM_VARIABLE_NODE_ID,
]:
# NOTE(QuantumGhost): While we store the system and conversation variables as node variables
# with specific `node_id` in database, we still want to make the API separated. By disallowing
# accessing system and conversation variables in `WorkflowDraftNodeVariableListApi`,
# we mitigate the risk that user of the API depending on the implementation detail of the API.
#
# ref: [Hyrum's Law](https://www.hyrumslaw.com/)
raise InvalidArgumentError(
f"invalid node_id, please use correspond api for conversation and system variables, node_id={node_id}",
)
return None
class NodeVariableCollectionApi(Resource):
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
def get(self, app_model: App, node_id: str):
validate_node_id(node_id)
with Session(bind=db.engine, expire_on_commit=False) as session:
draft_var_srv = WorkflowDraftVariableService(
session=session,
)
node_vars = draft_var_srv.list_node_variables(app_model.id, node_id)
return node_vars
@_api_prerequisite
def delete(self, app_model: App, node_id: str):
validate_node_id(node_id)
srv = WorkflowDraftVariableService(db.session())
srv.delete_node_variables(app_model.id, node_id)
db.session.commit()
return Response("", 204)
class VariableApi(Resource):
_PATCH_NAME_FIELD = "name"
_PATCH_VALUE_FIELD = "value"
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
def get(self, app_model: App, variable_id: str):
draft_var_srv = WorkflowDraftVariableService(
session=db.session(),
)
variable = draft_var_srv.get_variable(variable_id=variable_id)
if variable is None:
raise NotFoundError(description=f"variable not found, id={variable_id}")
if variable.app_id != app_model.id:
raise NotFoundError(description=f"variable not found, id={variable_id}")
return variable
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
def patch(self, app_model: App, variable_id: str):
# Request payload for file types:
#
# Local File:
#
# {
# "type": "image",
# "transfer_method": "local_file",
# "url": "",
# "upload_file_id": "daded54f-72c7-4f8e-9d18-9b0abdd9f190"
# }
#
# Remote File:
#
#
# {
# "type": "image",
# "transfer_method": "remote_url",
# "url": "http://127.0.0.1:5001/files/1602650a-4fe4-423c-85a2-af76c083e3c4/file-preview?timestamp=1750041099&nonce=...&sign=...=",
# "upload_file_id": "1602650a-4fe4-423c-85a2-af76c083e3c4"
# }
parser = reqparse.RequestParser()
parser.add_argument(self._PATCH_NAME_FIELD, type=str, required=False, nullable=True, location="json")
# Parse 'value' field as-is to maintain its original data structure
parser.add_argument(self._PATCH_VALUE_FIELD, type=lambda x: x, required=False, nullable=True, location="json")
draft_var_srv = WorkflowDraftVariableService(
session=db.session(),
)
args = parser.parse_args(strict=True)
variable = draft_var_srv.get_variable(variable_id=variable_id)
if variable is None:
raise NotFoundError(description=f"variable not found, id={variable_id}")
if variable.app_id != app_model.id:
raise NotFoundError(description=f"variable not found, id={variable_id}")
new_name = args.get(self._PATCH_NAME_FIELD, None)
raw_value = args.get(self._PATCH_VALUE_FIELD, None)
if new_name is None and raw_value is None:
return variable
new_value = None
if raw_value is not None:
if variable.value_type == SegmentType.FILE:
if not isinstance(raw_value, dict):
raise InvalidArgumentError(description=f"expected dict for file, got {type(raw_value)}")
raw_value = build_from_mapping(mapping=raw_value, tenant_id=app_model.tenant_id)
elif variable.value_type == SegmentType.ARRAY_FILE:
if not isinstance(raw_value, list):
raise InvalidArgumentError(description=f"expected list for files, got {type(raw_value)}")
if len(raw_value) > 0 and not isinstance(raw_value[0], dict):
raise InvalidArgumentError(description=f"expected dict for files[0], got {type(raw_value)}")
raw_value = build_from_mappings(mappings=raw_value, tenant_id=app_model.tenant_id)
new_value = build_segment_with_type(variable.value_type, raw_value)
draft_var_srv.update_variable(variable, name=new_name, value=new_value)
db.session.commit()
return variable
@_api_prerequisite
def delete(self, app_model: App, variable_id: str):
draft_var_srv = WorkflowDraftVariableService(
session=db.session(),
)
variable = draft_var_srv.get_variable(variable_id=variable_id)
if variable is None:
raise NotFoundError(description=f"variable not found, id={variable_id}")
if variable.app_id != app_model.id:
raise NotFoundError(description=f"variable not found, id={variable_id}")
draft_var_srv.delete_variable(variable)
db.session.commit()
return Response("", 204)
class VariableResetApi(Resource):
@_api_prerequisite
def put(self, app_model: App, variable_id: str):
draft_var_srv = WorkflowDraftVariableService(
session=db.session(),
)
workflow_srv = WorkflowService()
draft_workflow = workflow_srv.get_draft_workflow(app_model)
if draft_workflow is None:
raise NotFoundError(
f"Draft workflow not found, app_id={app_model.id}",
)
variable = draft_var_srv.get_variable(variable_id=variable_id)
if variable is None:
raise NotFoundError(description=f"variable not found, id={variable_id}")
if variable.app_id != app_model.id:
raise NotFoundError(description=f"variable not found, id={variable_id}")
resetted = draft_var_srv.reset_variable(draft_workflow, variable)
db.session.commit()
if resetted is None:
return Response("", 204)
else:
return marshal(resetted, _WORKFLOW_DRAFT_VARIABLE_FIELDS)
def _get_variable_list(app_model: App, node_id) -> WorkflowDraftVariableList:
with Session(bind=db.engine, expire_on_commit=False) as session:
draft_var_srv = WorkflowDraftVariableService(
session=session,
)
if node_id == CONVERSATION_VARIABLE_NODE_ID:
draft_vars = draft_var_srv.list_conversation_variables(app_model.id)
elif node_id == SYSTEM_VARIABLE_NODE_ID:
draft_vars = draft_var_srv.list_system_variables(app_model.id)
else:
draft_vars = draft_var_srv.list_node_variables(app_id=app_model.id, node_id=node_id)
return draft_vars
class ConversationVariableCollectionApi(Resource):
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
def get(self, app_model: App):
# NOTE(QuantumGhost): Prefill conversation variables into the draft variables table
# so their IDs can be returned to the caller.
workflow_srv = WorkflowService()
draft_workflow = workflow_srv.get_draft_workflow(app_model)
if draft_workflow is None:
raise NotFoundError(description=f"draft workflow not found, id={app_model.id}")
draft_var_srv = WorkflowDraftVariableService(db.session())
draft_var_srv.prefill_conversation_variable_default_values(draft_workflow)
db.session.commit()
return _get_variable_list(app_model, CONVERSATION_VARIABLE_NODE_ID)
class SystemVariableCollectionApi(Resource):
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
def get(self, app_model: App):
return _get_variable_list(app_model, SYSTEM_VARIABLE_NODE_ID)
class EnvironmentVariableCollectionApi(Resource):
@_api_prerequisite
def get(self, app_model: App):
"""
Get draft workflow
"""
# fetch draft workflow by app_model
workflow_service = WorkflowService()
workflow = workflow_service.get_draft_workflow(app_model=app_model)
if workflow is None:
raise DraftWorkflowNotExist()
env_vars = workflow.environment_variables
env_vars_list = []
for v in env_vars:
env_vars_list.append(
{
"id": v.id,
"type": "env",
"name": v.name,
"description": v.description,
"selector": v.selector,
"value_type": v.value_type.value,
"value": v.value,
# Do not track edited for env vars.
"edited": False,
"visible": True,
"editable": True,
}
)
return {"items": env_vars_list}
api.add_resource(
WorkflowVariableCollectionApi,
"/apps/<uuid:app_id>/workflows/draft/variables",
)
api.add_resource(NodeVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/variables")
api.add_resource(VariableApi, "/apps/<uuid:app_id>/workflows/draft/variables/<uuid:variable_id>")
api.add_resource(VariableResetApi, "/apps/<uuid:app_id>/workflows/draft/variables/<uuid:variable_id>/reset")
api.add_resource(ConversationVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/conversation-variables")
api.add_resource(SystemVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/system-variables")
api.add_resource(EnvironmentVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/environment-variables")

View File

@ -8,6 +8,15 @@ from libs.login import current_user
from models import App, AppMode
def _load_app_model(app_id: str) -> Optional[App]:
app_model = (
db.session.query(App)
.filter(App.id == app_id, App.tenant_id == current_user.current_tenant_id, App.status == "normal")
.first()
)
return app_model
def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[AppMode], None] = None):
def decorator(view_func):
@wraps(view_func)
@ -20,11 +29,7 @@ def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[
del kwargs["app_id"]
app_model = (
db.session.query(App)
.filter(App.id == app_id, App.tenant_id == current_user.current_tenant_id, App.status == "normal")
.first()
)
app_model = _load_app_model(app_id)
if not app_model:
raise AppNotFoundError()

View File

@ -6,7 +6,7 @@ from typing import cast
from flask import request
from flask_login import current_user
from flask_restful import Resource, fields, marshal, marshal_with, reqparse
from flask_restful import Resource, marshal, marshal_with, reqparse
from sqlalchemy import asc, desc, select
from werkzeug.exceptions import Forbidden, NotFound
@ -44,7 +44,6 @@ 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,
@ -56,8 +55,6 @@ from models import Dataset, DatasetProcessRule, Document, DocumentSegment, Uploa
from models.dataset import DocumentPipelineExecutionLog
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):
@ -244,12 +241,10 @@ class DatasetDocumentListApi(Resource):
return response
documents_and_batch_fields = {"documents": fields.List(fields.Nested(document_fields)), "batch": fields.String}
@setup_required
@login_required
@account_initialization_required
@marshal_with(documents_and_batch_fields)
@marshal_with(dataset_and_document_fields)
@cloud_edition_billing_resource_check("vector_space")
@cloud_edition_billing_rate_limit_check("knowledge")
def post(self, dataset_id):
@ -295,6 +290,8 @@ class DatasetDocumentListApi(Resource):
try:
documents, batch = DocumentService.save_document_with_dataset_id(dataset, knowledge_config, current_user)
dataset = DatasetService.get_dataset(dataset_id)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
except QuotaExceededError:
@ -302,7 +299,7 @@ class DatasetDocumentListApi(Resource):
except ModelCurrentlyNotSupportError:
raise ProviderModelCurrentlyNotSupportError()
return {"documents": documents, "batch": batch}
return {"dataset": dataset, "documents": documents, "batch": batch}
@setup_required
@login_required
@ -864,77 +861,16 @@ 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

View File

@ -15,7 +15,7 @@ class LoadBalancingCredentialsValidateApi(Resource):
@login_required
@account_initialization_required
def post(self, provider: str):
if not TenantAccountRole.is_privileged_role(current_user.current_tenant.current_role):
if not TenantAccountRole.is_privileged_role(current_user.current_role):
raise Forbidden()
tenant_id = current_user.current_tenant_id
@ -64,7 +64,7 @@ class LoadBalancingConfigCredentialsValidateApi(Resource):
@login_required
@account_initialization_required
def post(self, provider: str, config_id: str):
if not TenantAccountRole.is_privileged_role(current_user.current_tenant.current_role):
if not TenantAccountRole.is_privileged_role(current_user.current_role):
raise Forbidden()
tenant_id = current_user.current_tenant_id

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")

View File

@ -139,3 +139,13 @@ class InvokeRateLimitError(BaseHTTPException):
error_code = "rate_limit_error"
description = "Rate Limit Error"
code = 429
class NotFoundError(BaseHTTPException):
error_code = "not_found"
code = 404
class InvalidArgumentError(BaseHTTPException):
error_code = "invalid_param"
code = 400