Merge branch 'main' into feat/external-knowledge

# Conflicts:
#	api/core/rag/datasource/retrieval_service.py
#	api/models/dataset.py
#	api/services/dataset_service.py

api/controllers/console/datasets/datasets.py

@@ -18,7 +18,7 @@ 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.retrival_methods import RetrievalMethod
+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
@@ -422,7 +422,7 @@ class DatasetIndexingEstimateApi(Resource):
             )
         except LLMBadRequestError:
             raise ProviderNotInitializeError(
-                "No Embedding Model available. Please configure a valid provider " "in the Settings -> Model Provider."
+                "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
             )
         except ProviderTokenNotInitError as ex:
             raise ProviderNotInitializeError(ex.description)
@@ -573,12 +573,7 @@ class DatasetApiBaseUrlApi(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        return {
-            "api_base_url": (
-                dify_config.SERVICE_API_URL if dify_config.SERVICE_API_URL else request.host_url.rstrip("/")
-            )
-            + "/v1"
-        }
+        return {"api_base_url": (dify_config.SERVICE_API_URL or request.host_url.rstrip("/")) + "/v1"}
 
 
 class DatasetRetrievalSettingApi(Resource):

api/controllers/console/datasets/datasets_document.py

@@ -302,6 +302,8 @@ class DatasetInitApi(Resource):
             "doc_language", type=str, default="English", required=False, nullable=False, location="json"
         )
         parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
+        parser.add_argument("embedding_model", type=str, required=False, nullable=True, location="json")
+        parser.add_argument("embedding_model_provider", type=str, required=False, nullable=True, 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
@@ -309,6 +311,8 @@ class DatasetInitApi(Resource):
             raise Forbidden()
 
         if args["indexing_technique"] == "high_quality":
+            if args["embedding_model"] is None or args["embedding_model_provider"] is None:
+                raise ValueError("embedding model and embedding model provider are required for high quality indexing.")
             try:
                 model_manager = ModelManager()
                 model_manager.get_default_model_instance(
@@ -350,7 +354,7 @@ class DocumentIndexingEstimateApi(DocumentResource):
         document_id = str(document_id)
         document = self.get_document(dataset_id, document_id)
 
-        if document.indexing_status in ["completed", "error"]:
+        if document.indexing_status in {"completed", "error"}:
             raise DocumentAlreadyFinishedError()
 
         data_process_rule = document.dataset_process_rule
@@ -417,7 +421,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
         info_list = []
         extract_settings = []
         for document in documents:
-            if document.indexing_status in ["completed", "error"]:
+            if document.indexing_status in {"completed", "error"}:
                 raise DocumentAlreadyFinishedError()
             data_source_info = document.data_source_info_dict
             # format document files info
@@ -661,7 +665,7 @@ class DocumentProcessingApi(DocumentResource):
             db.session.commit()
 
         elif action == "resume":
-            if document.indexing_status not in ["paused", "error"]:
+            if document.indexing_status not in {"paused", "error"}:
                 raise InvalidActionError("Document not in paused or error state.")
 
             document.paused_by = None