use model_validate (#26182)

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>

api/controllers/console/datasets/data_source.py

@@ -15,7 +15,7 @@ from core.datasource.entities.datasource_entities import DatasourceProviderType,
 from core.datasource.online_document.online_document_plugin import OnlineDocumentDatasourcePlugin
 from core.indexing_runner import IndexingRunner
 from core.rag.extractor.entity.datasource_type import DatasourceType
-from core.rag.extractor.entity.extract_setting import ExtractSetting
+from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo
 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
@@ -257,13 +257,15 @@ class DataSourceNotionApi(Resource):
             for page in notion_info["pages"]:
                 extract_setting = ExtractSetting(
                     datasource_type=DatasourceType.NOTION.value,
-                    notion_info={
-                        "credential_id": credential_id,
-                        "notion_workspace_id": workspace_id,
-                        "notion_obj_id": page["page_id"],
-                        "notion_page_type": page["type"],
-                        "tenant_id": current_user.current_tenant_id,
-                    },
+                    notion_info=NotionInfo.model_validate(
+                        {
+                            "credential_id": credential_id,
+                            "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)

api/controllers/console/datasets/datasets.py

@@ -24,7 +24,7 @@ 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.datasource_type import DatasourceType
-from core.rag.extractor.entity.extract_setting import ExtractSetting
+from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
 from extensions.ext_database import db
 from fields.app_fields import related_app_list
@@ -513,13 +513,15 @@ class DatasetIndexingEstimateApi(Resource):
                 for page in notion_info["pages"]:
                     extract_setting = ExtractSetting(
                         datasource_type=DatasourceType.NOTION.value,
-                        notion_info={
-                            "credential_id": credential_id,
-                            "notion_workspace_id": workspace_id,
-                            "notion_obj_id": page["page_id"],
-                            "notion_page_type": page["type"],
-                            "tenant_id": current_user.current_tenant_id,
-                        },
+                        notion_info=NotionInfo.model_validate(
+                            {
+                                "credential_id": credential_id,
+                                "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)
@@ -528,14 +530,16 @@ class DatasetIndexingEstimateApi(Resource):
             for url in website_info_list["urls"]:
                 extract_setting = ExtractSetting(
                     datasource_type=DatasourceType.WEBSITE.value,
-                    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"],
-                    },
+                    website_info=WebsiteInfo.model_validate(
+                        {
+                            "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)

api/controllers/console/datasets/datasets_document.py

@@ -44,7 +44,7 @@ from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.plugin.impl.exc import PluginDaemonClientSideError
 from core.rag.extractor.entity.datasource_type import DatasourceType
-from core.rag.extractor.entity.extract_setting import ExtractSetting
+from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
 from extensions.ext_database import db
 from fields.document_fields import (
     dataset_and_document_fields,
@@ -305,7 +305,7 @@ class DatasetDocumentListApi(Resource):
             "doc_language", type=str, default="English", required=False, nullable=False, location="json"
         )
         args = parser.parse_args()
-        knowledge_config = KnowledgeConfig(**args)
+        knowledge_config = KnowledgeConfig.model_validate(args)
 
         if not dataset.indexing_technique and not knowledge_config.indexing_technique:
             raise ValueError("indexing_technique is required.")
@@ -395,7 +395,7 @@ class DatasetInitApi(Resource):
         parser.add_argument("embedding_model_provider", type=str, required=False, nullable=True, location="json")
         args = parser.parse_args()
 
-        knowledge_config = KnowledgeConfig(**args)
+        knowledge_config = KnowledgeConfig.model_validate(args)
         if knowledge_config.indexing_technique == "high_quality":
             if knowledge_config.embedding_model is None or knowledge_config.embedding_model_provider is None:
                 raise ValueError("embedding model and embedding model provider are required for high quality indexing.")
@@ -547,13 +547,15 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                     continue
                 extract_setting = ExtractSetting(
                     datasource_type=DatasourceType.NOTION.value,
-                    notion_info={
-                        "credential_id": data_source_info["credential_id"],
-                        "notion_workspace_id": data_source_info["notion_workspace_id"],
-                        "notion_obj_id": data_source_info["notion_page_id"],
-                        "notion_page_type": data_source_info["type"],
-                        "tenant_id": current_user.current_tenant_id,
-                    },
+                    notion_info=NotionInfo.model_validate(
+                        {
+                            "credential_id": data_source_info["credential_id"],
+                            "notion_workspace_id": data_source_info["notion_workspace_id"],
+                            "notion_obj_id": data_source_info["notion_page_id"],
+                            "notion_page_type": data_source_info["type"],
+                            "tenant_id": current_user.current_tenant_id,
+                        }
+                    ),
                     document_model=document.doc_form,
                 )
                 extract_settings.append(extract_setting)
@@ -562,14 +564,16 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                     continue
                 extract_setting = ExtractSetting(
                     datasource_type=DatasourceType.WEBSITE.value,
-                    website_info={
-                        "provider": data_source_info["provider"],
-                        "job_id": data_source_info["job_id"],
-                        "url": data_source_info["url"],
-                        "tenant_id": current_user.current_tenant_id,
-                        "mode": data_source_info["mode"],
-                        "only_main_content": data_source_info["only_main_content"],
-                    },
+                    website_info=WebsiteInfo.model_validate(
+                        {
+                            "provider": data_source_info["provider"],
+                            "job_id": data_source_info["job_id"],
+                            "url": data_source_info["url"],
+                            "tenant_id": current_user.current_tenant_id,
+                            "mode": data_source_info["mode"],
+                            "only_main_content": data_source_info["only_main_content"],
+                        }
+                    ),
                     document_model=document.doc_form,
                 )
                 extract_settings.append(extract_setting)

api/controllers/console/datasets/datasets_segments.py

@@ -309,7 +309,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
         )
         args = parser.parse_args()
         SegmentService.segment_create_args_validate(args, document)
-        segment = SegmentService.update_segment(SegmentUpdateArgs(**args), segment, document, dataset)
+        segment = SegmentService.update_segment(SegmentUpdateArgs.model_validate(args), segment, document, dataset)
         return {"data": marshal(segment, segment_fields), "doc_form": document.doc_form}, 200
 
     @setup_required
@@ -564,7 +564,7 @@ class ChildChunkAddApi(Resource):
         args = parser.parse_args()
         try:
             chunks_data = args["chunks"]
-            chunks = [ChildChunkUpdateArgs(**chunk) for chunk in chunks_data]
+            chunks = [ChildChunkUpdateArgs.model_validate(chunk) for chunk in chunks_data]
             child_chunks = SegmentService.update_child_chunks(chunks, segment, document, dataset)
         except ChildChunkIndexingServiceError as e:
             raise ChildChunkIndexingError(str(e))

api/controllers/console/datasets/metadata.py

@@ -28,7 +28,7 @@ class DatasetMetadataCreateApi(Resource):
         parser.add_argument("type", type=str, required=True, nullable=False, location="json")
         parser.add_argument("name", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
-        metadata_args = MetadataArgs(**args)
+        metadata_args = MetadataArgs.model_validate(args)
 
         dataset_id_str = str(dataset_id)
         dataset = DatasetService.get_dataset(dataset_id_str)
@@ -137,7 +137,7 @@ class DocumentMetadataEditApi(Resource):
         parser = reqparse.RequestParser()
         parser.add_argument("operation_data", type=list, required=True, nullable=False, location="json")
         args = parser.parse_args()
-        metadata_args = MetadataOperationData(**args)
+        metadata_args = MetadataOperationData.model_validate(args)
 
         MetadataService.update_documents_metadata(dataset, metadata_args)
 

api/controllers/console/datasets/rag_pipeline/rag_pipeline.py

@@ -88,7 +88,7 @@ class CustomizedPipelineTemplateApi(Resource):
             nullable=True,
         )
         args = parser.parse_args()
-        pipeline_template_info = PipelineTemplateInfoEntity(**args)
+        pipeline_template_info = PipelineTemplateInfoEntity.model_validate(args)
         RagPipelineService.update_customized_pipeline_template(template_id, pipeline_template_info)
         return 200