Refactor: use DatasourceType.XX.value instead of hardcoded (#25015)

Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>

api/controllers/console/app/workflow.py

             )
 
             app_model.workflow_id = workflow.id
-            db.session.commit()
 
             workflow_created_at = TimestampField().format(workflow.created_at)
 

api/controllers/console/datasets/data_source.py

 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.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting
 from core.rag.extractor.notion_extractor import NotionExtractor
 from extensions.ext_database import db
             workspace_id = notion_info["workspace_id"]
             for page in notion_info["pages"]:
                 extract_setting = ExtractSetting(
-                    datasource_type="notion_import",
+                    datasource_type=DatasourceType.NOTION.value,
                     notion_info={
                         "notion_workspace_id": workspace_id,
                         "notion_obj_id": page["page_id"],

api/controllers/console/datasets/datasets.py

 from core.plugin.entities.plugin import ModelProviderID
 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.retrieval.retrieval_methods import RetrievalMethod
 from extensions.ext_database import db
             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"]
+                        datasource_type=DatasourceType.FILE.value,
+                        upload_file=file_detail,
+                        document_model=args["doc_form"],
                     )
                     extract_settings.append(extract_setting)
         elif args["info_list"]["data_source_type"] == "notion_import":
                 workspace_id = notion_info["workspace_id"]
                 for page in notion_info["pages"]:
                     extract_setting = ExtractSetting(
-                        datasource_type="notion_import",
+                        datasource_type=DatasourceType.NOTION.value,
                         notion_info={
                             "notion_workspace_id": workspace_id,
                             "notion_obj_id": page["page_id"],
             website_info_list = args["info_list"]["website_info_list"]
             for url in website_info_list["urls"]:
                 extract_setting = ExtractSetting(
-                    datasource_type="website_crawl",
+                    datasource_type=DatasourceType.WEBSITE.value,
                     website_info={
                         "provider": website_info_list["provider"],
                         "job_id": website_info_list["job_id"],

api/controllers/console/datasets/datasets_document.py

 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 extensions.ext_database import db
 from fields.document_fields import (
                     raise NotFound("File not found.")
 
                 extract_setting = ExtractSetting(
-                    datasource_type="upload_file", upload_file=file, document_model=document.doc_form
+                    datasource_type=DatasourceType.FILE.value, upload_file=file, document_model=document.doc_form
                 )
 
                 indexing_runner = IndexingRunner()
                     raise NotFound("File not found.")
 
                 extract_setting = ExtractSetting(
-                    datasource_type="upload_file", upload_file=file_detail, document_model=document.doc_form
+                    datasource_type=DatasourceType.FILE.value, upload_file=file_detail, document_model=document.doc_form
                 )
                 extract_settings.append(extract_setting)
 
             elif document.data_source_type == "notion_import":
                 extract_setting = ExtractSetting(
-                    datasource_type="notion_import",
+                    datasource_type=DatasourceType.NOTION.value,
                     notion_info={
                         "notion_workspace_id": data_source_info["notion_workspace_id"],
                         "notion_obj_id": data_source_info["notion_page_id"],
                 extract_settings.append(extract_setting)
             elif document.data_source_type == "website_crawl":
                 extract_setting = ExtractSetting(
-                    datasource_type="website_crawl",
+                    datasource_type=DatasourceType.WEBSITE.value,
                     website_info={
                         "provider": data_source_info["provider"],
                         "job_id": data_source_info["job_id"],

api/core/indexing_runner.py

 from core.rag.cleaner.clean_processor import CleanProcessor
 from core.rag.datasource.keyword.keyword_factory import Keyword
 from core.rag.docstore.dataset_docstore import DatasetDocumentStore
+from core.rag.extractor.entity.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting
 from core.rag.index_processor.constant.index_type import IndexType
 from core.rag.index_processor.index_processor_base import BaseIndexProcessor
 
             if file_detail:
                 extract_setting = ExtractSetting(
-                    datasource_type="upload_file", upload_file=file_detail, document_model=dataset_document.doc_form
+                    datasource_type=DatasourceType.FILE.value,
+                    upload_file=file_detail,
+                    document_model=dataset_document.doc_form,
                 )
                 text_docs = index_processor.extract(extract_setting, process_rule_mode=process_rule["mode"])
         elif dataset_document.data_source_type == "notion_import":
             ):
                 raise ValueError("no notion import info found")
             extract_setting = ExtractSetting(
-                datasource_type="notion_import",
+                datasource_type=DatasourceType.NOTION.value,
                 notion_info={
                     "notion_workspace_id": data_source_info["notion_workspace_id"],
                     "notion_obj_id": data_source_info["notion_page_id"],
             ):
                 raise ValueError("no website import info found")
             extract_setting = ExtractSetting(
-                datasource_type="website_crawl",
+                datasource_type=DatasourceType.WEBSITE.value,
                 website_info={
                     "provider": data_source_info["provider"],
                     "job_id": data_source_info["job_id"],

api/core/rag/extractor/extract_processor.py

         cls, upload_file: UploadFile, return_text: bool = False, is_automatic: bool = False
     ) -> Union[list[Document], str]:
         extract_setting = ExtractSetting(
-            datasource_type="upload_file", upload_file=upload_file, document_model="text_model"
+            datasource_type=DatasourceType.FILE.value, upload_file=upload_file, document_model="text_model"
         )
         if return_text:
             delimiter = "\n"
             # https://stackoverflow.com/questions/26541416/generate-temporary-file-names-without-creating-actual-file-in-python#comment90414256_26541521
             file_path = f"{temp_dir}/{tempfile.gettempdir()}{suffix}"
             Path(file_path).write_bytes(response.content)
-            extract_setting = ExtractSetting(datasource_type="upload_file", document_model="text_model")
+            extract_setting = ExtractSetting(datasource_type=DatasourceType.FILE.value, document_model="text_model")
             if return_text:
                 delimiter = "\n"
                 return delimiter.join(