Merge branch 'main' into feat/r2

# Conflicts:
#	api/core/repositories/sqlalchemy_workflow_node_execution_repository.py
#	api/core/workflow/entities/node_entities.py
#	api/core/workflow/enums.py

api/controllers/console/app/workflow_app_log.py

@@ -6,12 +6,12 @@ from sqlalchemy.orm import Session
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
+from core.workflow.entities.workflow_execution import WorkflowExecutionStatus
 from extensions.ext_database import db
 from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs.login import login_required
 from models import App
 from models.model import AppMode
-from models.workflow import WorkflowRunStatus
 from services.workflow_app_service import WorkflowAppService
 
 
@@ -38,7 +38,7 @@ class WorkflowAppLogApi(Resource):
         parser.add_argument("limit", type=int_range(1, 100), default=20, location="args")
         args = parser.parse_args()
 
-        args.status = WorkflowRunStatus(args.status) if args.status else None
+        args.status = WorkflowExecutionStatus(args.status) if args.status else None
         if args.created_at__before:
             args.created_at__before = isoparse(args.created_at__before)
 

api/controllers/service_api/app/workflow.py

@@ -24,12 +24,13 @@ from core.errors.error import (
     QuotaExceededError,
 )
 from core.model_runtime.errors.invoke import InvokeError
+from core.workflow.entities.workflow_execution import WorkflowExecutionStatus
 from extensions.ext_database import db
 from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs import helper
 from libs.helper import TimestampField
 from models.model import App, AppMode, EndUser
-from models.workflow import WorkflowRun, WorkflowRunStatus
+from models.workflow import WorkflowRun
 from services.app_generate_service import AppGenerateService
 from services.errors.llm import InvokeRateLimitError
 from services.workflow_app_service import WorkflowAppService
@@ -138,7 +139,7 @@ class WorkflowAppLogApi(Resource):
         parser.add_argument("limit", type=int_range(1, 100), default=20, location="args")
         args = parser.parse_args()
 
-        args.status = WorkflowRunStatus(args.status) if args.status else None
+        args.status = WorkflowExecutionStatus(args.status) if args.status else None
         if args.created_at__before:
             args.created_at__before = isoparse(args.created_at__before)
 

api/controllers/service_api/dataset/dataset.py

@@ -1,19 +1,21 @@
 from flask import request
-from flask_restful import marshal, reqparse
+from flask_restful import marshal, marshal_with, reqparse
 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.wraps import DatasetApiResource
+from controllers.service_api.wraps import DatasetApiResource, validate_dataset_token
 from core.model_runtime.entities.model_entities import ModelType
 from core.plugin.entities.plugin import ModelProviderID
 from core.provider_manager import ProviderManager
 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.entities.knowledge_entities.knowledge_entities import RetrievalModel
+from services.tag_service import TagService
 
 
 def _validate_name(name):
@@ -320,5 +322,134 @@ class DatasetApi(DatasetApiResource):
             raise DatasetInUseError()
 
 
+class DatasetTagsApi(DatasetApiResource):
+    @validate_dataset_token
+    @marshal_with(tag_fields)
+    def get(self, _, dataset_id):
+        """Get all knowledge type tags."""
+        tags = TagService.get_tags("knowledge", current_user.current_tenant_id)
+
+        return tags, 200
+
+    @validate_dataset_token
+    def post(self, _, dataset_id):
+        """Add a knowledge type tag."""
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="Name must be between 1 to 50 characters.",
+            type=DatasetTagsApi._validate_tag_name,
+        )
+
+        args = parser.parse_args()
+        args["type"] = "knowledge"
+        tag = TagService.save_tags(args)
+
+        response = {"id": tag.id, "name": tag.name, "type": tag.type, "binding_count": 0}
+
+        return response, 200
+
+    @validate_dataset_token
+    def patch(self, _, dataset_id):
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="Name must be between 1 to 50 characters.",
+            type=DatasetTagsApi._validate_tag_name,
+        )
+        parser.add_argument("tag_id", nullable=False, required=True, help="Id of a tag.", type=str)
+        args = parser.parse_args()
+        tag = TagService.update_tags(args, args.get("tag_id"))
+
+        binding_count = TagService.get_tag_binding_count(args.get("tag_id"))
+
+        response = {"id": tag.id, "name": tag.name, "type": tag.type, "binding_count": binding_count}
+
+        return response, 200
+
+    @validate_dataset_token
+    def delete(self, _, dataset_id):
+        """Delete a knowledge type tag."""
+        if not current_user.is_editor:
+            raise Forbidden()
+        parser = reqparse.RequestParser()
+        parser.add_argument("tag_id", nullable=False, required=True, help="Id of a tag.", type=str)
+        args = parser.parse_args()
+        TagService.delete_tag(args.get("tag_id"))
+
+        return 204
+
+    @staticmethod
+    def _validate_tag_name(name):
+        if not name or len(name) < 1 or len(name) > 50:
+            raise ValueError("Name must be between 1 to 50 characters.")
+        return name
+
+
+class DatasetTagBindingApi(DatasetApiResource):
+    @validate_dataset_token
+    def post(self, _, dataset_id):
+        # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "tag_ids", type=list, nullable=False, required=True, location="json", help="Tag IDs is required."
+        )
+        parser.add_argument(
+            "target_id", type=str, nullable=False, required=True, location="json", help="Target Dataset ID is required."
+        )
+
+        args = parser.parse_args()
+        args["type"] = "knowledge"
+        TagService.save_tag_binding(args)
+
+        return 204
+
+
+class DatasetTagUnbindingApi(DatasetApiResource):
+    @validate_dataset_token
+    def post(self, _, dataset_id):
+        # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("tag_id", type=str, nullable=False, required=True, help="Tag ID is required.")
+        parser.add_argument("target_id", type=str, nullable=False, required=True, help="Target ID is required.")
+
+        args = parser.parse_args()
+        args["type"] = "knowledge"
+        TagService.delete_tag_binding(args)
+
+        return 204
+
+
+class DatasetTagsBindingStatusApi(DatasetApiResource):
+    @validate_dataset_token
+    def get(self, _, *args, **kwargs):
+        """Get all knowledge type tags."""
+        dataset_id = kwargs.get("dataset_id")
+        tags = TagService.get_tags_by_target_id("knowledge", current_user.current_tenant_id, str(dataset_id))
+        tags_list = [{"id": tag.id, "name": tag.name} for tag in tags]
+        response = {"data": tags_list, "total": len(tags)}
+        return response, 200
+
+
 api.add_resource(DatasetListApi, "/datasets")
 api.add_resource(DatasetApi, "/datasets/<uuid:dataset_id>")
+api.add_resource(DatasetTagsApi, "/datasets/tags")
+api.add_resource(DatasetTagBindingApi, "/datasets/tags/binding")
+api.add_resource(DatasetTagUnbindingApi, "/datasets/tags/unbinding")
+api.add_resource(DatasetTagsBindingStatusApi, "/datasets/<uuid:dataset_id>/tags")

api/controllers/service_api/dataset/segment.py

@@ -208,6 +208,28 @@ class DatasetSegmentApi(DatasetApiResource):
         )
         return {"data": marshal(updated_segment, segment_fields), "doc_form": document.doc_form}, 200
 
+    def get(self, tenant_id, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        # check segment
+        segment_id = str(segment_id)
+        segment = SegmentService.get_segment_by_id(segment_id=segment_id, tenant_id=current_user.current_tenant_id)
+        if not segment:
+            raise NotFound("Segment not found.")
+
+        return {"data": marshal(segment, segment_fields), "doc_form": document.doc_form}, 200
+
 
 class ChildChunkApi(DatasetApiResource):
     """Resource for child chunks."""