Initial commit

dify_0.15.3/api/controllers/console/datasets/data_source.py

@@ -0,0 +1,268 @@
+import datetime
+import json
+
+from flask import request
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from werkzeug.exceptions import NotFound
+
+from controllers.console import api
+from controllers.console.wraps import account_initialization_required, setup_required
+from core.indexing_runner import IndexingRunner
+from core.rag.extractor.entity.extract_setting import ExtractSetting
+from core.rag.extractor.notion_extractor import NotionExtractor
+from extensions.ext_database import db
+from fields.data_source_fields import integrate_list_fields, integrate_notion_info_list_fields
+from libs.login import login_required
+from models import DataSourceOauthBinding, Document
+from services.dataset_service import DatasetService, DocumentService
+from tasks.document_indexing_sync_task import document_indexing_sync_task
+
+
+class DataSourceApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(integrate_list_fields)
+    def get(self):
+        # get workspace data source integrates
+        data_source_integrates = (
+            db.session.query(DataSourceOauthBinding)
+            .filter(
+                DataSourceOauthBinding.tenant_id == current_user.current_tenant_id,
+                DataSourceOauthBinding.disabled == False,
+            )
+            .all()
+        )
+
+        base_url = request.url_root.rstrip("/")
+        data_source_oauth_base_path = "/console/api/oauth/data-source"
+        providers = ["notion"]
+
+        integrate_data = []
+        for provider in providers:
+            # existing_integrate = next((ai for ai in data_source_integrates if ai.provider == provider), None)
+            existing_integrates = filter(lambda item: item.provider == provider, data_source_integrates)
+            if existing_integrates:
+                for existing_integrate in list(existing_integrates):
+                    integrate_data.append(
+                        {
+                            "id": existing_integrate.id,
+                            "provider": provider,
+                            "created_at": existing_integrate.created_at,
+                            "is_bound": True,
+                            "disabled": existing_integrate.disabled,
+                            "source_info": existing_integrate.source_info,
+                            "link": f"{base_url}{data_source_oauth_base_path}/{provider}",
+                        }
+                    )
+            else:
+                integrate_data.append(
+                    {
+                        "id": None,
+                        "provider": provider,
+                        "created_at": None,
+                        "source_info": None,
+                        "is_bound": False,
+                        "disabled": None,
+                        "link": f"{base_url}{data_source_oauth_base_path}/{provider}",
+                    }
+                )
+        return {"data": integrate_data}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def patch(self, binding_id, action):
+        binding_id = str(binding_id)
+        action = str(action)
+        data_source_binding = DataSourceOauthBinding.query.filter_by(id=binding_id).first()
+        if data_source_binding is None:
+            raise NotFound("Data source binding not found.")
+        # enable binding
+        if action == "enable":
+            if data_source_binding.disabled:
+                data_source_binding.disabled = False
+                data_source_binding.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
+                db.session.add(data_source_binding)
+                db.session.commit()
+            else:
+                raise ValueError("Data source is not disabled.")
+        # disable binding
+        if action == "disable":
+            if not data_source_binding.disabled:
+                data_source_binding.disabled = True
+                data_source_binding.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
+                db.session.add(data_source_binding)
+                db.session.commit()
+            else:
+                raise ValueError("Data source is disabled.")
+        return {"result": "success"}, 200
+
+
+class DataSourceNotionListApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(integrate_notion_info_list_fields)
+    def get(self):
+        dataset_id = request.args.get("dataset_id", default=None, type=str)
+        exist_page_ids = []
+        # import notion in the exist dataset
+        if dataset_id:
+            dataset = DatasetService.get_dataset(dataset_id)
+            if not dataset:
+                raise NotFound("Dataset not found.")
+            if dataset.data_source_type != "notion_import":
+                raise ValueError("Dataset is not notion type.")
+            documents = Document.query.filter_by(
+                dataset_id=dataset_id,
+                tenant_id=current_user.current_tenant_id,
+                data_source_type="notion_import",
+                enabled=True,
+            ).all()
+            if documents:
+                for document in documents:
+                    data_source_info = json.loads(document.data_source_info)
+                    exist_page_ids.append(data_source_info["notion_page_id"])
+        # get all authorized pages
+        data_source_bindings = DataSourceOauthBinding.query.filter_by(
+            tenant_id=current_user.current_tenant_id, provider="notion", disabled=False
+        ).all()
+        if not data_source_bindings:
+            return {"notion_info": []}, 200
+        pre_import_info_list = []
+        for data_source_binding in data_source_bindings:
+            source_info = data_source_binding.source_info
+            pages = source_info["pages"]
+            # Filter out already bound pages
+            for page in pages:
+                if page["page_id"] in exist_page_ids:
+                    page["is_bound"] = True
+                else:
+                    page["is_bound"] = False
+            pre_import_info = {
+                "workspace_name": source_info["workspace_name"],
+                "workspace_icon": source_info["workspace_icon"],
+                "workspace_id": source_info["workspace_id"],
+                "pages": pages,
+            }
+            pre_import_info_list.append(pre_import_info)
+        return {"notion_info": pre_import_info_list}, 200
+
+
+class DataSourceNotionApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, workspace_id, page_id, page_type):
+        workspace_id = str(workspace_id)
+        page_id = str(page_id)
+        data_source_binding = DataSourceOauthBinding.query.filter(
+            db.and_(
+                DataSourceOauthBinding.tenant_id == current_user.current_tenant_id,
+                DataSourceOauthBinding.provider == "notion",
+                DataSourceOauthBinding.disabled == False,
+                DataSourceOauthBinding.source_info["workspace_id"] == f'"{workspace_id}"',
+            )
+        ).first()
+        if not data_source_binding:
+            raise NotFound("Data source binding not found.")
+
+        extractor = NotionExtractor(
+            notion_workspace_id=workspace_id,
+            notion_obj_id=page_id,
+            notion_page_type=page_type,
+            notion_access_token=data_source_binding.access_token,
+            tenant_id=current_user.current_tenant_id,
+        )
+
+        text_docs = extractor.extract()
+        return {"content": "\n".join([doc.page_content for doc in text_docs])}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("notion_info_list", type=list, required=True, nullable=True, location="json")
+        parser.add_argument("process_rule", type=dict, required=True, nullable=True, location="json")
+        parser.add_argument("doc_form", type=str, default="text_model", required=False, nullable=False, location="json")
+        parser.add_argument(
+            "doc_language", type=str, default="English", required=False, nullable=False, location="json"
+        )
+        args = parser.parse_args()
+        # validate args
+        DocumentService.estimate_args_validate(args)
+        notion_info_list = args["notion_info_list"]
+        extract_settings = []
+        for notion_info in notion_info_list:
+            workspace_id = notion_info["workspace_id"]
+            for page in notion_info["pages"]:
+                extract_setting = ExtractSetting(
+                    datasource_type="notion_import",
+                    notion_info={
+                        "notion_workspace_id": workspace_id,
+                        "notion_obj_id": page["page_id"],
+                        "notion_page_type": page["type"],
+                        "tenant_id": current_user.current_tenant_id,
+                    },
+                    document_model=args["doc_form"],
+                )
+                extract_settings.append(extract_setting)
+        indexing_runner = IndexingRunner()
+        response = indexing_runner.indexing_estimate(
+            current_user.current_tenant_id,
+            extract_settings,
+            args["process_rule"],
+            args["doc_form"],
+            args["doc_language"],
+        )
+        return response.model_dump(), 200
+
+
+class DataSourceNotionDatasetSyncApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        documents = DocumentService.get_document_by_dataset_id(dataset_id_str)
+        for document in documents:
+            document_indexing_sync_task.delay(dataset_id_str, document.id)
+        return 200
+
+
+class DataSourceNotionDocumentSyncApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, document_id):
+        dataset_id_str = str(dataset_id)
+        document_id_str = str(document_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        document = DocumentService.get_document(dataset_id_str, document_id_str)
+        if document is None:
+            raise NotFound("Document not found.")
+        document_indexing_sync_task.delay(dataset_id_str, document_id_str)
+        return 200
+
+
+api.add_resource(DataSourceApi, "/data-source/integrates", "/data-source/integrates/<uuid:binding_id>/<string:action>")
+api.add_resource(DataSourceNotionListApi, "/notion/pre-import/pages")
+api.add_resource(
+    DataSourceNotionApi,
+    "/notion/workspaces/<uuid:workspace_id>/pages/<uuid:page_id>/<string:page_type>/preview",
+    "/datasets/notion-indexing-estimate",
+)
+api.add_resource(DataSourceNotionDatasetSyncApi, "/datasets/<uuid:dataset_id>/notion/sync")
+api.add_resource(
+    DataSourceNotionDocumentSyncApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/notion/sync"
+)

dify_0.15.3/api/controllers/console/datasets/datasets.py

@@ -0,0 +1,763 @@
+import flask_restful  # type: ignore
+from flask import request
+from flask_login import current_user  # type: ignore  # type: ignore
+from flask_restful import Resource, marshal, marshal_with, reqparse  # type: ignore
+from werkzeug.exceptions import Forbidden, NotFound
+
+import services
+from configs import dify_config
+from controllers.console import api
+from controllers.console.apikey import api_key_fields, api_key_list
+from controllers.console.app.error import ProviderNotInitializeError
+from controllers.console.datasets.error import DatasetInUseError, DatasetNameDuplicateError, IndexingEstimateError
+from controllers.console.wraps import account_initialization_required, enterprise_license_required, setup_required
+from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
+from core.indexing_runner import IndexingRunner
+from core.model_runtime.entities.model_entities import ModelType
+from core.provider_manager import ProviderManager
+from core.rag.datasource.vdb.vector_type import VectorType
+from core.rag.extractor.entity.extract_setting import ExtractSetting
+from core.rag.retrieval.retrieval_methods import RetrievalMethod
+from extensions.ext_database import db
+from fields.app_fields import related_app_list
+from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
+from fields.document_fields import document_status_fields
+from libs.login import login_required
+from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
+from models.dataset import DatasetPermissionEnum
+from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
+
+
+def _validate_name(name):
+    if not name or len(name) < 1 or len(name) > 40:
+        raise ValueError("Name must be between 1 to 40 characters.")
+    return name
+
+
+def _validate_description_length(description):
+    if len(description) > 400:
+        raise ValueError("Description cannot exceed 400 characters.")
+    return description
+
+
+class DatasetListApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def get(self):
+        page = request.args.get("page", default=1, type=int)
+        limit = request.args.get("limit", default=20, type=int)
+        ids = request.args.getlist("ids")
+        # provider = request.args.get("provider", default="vendor")
+        search = request.args.get("keyword", default=None, type=str)
+        tag_ids = request.args.getlist("tag_ids")
+        include_all = request.args.get("include_all", default="false").lower() == "true"
+        if ids:
+            datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
+        else:
+            datasets, total = DatasetService.get_datasets(
+                page, limit, current_user.current_tenant_id, current_user, search, tag_ids, include_all
+            )
+
+        # check embedding setting
+        provider_manager = ProviderManager()
+        configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)
+
+        embedding_models = configurations.get_models(model_type=ModelType.TEXT_EMBEDDING, only_active=True)
+
+        model_names = []
+        for embedding_model in embedding_models:
+            model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")
+
+        data = marshal(datasets, dataset_detail_fields)
+        for item in data:
+            if item["indexing_technique"] == "high_quality":
+                item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}"
+                if item_model in model_names:
+                    item["embedding_available"] = True
+                else:
+                    item["embedding_available"] = False
+            else:
+                item["embedding_available"] = True
+
+            if item.get("permission") == "partial_members":
+                part_users_list = DatasetPermissionService.get_dataset_partial_member_list(item["id"])
+                item.update({"partial_member_list": part_users_list})
+            else:
+                item.update({"partial_member_list": []})
+
+        response = {"data": data, "has_more": len(datasets) == limit, "limit": limit, "total": total, "page": page}
+        return response, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="type is required. Name must be between 1 to 40 characters.",
+            type=_validate_name,
+        )
+        parser.add_argument(
+            "description",
+            type=str,
+            nullable=True,
+            required=False,
+            default="",
+        )
+        parser.add_argument(
+            "indexing_technique",
+            type=str,
+            location="json",
+            choices=Dataset.INDEXING_TECHNIQUE_LIST,
+            nullable=True,
+            help="Invalid indexing technique.",
+        )
+        parser.add_argument(
+            "external_knowledge_api_id",
+            type=str,
+            nullable=True,
+            required=False,
+        )
+        parser.add_argument(
+            "provider",
+            type=str,
+            nullable=True,
+            choices=Dataset.PROVIDER_LIST,
+            required=False,
+            default="vendor",
+        )
+        parser.add_argument(
+            "external_knowledge_id",
+            type=str,
+            nullable=True,
+            required=False,
+        )
+        args = parser.parse_args()
+
+        # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
+        if not current_user.is_dataset_editor:
+            raise Forbidden()
+
+        try:
+            dataset = DatasetService.create_empty_dataset(
+                tenant_id=current_user.current_tenant_id,
+                name=args["name"],
+                description=args["description"],
+                indexing_technique=args["indexing_technique"],
+                account=current_user,
+                permission=DatasetPermissionEnum.ONLY_ME,
+                provider=args["provider"],
+                external_knowledge_api_id=args["external_knowledge_api_id"],
+                external_knowledge_id=args["external_knowledge_id"],
+            )
+        except services.errors.dataset.DatasetNameDuplicateError:
+            raise DatasetNameDuplicateError()
+
+        return marshal(dataset, dataset_detail_fields), 201
+
+
+class DatasetApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        data = marshal(dataset, dataset_detail_fields)
+        if data.get("permission") == "partial_members":
+            part_users_list = DatasetPermissionService.get_dataset_partial_member_list(dataset_id_str)
+            data.update({"partial_member_list": part_users_list})
+
+        # check embedding setting
+        provider_manager = ProviderManager()
+        configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)
+
+        embedding_models = configurations.get_models(model_type=ModelType.TEXT_EMBEDDING, only_active=True)
+
+        model_names = []
+        for embedding_model in embedding_models:
+            model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")
+
+        if data["indexing_technique"] == "high_quality":
+            item_model = f"{data['embedding_model']}:{data['embedding_model_provider']}"
+            if item_model in model_names:
+                data["embedding_available"] = True
+            else:
+                data["embedding_available"] = False
+        else:
+            data["embedding_available"] = True
+
+        if data.get("permission") == "partial_members":
+            part_users_list = DatasetPermissionService.get_dataset_partial_member_list(dataset_id_str)
+            data.update({"partial_member_list": part_users_list})
+
+        return data, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def patch(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            help="type is required. Name must be between 1 to 40 characters.",
+            type=_validate_name,
+        )
+        parser.add_argument("description", location="json", store_missing=False, type=_validate_description_length)
+        parser.add_argument(
+            "indexing_technique",
+            type=str,
+            location="json",
+            choices=Dataset.INDEXING_TECHNIQUE_LIST,
+            nullable=True,
+            help="Invalid indexing technique.",
+        )
+        parser.add_argument(
+            "permission",
+            type=str,
+            location="json",
+            choices=(DatasetPermissionEnum.ONLY_ME, DatasetPermissionEnum.ALL_TEAM, DatasetPermissionEnum.PARTIAL_TEAM),
+            help="Invalid permission.",
+        )
+        parser.add_argument("embedding_model", type=str, location="json", help="Invalid embedding model.")
+        parser.add_argument(
+            "embedding_model_provider", type=str, location="json", help="Invalid embedding model provider."
+        )
+        parser.add_argument("retrieval_model", type=dict, location="json", help="Invalid retrieval model.")
+        parser.add_argument("partial_member_list", type=list, location="json", help="Invalid parent user list.")
+
+        parser.add_argument(
+            "external_retrieval_model",
+            type=dict,
+            required=False,
+            nullable=True,
+            location="json",
+            help="Invalid external retrieval model.",
+        )
+
+        parser.add_argument(
+            "external_knowledge_id",
+            type=str,
+            required=False,
+            nullable=True,
+            location="json",
+            help="Invalid external knowledge id.",
+        )
+
+        parser.add_argument(
+            "external_knowledge_api_id",
+            type=str,
+            required=False,
+            nullable=True,
+            location="json",
+            help="Invalid external knowledge api id.",
+        )
+        args = parser.parse_args()
+        data = request.get_json()
+
+        # check embedding model setting
+        if data.get("indexing_technique") == "high_quality":
+            DatasetService.check_embedding_model_setting(
+                dataset.tenant_id, data.get("embedding_model_provider"), data.get("embedding_model")
+            )
+
+        # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
+        DatasetPermissionService.check_permission(
+            current_user, dataset, data.get("permission"), data.get("partial_member_list")
+        )
+
+        dataset = DatasetService.update_dataset(dataset_id_str, args, current_user)
+
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        result_data = marshal(dataset, dataset_detail_fields)
+        tenant_id = current_user.current_tenant_id
+
+        if data.get("partial_member_list") and data.get("permission") == "partial_members":
+            DatasetPermissionService.update_partial_member_list(
+                tenant_id, dataset_id_str, data.get("partial_member_list")
+            )
+        # clear partial member list when permission is only_me or all_team_members
+        elif (
+            data.get("permission") == DatasetPermissionEnum.ONLY_ME
+            or data.get("permission") == DatasetPermissionEnum.ALL_TEAM
+        ):
+            DatasetPermissionService.clear_partial_member_list(dataset_id_str)
+
+        partial_member_list = DatasetPermissionService.get_dataset_partial_member_list(dataset_id_str)
+        result_data.update({"partial_member_list": partial_member_list})
+
+        return result_data, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor or current_user.is_dataset_operator:
+            raise Forbidden()
+
+        try:
+            if DatasetService.delete_dataset(dataset_id_str, current_user):
+                DatasetPermissionService.clear_partial_member_list(dataset_id_str)
+                return {"result": "success"}, 204
+            else:
+                raise NotFound("Dataset not found.")
+        except services.errors.dataset.DatasetInUseError:
+            raise DatasetInUseError()
+
+
+class DatasetUseCheckApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+
+        dataset_is_using = DatasetService.dataset_use_check(dataset_id_str)
+        return {"is_using": dataset_is_using}, 200
+
+
+class DatasetQueryApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        page = request.args.get("page", default=1, type=int)
+        limit = request.args.get("limit", default=20, type=int)
+
+        dataset_queries, total = DatasetService.get_dataset_queries(dataset_id=dataset.id, page=page, per_page=limit)
+
+        response = {
+            "data": marshal(dataset_queries, dataset_query_detail_fields),
+            "has_more": len(dataset_queries) == limit,
+            "limit": limit,
+            "total": total,
+            "page": page,
+        }
+        return response, 200
+
+
+class DatasetIndexingEstimateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("info_list", type=dict, required=True, nullable=True, location="json")
+        parser.add_argument("process_rule", type=dict, required=True, nullable=True, location="json")
+        parser.add_argument(
+            "indexing_technique",
+            type=str,
+            required=True,
+            choices=Dataset.INDEXING_TECHNIQUE_LIST,
+            nullable=True,
+            location="json",
+        )
+        parser.add_argument("doc_form", type=str, default="text_model", required=False, nullable=False, location="json")
+        parser.add_argument("dataset_id", type=str, required=False, nullable=False, location="json")
+        parser.add_argument(
+            "doc_language", type=str, default="English", required=False, nullable=False, location="json"
+        )
+        args = parser.parse_args()
+        # validate args
+        DocumentService.estimate_args_validate(args)
+        extract_settings = []
+        if args["info_list"]["data_source_type"] == "upload_file":
+            file_ids = args["info_list"]["file_info_list"]["file_ids"]
+            file_details = (
+                db.session.query(UploadFile)
+                .filter(UploadFile.tenant_id == current_user.current_tenant_id, UploadFile.id.in_(file_ids))
+                .all()
+            )
+
+            if file_details is None:
+                raise NotFound("File not found.")
+
+            if file_details:
+                for file_detail in file_details:
+                    extract_setting = ExtractSetting(
+                        datasource_type="upload_file", upload_file=file_detail, document_model=args["doc_form"]
+                    )
+                    extract_settings.append(extract_setting)
+        elif args["info_list"]["data_source_type"] == "notion_import":
+            notion_info_list = args["info_list"]["notion_info_list"]
+            for notion_info in notion_info_list:
+                workspace_id = notion_info["workspace_id"]
+                for page in notion_info["pages"]:
+                    extract_setting = ExtractSetting(
+                        datasource_type="notion_import",
+                        notion_info={
+                            "notion_workspace_id": workspace_id,
+                            "notion_obj_id": page["page_id"],
+                            "notion_page_type": page["type"],
+                            "tenant_id": current_user.current_tenant_id,
+                        },
+                        document_model=args["doc_form"],
+                    )
+                    extract_settings.append(extract_setting)
+        elif args["info_list"]["data_source_type"] == "website_crawl":
+            website_info_list = args["info_list"]["website_info_list"]
+            for url in website_info_list["urls"]:
+                extract_setting = ExtractSetting(
+                    datasource_type="website_crawl",
+                    website_info={
+                        "provider": website_info_list["provider"],
+                        "job_id": website_info_list["job_id"],
+                        "url": url,
+                        "tenant_id": current_user.current_tenant_id,
+                        "mode": "crawl",
+                        "only_main_content": website_info_list["only_main_content"],
+                    },
+                    document_model=args["doc_form"],
+                )
+                extract_settings.append(extract_setting)
+        else:
+            raise ValueError("Data source type not support")
+        indexing_runner = IndexingRunner()
+        try:
+            response = indexing_runner.indexing_estimate(
+                current_user.current_tenant_id,
+                extract_settings,
+                args["process_rule"],
+                args["doc_form"],
+                args["doc_language"],
+                args["dataset_id"],
+                args["indexing_technique"],
+            )
+        except LLMBadRequestError:
+            raise ProviderNotInitializeError(
+                "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except Exception as e:
+            raise IndexingEstimateError(str(e))
+
+        return response.model_dump(), 200
+
+
+class DatasetRelatedAppListApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(related_app_list)
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        app_dataset_joins = DatasetService.get_related_apps(dataset.id)
+
+        related_apps = []
+        for app_dataset_join in app_dataset_joins:
+            app_model = app_dataset_join.app
+            if app_model:
+                related_apps.append(app_model)
+
+        return {"data": related_apps, "total": len(related_apps)}, 200
+
+
+class DatasetIndexingStatusApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id = str(dataset_id)
+        documents = (
+            db.session.query(Document)
+            .filter(Document.dataset_id == dataset_id, Document.tenant_id == current_user.current_tenant_id)
+            .all()
+        )
+        documents_status = []
+        for document in documents:
+            completed_segments = DocumentSegment.query.filter(
+                DocumentSegment.completed_at.isnot(None),
+                DocumentSegment.document_id == str(document.id),
+                DocumentSegment.status != "re_segment",
+            ).count()
+            total_segments = DocumentSegment.query.filter(
+                DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment"
+            ).count()
+            document.completed_segments = completed_segments
+            document.total_segments = total_segments
+            documents_status.append(marshal(document, document_status_fields))
+        data = {"data": documents_status}
+        return data
+
+
+class DatasetApiKeyApi(Resource):
+    max_keys = 10
+    token_prefix = "dataset-"
+    resource_type = "dataset"
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(api_key_list)
+    def get(self):
+        keys = (
+            db.session.query(ApiToken)
+            .filter(ApiToken.type == self.resource_type, ApiToken.tenant_id == current_user.current_tenant_id)
+            .all()
+        )
+        return {"items": keys}
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(api_key_fields)
+    def post(self):
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_admin_or_owner:
+            raise Forbidden()
+
+        current_key_count = (
+            db.session.query(ApiToken)
+            .filter(ApiToken.type == self.resource_type, ApiToken.tenant_id == current_user.current_tenant_id)
+            .count()
+        )
+
+        if current_key_count >= self.max_keys:
+            flask_restful.abort(
+                400,
+                message=f"Cannot create more than {self.max_keys} API keys for this resource type.",
+                code="max_keys_exceeded",
+            )
+
+        key = ApiToken.generate_api_key(self.token_prefix, 24)
+        api_token = ApiToken()
+        api_token.tenant_id = current_user.current_tenant_id
+        api_token.token = key
+        api_token.type = self.resource_type
+        db.session.add(api_token)
+        db.session.commit()
+        return api_token, 200
+
+
+class DatasetApiDeleteApi(Resource):
+    resource_type = "dataset"
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, api_key_id):
+        api_key_id = str(api_key_id)
+
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_admin_or_owner:
+            raise Forbidden()
+
+        key = (
+            db.session.query(ApiToken)
+            .filter(
+                ApiToken.tenant_id == current_user.current_tenant_id,
+                ApiToken.type == self.resource_type,
+                ApiToken.id == api_key_id,
+            )
+            .first()
+        )
+
+        if key is None:
+            flask_restful.abort(404, message="API key not found")
+
+        db.session.query(ApiToken).filter(ApiToken.id == api_key_id).delete()
+        db.session.commit()
+
+        return {"result": "success"}, 204
+
+
+class DatasetApiBaseUrlApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        return {"api_base_url": (dify_config.SERVICE_API_URL or request.host_url.rstrip("/")) + "/v1"}
+
+
+class DatasetRetrievalSettingApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        vector_type = dify_config.VECTOR_STORE
+        match vector_type:
+            case (
+                VectorType.RELYT
+                | VectorType.TIDB_VECTOR
+                | VectorType.CHROMA
+                | VectorType.TENCENT
+                | VectorType.PGVECTO_RS
+                | VectorType.BAIDU
+                | VectorType.VIKINGDB
+                | VectorType.UPSTASH
+                | VectorType.OCEANBASE
+            ):
+                return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
+            case (
+                VectorType.QDRANT
+                | VectorType.WEAVIATE
+                | VectorType.OPENSEARCH
+                | VectorType.ANALYTICDB
+                | VectorType.MYSCALE
+                | VectorType.ORACLE
+                | VectorType.ELASTICSEARCH
+                | VectorType.ELASTICSEARCH_JA
+                | VectorType.PGVECTOR
+                | VectorType.TIDB_ON_QDRANT
+                | VectorType.LINDORM
+                | VectorType.COUCHBASE
+                | VectorType.MILVUS
+            ):
+                return {
+                    "retrieval_method": [
+                        RetrievalMethod.SEMANTIC_SEARCH.value,
+                        RetrievalMethod.FULL_TEXT_SEARCH.value,
+                        RetrievalMethod.HYBRID_SEARCH.value,
+                    ]
+                }
+            case _:
+                raise ValueError(f"Unsupported vector db type {vector_type}.")
+
+
+class DatasetRetrievalSettingMockApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, vector_type):
+        match vector_type:
+            case (
+                VectorType.MILVUS
+                | VectorType.RELYT
+                | VectorType.TIDB_VECTOR
+                | VectorType.CHROMA
+                | VectorType.TENCENT
+                | VectorType.PGVECTO_RS
+                | VectorType.BAIDU
+                | VectorType.VIKINGDB
+                | VectorType.UPSTASH
+                | VectorType.OCEANBASE
+            ):
+                return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
+            case (
+                VectorType.QDRANT
+                | VectorType.WEAVIATE
+                | VectorType.OPENSEARCH
+                | VectorType.ANALYTICDB
+                | VectorType.MYSCALE
+                | VectorType.ORACLE
+                | VectorType.ELASTICSEARCH
+                | VectorType.ELASTICSEARCH_JA
+                | VectorType.COUCHBASE
+                | VectorType.PGVECTOR
+                | VectorType.LINDORM
+            ):
+                return {
+                    "retrieval_method": [
+                        RetrievalMethod.SEMANTIC_SEARCH.value,
+                        RetrievalMethod.FULL_TEXT_SEARCH.value,
+                        RetrievalMethod.HYBRID_SEARCH.value,
+                    ]
+                }
+            case _:
+                raise ValueError(f"Unsupported vector db type {vector_type}.")
+
+
+class DatasetErrorDocs(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        results = DocumentService.get_error_documents_by_dataset_id(dataset_id_str)
+
+        return {"data": [marshal(item, document_status_fields) for item in results], "total": len(results)}, 200
+
+
+class DatasetPermissionUserListApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        partial_members_list = DatasetPermissionService.get_dataset_partial_member_list(dataset_id_str)
+
+        return {
+            "data": partial_members_list,
+        }, 200
+
+
+class DatasetAutoDisableLogApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        return DatasetService.get_dataset_auto_disable_logs(dataset_id_str), 200
+
+
+api.add_resource(DatasetListApi, "/datasets")
+api.add_resource(DatasetApi, "/datasets/<uuid:dataset_id>")
+api.add_resource(DatasetUseCheckApi, "/datasets/<uuid:dataset_id>/use-check")
+api.add_resource(DatasetQueryApi, "/datasets/<uuid:dataset_id>/queries")
+api.add_resource(DatasetErrorDocs, "/datasets/<uuid:dataset_id>/error-docs")
+api.add_resource(DatasetIndexingEstimateApi, "/datasets/indexing-estimate")
+api.add_resource(DatasetRelatedAppListApi, "/datasets/<uuid:dataset_id>/related-apps")
+api.add_resource(DatasetIndexingStatusApi, "/datasets/<uuid:dataset_id>/indexing-status")
+api.add_resource(DatasetApiKeyApi, "/datasets/api-keys")
+api.add_resource(DatasetApiDeleteApi, "/datasets/api-keys/<uuid:api_key_id>")
+api.add_resource(DatasetApiBaseUrlApi, "/datasets/api-base-info")
+api.add_resource(DatasetRetrievalSettingApi, "/datasets/retrieval-setting")
+api.add_resource(DatasetRetrievalSettingMockApi, "/datasets/retrieval-setting/<string:vector_type>")
+api.add_resource(DatasetPermissionUserListApi, "/datasets/<uuid:dataset_id>/permission-part-users")
+api.add_resource(DatasetAutoDisableLogApi, "/datasets/<uuid:dataset_id>/auto-disable-logs")

dify_0.15.3/api/controllers/console/datasets/datasets_segments.py

@@ -0,0 +1,657 @@
+import uuid
+
+import pandas as pd
+from flask import request
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal, reqparse  # type: ignore
+from werkzeug.exceptions import Forbidden, NotFound
+
+import services
+from controllers.console import api
+from controllers.console.app.error import ProviderNotInitializeError
+from controllers.console.datasets.error import (
+    ChildChunkDeleteIndexError,
+    ChildChunkIndexingError,
+    InvalidActionError,
+    NoFileUploadedError,
+    TooManyFilesError,
+)
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_knowledge_limit_check,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
+from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
+from core.model_manager import ModelManager
+from core.model_runtime.entities.model_entities import ModelType
+from extensions.ext_redis import redis_client
+from fields.segment_fields import child_chunk_fields, segment_fields
+from libs.login import login_required
+from models.dataset import ChildChunk, DocumentSegment
+from services.dataset_service import DatasetService, DocumentService, SegmentService
+from services.entities.knowledge_entities.knowledge_entities import ChildChunkUpdateArgs, SegmentUpdateArgs
+from services.errors.chunk import ChildChunkDeleteIndexError as ChildChunkDeleteIndexServiceError
+from services.errors.chunk import ChildChunkIndexingError as ChildChunkIndexingServiceError
+from tasks.batch_create_segment_to_index_task import batch_create_segment_to_index_task
+
+
+class DatasetDocumentSegmentListApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, document_id):
+        dataset_id = str(dataset_id)
+        document_id = str(document_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        document = DocumentService.get_document(dataset_id, document_id)
+
+        if not document:
+            raise NotFound("Document not found.")
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("limit", type=int, default=20, location="args")
+        parser.add_argument("status", type=str, action="append", default=[], location="args")
+        parser.add_argument("hit_count_gte", type=int, default=None, location="args")
+        parser.add_argument("enabled", type=str, default="all", location="args")
+        parser.add_argument("keyword", type=str, default=None, location="args")
+        parser.add_argument("page", type=int, default=1, location="args")
+
+        args = parser.parse_args()
+
+        page = args["page"]
+        limit = min(args["limit"], 100)
+        status_list = args["status"]
+        hit_count_gte = args["hit_count_gte"]
+        keyword = args["keyword"]
+
+        query = DocumentSegment.query.filter(
+            DocumentSegment.document_id == str(document_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).order_by(DocumentSegment.position.asc())
+
+        if status_list:
+            query = query.filter(DocumentSegment.status.in_(status_list))
+
+        if hit_count_gte is not None:
+            query = query.filter(DocumentSegment.hit_count >= hit_count_gte)
+
+        if keyword:
+            query = query.where(DocumentSegment.content.ilike(f"%{keyword}%"))
+
+        if args["enabled"].lower() != "all":
+            if args["enabled"].lower() == "true":
+                query = query.filter(DocumentSegment.enabled == True)
+            elif args["enabled"].lower() == "false":
+                query = query.filter(DocumentSegment.enabled == False)
+
+        segments = query.paginate(page=page, per_page=limit, max_per_page=100, error_out=False)
+
+        response = {
+            "data": marshal(segments.items, segment_fields),
+            "limit": limit,
+            "total": segments.total,
+            "total_pages": segments.pages,
+            "page": page,
+        }
+        return response, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, dataset_id, document_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        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.")
+        segment_ids = request.args.getlist("segment_id")
+
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_editor:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        SegmentService.delete_segments(segment_ids, document, dataset)
+        return {"result": "success"}, 200
+
+
+class DatasetDocumentSegmentApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_resource_check("vector_space")
+    def patch(self, dataset_id, document_id, action):
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        if dataset.indexing_technique == "high_quality":
+            # check embedding model setting
+            try:
+                model_manager = ModelManager()
+                model_manager.get_model_instance(
+                    tenant_id=current_user.current_tenant_id,
+                    provider=dataset.embedding_model_provider,
+                    model_type=ModelType.TEXT_EMBEDDING,
+                    model=dataset.embedding_model,
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                )
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+        segment_ids = request.args.getlist("segment_id")
+
+        document_indexing_cache_key = "document_{}_indexing".format(document.id)
+        cache_result = redis_client.get(document_indexing_cache_key)
+        if cache_result is not None:
+            raise InvalidActionError("Document is being indexed, please try again later")
+        try:
+            SegmentService.update_segments_status(segment_ids, action, dataset, document)
+        except Exception as e:
+            raise InvalidActionError(str(e))
+        return {"result": "success"}, 200
+
+
+class DatasetDocumentSegmentAddApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_resource_check("vector_space")
+    @cloud_edition_billing_knowledge_limit_check("add_segment")
+    def post(self, dataset_id, document_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        if not current_user.is_editor:
+            raise Forbidden()
+        # check embedding model setting
+        if dataset.indexing_technique == "high_quality":
+            try:
+                model_manager = ModelManager()
+                model_manager.get_model_instance(
+                    tenant_id=current_user.current_tenant_id,
+                    provider=dataset.embedding_model_provider,
+                    model_type=ModelType.TEXT_EMBEDDING,
+                    model=dataset.embedding_model,
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                )
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument("content", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("answer", type=str, required=False, nullable=True, location="json")
+        parser.add_argument("keywords", type=list, required=False, nullable=True, location="json")
+        args = parser.parse_args()
+        SegmentService.segment_create_args_validate(args, document)
+        segment = SegmentService.create_segment(args, document, dataset)
+        return {"data": marshal(segment, segment_fields), "doc_form": document.doc_form}, 200
+
+
+class DatasetDocumentSegmentUpdateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_resource_check("vector_space")
+    def patch(self, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        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.")
+        if dataset.indexing_technique == "high_quality":
+            # check embedding model setting
+            try:
+                model_manager = ModelManager()
+                model_manager.get_model_instance(
+                    tenant_id=current_user.current_tenant_id,
+                    provider=dataset.embedding_model_provider,
+                    model_type=ModelType.TEXT_EMBEDDING,
+                    model=dataset.embedding_model,
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                )
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+            # check segment
+        segment_id = str(segment_id)
+        segment = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument("content", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("answer", type=str, required=False, nullable=True, location="json")
+        parser.add_argument("keywords", type=list, required=False, nullable=True, location="json")
+        parser.add_argument(
+            "regenerate_child_chunks", type=bool, required=False, nullable=True, default=False, location="json"
+        )
+        args = parser.parse_args()
+        SegmentService.segment_create_args_validate(args, document)
+        segment = SegmentService.update_segment(SegmentUpdateArgs(**args), segment, document, dataset)
+        return {"data": marshal(segment, segment_fields), "doc_form": document.doc_form}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        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 = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_editor:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        SegmentService.delete_segment(segment, document, dataset)
+        return {"result": "success"}, 200
+
+
+class DatasetDocumentSegmentBatchImportApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_resource_check("vector_space")
+    @cloud_edition_billing_knowledge_limit_check("add_segment")
+    def post(self, dataset_id, document_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        # get file from request
+        file = request.files["file"]
+        # check file
+        if "file" not in request.files:
+            raise NoFileUploadedError()
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+        # check file type
+        if not file.filename.endswith(".csv"):
+            raise ValueError("Invalid file type. Only CSV files are allowed")
+
+        try:
+            # Skip the first row
+            df = pd.read_csv(file)
+            result = []
+            for index, row in df.iterrows():
+                if document.doc_form == "qa_model":
+                    data = {"content": row.iloc[0], "answer": row.iloc[1]}
+                else:
+                    data = {"content": row.iloc[0]}
+                result.append(data)
+            if len(result) == 0:
+                raise ValueError("The CSV file is empty.")
+            # async job
+            job_id = str(uuid.uuid4())
+            indexing_cache_key = "segment_batch_import_{}".format(str(job_id))
+            # send batch add segments task
+            redis_client.setnx(indexing_cache_key, "waiting")
+            batch_create_segment_to_index_task.delay(
+                str(job_id), result, dataset_id, document_id, current_user.current_tenant_id, current_user.id
+            )
+        except Exception as e:
+            return {"error": str(e)}, 500
+        return {"job_id": job_id, "job_status": "waiting"}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, job_id):
+        job_id = str(job_id)
+        indexing_cache_key = "segment_batch_import_{}".format(job_id)
+        cache_result = redis_client.get(indexing_cache_key)
+        if cache_result is None:
+            raise ValueError("The job is not exist.")
+
+        return {"job_id": job_id, "job_status": cache_result.decode()}, 200
+
+
+class ChildChunkAddApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_resource_check("vector_space")
+    @cloud_edition_billing_knowledge_limit_check("add_segment")
+    def post(self, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # 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 = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        if not current_user.is_editor:
+            raise Forbidden()
+        # check embedding model setting
+        if dataset.indexing_technique == "high_quality":
+            try:
+                model_manager = ModelManager()
+                model_manager.get_model_instance(
+                    tenant_id=current_user.current_tenant_id,
+                    provider=dataset.embedding_model_provider,
+                    model_type=ModelType.TEXT_EMBEDDING,
+                    model=dataset.embedding_model,
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
+                )
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument("content", type=str, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        try:
+            child_chunk = SegmentService.create_child_chunk(args.get("content"), segment, document, dataset)
+        except ChildChunkIndexingServiceError as e:
+            raise ChildChunkIndexingError(str(e))
+        return {"data": marshal(child_chunk, child_chunk_fields)}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        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 = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        parser = reqparse.RequestParser()
+        parser.add_argument("limit", type=int, default=20, location="args")
+        parser.add_argument("keyword", type=str, default=None, location="args")
+        parser.add_argument("page", type=int, default=1, location="args")
+
+        args = parser.parse_args()
+
+        page = args["page"]
+        limit = min(args["limit"], 100)
+        keyword = args["keyword"]
+
+        child_chunks = SegmentService.get_child_chunks(segment_id, document_id, dataset_id, page, limit, keyword)
+        return {
+            "data": marshal(child_chunks.items, child_chunk_fields),
+            "total": child_chunks.total,
+            "total_pages": child_chunks.pages,
+            "page": page,
+            "limit": limit,
+        }, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_resource_check("vector_space")
+    def patch(self, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        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 = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument("chunks", type=list, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        try:
+            chunks = [ChildChunkUpdateArgs(**chunk) for chunk in args.get("chunks")]
+            child_chunks = SegmentService.update_child_chunks(chunks, segment, document, dataset)
+        except ChildChunkIndexingServiceError as e:
+            raise ChildChunkIndexingError(str(e))
+        return {"data": marshal(child_chunks, child_chunk_fields)}, 200
+
+
+class ChildChunkUpdateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, dataset_id, document_id, segment_id, child_chunk_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        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 = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        # check child chunk
+        child_chunk_id = str(child_chunk_id)
+        child_chunk = ChildChunk.query.filter(
+            ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not child_chunk:
+            raise NotFound("Child chunk not found.")
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_editor:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        try:
+            SegmentService.delete_child_chunk(child_chunk, dataset)
+        except ChildChunkDeleteIndexServiceError as e:
+            raise ChildChunkDeleteIndexError(str(e))
+        return {"result": "success"}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_resource_check("vector_space")
+    def patch(self, dataset_id, document_id, segment_id, child_chunk_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        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 = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        # check child chunk
+        child_chunk_id = str(child_chunk_id)
+        child_chunk = ChildChunk.query.filter(
+            ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not child_chunk:
+            raise NotFound("Child chunk not found.")
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_editor:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument("content", type=str, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        try:
+            child_chunk = SegmentService.update_child_chunk(
+                args.get("content"), child_chunk, segment, document, dataset
+            )
+        except ChildChunkIndexingServiceError as e:
+            raise ChildChunkIndexingError(str(e))
+        return {"data": marshal(child_chunk, child_chunk_fields)}, 200
+
+
+api.add_resource(DatasetDocumentSegmentListApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments")
+api.add_resource(
+    DatasetDocumentSegmentApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segment/<string:action>"
+)
+api.add_resource(DatasetDocumentSegmentAddApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segment")
+api.add_resource(
+    DatasetDocumentSegmentUpdateApi,
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>",
+)
+api.add_resource(
+    DatasetDocumentSegmentBatchImportApi,
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/batch_import",
+    "/datasets/batch_import_status/<uuid:job_id>",
+)
+api.add_resource(
+    ChildChunkAddApi,
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>/child_chunks",
+)
+api.add_resource(
+    ChildChunkUpdateApi,
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>/child_chunks/<uuid:child_chunk_id>",
+)

dify_0.15.3/api/controllers/console/datasets/error.py

@@ -0,0 +1,103 @@
+from libs.exception import BaseHTTPException
+
+
+class NoFileUploadedError(BaseHTTPException):
+    error_code = "no_file_uploaded"
+    description = "Please upload your file."
+    code = 400
+
+
+class TooManyFilesError(BaseHTTPException):
+    error_code = "too_many_files"
+    description = "Only one file is allowed."
+    code = 400
+
+
+class FileTooLargeError(BaseHTTPException):
+    error_code = "file_too_large"
+    description = "File size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedFileTypeError(BaseHTTPException):
+    error_code = "unsupported_file_type"
+    description = "File type not allowed."
+    code = 415
+
+
+class HighQualityDatasetOnlyError(BaseHTTPException):
+    error_code = "high_quality_dataset_only"
+    description = "Current operation only supports 'high-quality' datasets."
+    code = 400
+
+
+class DatasetNotInitializedError(BaseHTTPException):
+    error_code = "dataset_not_initialized"
+    description = "The dataset is still being initialized or indexing. Please wait a moment."
+    code = 400
+
+
+class ArchivedDocumentImmutableError(BaseHTTPException):
+    error_code = "archived_document_immutable"
+    description = "The archived document is not editable."
+    code = 403
+
+
+class DatasetNameDuplicateError(BaseHTTPException):
+    error_code = "dataset_name_duplicate"
+    description = "The dataset name already exists. Please modify your dataset name."
+    code = 409
+
+
+class InvalidActionError(BaseHTTPException):
+    error_code = "invalid_action"
+    description = "Invalid action."
+    code = 400
+
+
+class DocumentAlreadyFinishedError(BaseHTTPException):
+    error_code = "document_already_finished"
+    description = "The document has been processed. Please refresh the page or go to the document details."
+    code = 400
+
+
+class DocumentIndexingError(BaseHTTPException):
+    error_code = "document_indexing"
+    description = "The document is being processed and cannot be edited."
+    code = 400
+
+
+class InvalidMetadataError(BaseHTTPException):
+    error_code = "invalid_metadata"
+    description = "The metadata content is incorrect. Please check and verify."
+    code = 400
+
+
+class WebsiteCrawlError(BaseHTTPException):
+    error_code = "crawl_failed"
+    description = "{message}"
+    code = 500
+
+
+class DatasetInUseError(BaseHTTPException):
+    error_code = "dataset_in_use"
+    description = "The dataset is being used by some apps. Please remove the dataset from the apps before deleting it."
+    code = 409
+
+
+class IndexingEstimateError(BaseHTTPException):
+    error_code = "indexing_estimate_error"
+    description = "Knowledge indexing estimate failed: {message}"
+    code = 500
+
+
+class ChildChunkIndexingError(BaseHTTPException):
+    error_code = "child_chunk_indexing_error"
+    description = "Create child chunk index failed: {message}"
+    code = 500
+
+
+class ChildChunkDeleteIndexError(BaseHTTPException):
+    error_code = "child_chunk_delete_index_error"
+    description = "Delete child chunk index failed: {message}"
+    code = 500

dify_0.15.3/api/controllers/console/datasets/external.py

@@ -0,0 +1,262 @@
+from flask import request
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal, reqparse  # type: ignore
+from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
+
+import services
+from controllers.console import api
+from controllers.console.datasets.error import DatasetNameDuplicateError
+from controllers.console.wraps import account_initialization_required, setup_required
+from fields.dataset_fields import dataset_detail_fields
+from libs.login import login_required
+from services.dataset_service import DatasetService
+from services.external_knowledge_service import ExternalDatasetService
+from services.hit_testing_service import HitTestingService
+from services.knowledge_service import ExternalDatasetTestService
+
+
+def _validate_name(name):
+    if not name or len(name) < 1 or len(name) > 100:
+        raise ValueError("Name must be between 1 to 100 characters.")
+    return name
+
+
+def _validate_description_length(description):
+    if description and len(description) > 400:
+        raise ValueError("Description cannot exceed 400 characters.")
+    return description
+
+
+class ExternalApiTemplateListApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        page = request.args.get("page", default=1, type=int)
+        limit = request.args.get("limit", default=20, type=int)
+        search = request.args.get("keyword", default=None, type=str)
+
+        external_knowledge_apis, total = ExternalDatasetService.get_external_knowledge_apis(
+            page, limit, current_user.current_tenant_id, search
+        )
+        response = {
+            "data": [item.to_dict() for item in external_knowledge_apis],
+            "has_more": len(external_knowledge_apis) == limit,
+            "limit": limit,
+            "total": total,
+            "page": page,
+        }
+        return response, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="Name is required. Name must be between 1 to 100 characters.",
+            type=_validate_name,
+        )
+        parser.add_argument(
+            "settings",
+            type=dict,
+            location="json",
+            nullable=False,
+            required=True,
+        )
+        args = parser.parse_args()
+
+        ExternalDatasetService.validate_api_list(args["settings"])
+
+        # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
+        if not current_user.is_dataset_editor:
+            raise Forbidden()
+
+        try:
+            external_knowledge_api = ExternalDatasetService.create_external_knowledge_api(
+                tenant_id=current_user.current_tenant_id, user_id=current_user.id, args=args
+            )
+        except services.errors.dataset.DatasetNameDuplicateError:
+            raise DatasetNameDuplicateError()
+
+        return external_knowledge_api.to_dict(), 201
+
+
+class ExternalApiTemplateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, external_knowledge_api_id):
+        external_knowledge_api_id = str(external_knowledge_api_id)
+        external_knowledge_api = ExternalDatasetService.get_external_knowledge_api(external_knowledge_api_id)
+        if external_knowledge_api is None:
+            raise NotFound("API template not found.")
+
+        return external_knowledge_api.to_dict(), 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def patch(self, external_knowledge_api_id):
+        external_knowledge_api_id = str(external_knowledge_api_id)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="type is required. Name must be between 1 to 100 characters.",
+            type=_validate_name,
+        )
+        parser.add_argument(
+            "settings",
+            type=dict,
+            location="json",
+            nullable=False,
+            required=True,
+        )
+        args = parser.parse_args()
+        ExternalDatasetService.validate_api_list(args["settings"])
+
+        external_knowledge_api = ExternalDatasetService.update_external_knowledge_api(
+            tenant_id=current_user.current_tenant_id,
+            user_id=current_user.id,
+            external_knowledge_api_id=external_knowledge_api_id,
+            args=args,
+        )
+
+        return external_knowledge_api.to_dict(), 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, external_knowledge_api_id):
+        external_knowledge_api_id = str(external_knowledge_api_id)
+
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor or current_user.is_dataset_operator:
+            raise Forbidden()
+
+        ExternalDatasetService.delete_external_knowledge_api(current_user.current_tenant_id, external_knowledge_api_id)
+        return {"result": "success"}, 200
+
+
+class ExternalApiUseCheckApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, external_knowledge_api_id):
+        external_knowledge_api_id = str(external_knowledge_api_id)
+
+        external_knowledge_api_is_using, count = ExternalDatasetService.external_knowledge_api_use_check(
+            external_knowledge_api_id
+        )
+        return {"is_using": external_knowledge_api_is_using, "count": count}, 200
+
+
+class ExternalDatasetCreateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("external_knowledge_api_id", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("external_knowledge_id", type=str, required=True, nullable=False, location="json")
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="name is required. Name must be between 1 to 100 characters.",
+            type=_validate_name,
+        )
+        parser.add_argument("description", type=str, required=False, nullable=True, location="json")
+        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
+
+        args = parser.parse_args()
+
+        # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
+        if not current_user.is_dataset_editor:
+            raise Forbidden()
+
+        try:
+            dataset = ExternalDatasetService.create_external_dataset(
+                tenant_id=current_user.current_tenant_id,
+                user_id=current_user.id,
+                args=args,
+            )
+        except services.errors.dataset.DatasetNameDuplicateError:
+            raise DatasetNameDuplicateError()
+
+        return marshal(dataset, dataset_detail_fields), 201
+
+
+class ExternalKnowledgeHitTestingApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("query", type=str, location="json")
+        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
+        args = parser.parse_args()
+
+        HitTestingService.hit_testing_args_check(args)
+
+        try:
+            response = HitTestingService.external_retrieve(
+                dataset=dataset,
+                query=args["query"],
+                account=current_user,
+                external_retrieval_model=args["external_retrieval_model"],
+            )
+
+            return response
+        except Exception as e:
+            raise InternalServerError(str(e))
+
+
+class BedrockRetrievalApi(Resource):
+    # this api is only for internal testing
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("retrieval_setting", nullable=False, required=True, type=dict, location="json")
+        parser.add_argument(
+            "query",
+            nullable=False,
+            required=True,
+            type=str,
+        )
+        parser.add_argument("knowledge_id", nullable=False, required=True, type=str)
+        args = parser.parse_args()
+
+        # Call the knowledge retrieval service
+        result = ExternalDatasetTestService.knowledge_retrieval(
+            args["retrieval_setting"], args["query"], args["knowledge_id"]
+        )
+        return result, 200
+
+
+api.add_resource(ExternalKnowledgeHitTestingApi, "/datasets/<uuid:dataset_id>/external-hit-testing")
+api.add_resource(ExternalDatasetCreateApi, "/datasets/external")
+api.add_resource(ExternalApiTemplateListApi, "/datasets/external-knowledge-api")
+api.add_resource(ExternalApiTemplateApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>")
+api.add_resource(ExternalApiUseCheckApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>/use-check")
+# this api is only for internal test
+api.add_resource(BedrockRetrievalApi, "/test/retrieval")

dify_0.15.3/api/controllers/console/datasets/hit_testing.py

@@ -0,0 +1,23 @@
+from flask_restful import Resource  # type: ignore
+
+from controllers.console import api
+from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
+from controllers.console.wraps import account_initialization_required, setup_required
+from libs.login import login_required
+
+
+class HitTestingApi(Resource, DatasetsHitTestingBase):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+
+        dataset = self.get_and_validate_dataset(dataset_id_str)
+        args = self.parse_args()
+        self.hit_testing_args_check(args)
+
+        return self.perform_hit_testing(dataset, args)
+
+
+api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")

dify_0.15.3/api/controllers/console/datasets/hit_testing_base.py

@@ -0,0 +1,85 @@
+import logging
+
+from flask_login import current_user  # type: ignore
+from flask_restful import marshal, reqparse  # type: ignore
+from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
+
+import services.dataset_service
+from controllers.console.app.error import (
+    CompletionRequestError,
+    ProviderModelCurrentlyNotSupportError,
+    ProviderNotInitializeError,
+    ProviderQuotaExceededError,
+)
+from controllers.console.datasets.error import DatasetNotInitializedError
+from core.errors.error import (
+    LLMBadRequestError,
+    ModelCurrentlyNotSupportError,
+    ProviderTokenNotInitError,
+    QuotaExceededError,
+)
+from core.model_runtime.errors.invoke import InvokeError
+from fields.hit_testing_fields import hit_testing_record_fields
+from services.dataset_service import DatasetService
+from services.hit_testing_service import HitTestingService
+
+
+class DatasetsHitTestingBase:
+    @staticmethod
+    def get_and_validate_dataset(dataset_id: str):
+        dataset = DatasetService.get_dataset(dataset_id)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        return dataset
+
+    @staticmethod
+    def hit_testing_args_check(args):
+        HitTestingService.hit_testing_args_check(args)
+
+    @staticmethod
+    def parse_args():
+        parser = reqparse.RequestParser()
+
+        parser.add_argument("query", type=str, location="json")
+        parser.add_argument("retrieval_model", type=dict, required=False, location="json")
+        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
+        return parser.parse_args()
+
+    @staticmethod
+    def perform_hit_testing(dataset, args):
+        try:
+            response = HitTestingService.retrieve(
+                dataset=dataset,
+                query=args["query"],
+                account=current_user,
+                retrieval_model=args["retrieval_model"],
+                external_retrieval_model=args["external_retrieval_model"],
+                limit=10,
+            )
+            return {"query": response["query"], "records": marshal(response["records"], hit_testing_record_fields)}
+        except services.errors.index.IndexNotInitializedError:
+            raise DatasetNotInitializedError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except LLMBadRequestError:
+            raise ProviderNotInitializeError(
+                "No Embedding Model or Reranking Model available. Please configure a valid provider "
+                "in the Settings -> Model Provider."
+            )
+        except InvokeError as e:
+            raise CompletionRequestError(e.description)
+        except ValueError as e:
+            raise ValueError(str(e))
+        except Exception as e:
+            logging.exception("Hit testing failed.")
+            raise InternalServerError(str(e))

dify_0.15.3/api/controllers/console/datasets/website.py

@@ -0,0 +1,48 @@
+from flask_restful import Resource, reqparse  # type: ignore
+
+from controllers.console import api
+from controllers.console.datasets.error import WebsiteCrawlError
+from controllers.console.wraps import account_initialization_required, setup_required
+from libs.login import login_required
+from services.website_service import WebsiteService
+
+
+class WebsiteCrawlApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "provider", type=str, choices=["firecrawl", "jinareader"], required=True, nullable=True, location="json"
+        )
+        parser.add_argument("url", type=str, required=True, nullable=True, location="json")
+        parser.add_argument("options", type=dict, required=True, nullable=True, location="json")
+        args = parser.parse_args()
+        WebsiteService.document_create_args_validate(args)
+        # crawl url
+        try:
+            result = WebsiteService.crawl_url(args)
+        except Exception as e:
+            raise WebsiteCrawlError(str(e))
+        return result, 200
+
+
+class WebsiteCrawlStatusApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, job_id: str):
+        parser = reqparse.RequestParser()
+        parser.add_argument("provider", type=str, choices=["firecrawl", "jinareader"], required=True, location="args")
+        args = parser.parse_args()
+        # get crawl status
+        try:
+            result = WebsiteService.get_crawl_status(job_id, args["provider"])
+        except Exception as e:
+            raise WebsiteCrawlError(str(e))
+        return result, 200
+
+
+api.add_resource(WebsiteCrawlApi, "/website/crawl")
+api.add_resource(WebsiteCrawlStatusApi, "/website/crawl/status/<string:job_id>")