Migrate SQLAlchemy from 1.x to 2.0 with automated and manual adjustments (#23224)

Co-authored-by: Yongtao Huang <99629139+hyongtao-db@users.noreply.github.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>

api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py

@@ -6,7 +6,7 @@ from collections import defaultdict
 from collections.abc import Mapping, Sequence
 from typing import TYPE_CHECKING, Any, Optional, cast
 
-from sqlalchemy import Float, and_, func, or_, text
+from sqlalchemy import Float, and_, func, or_, select, text
 from sqlalchemy import cast as sqlalchemy_cast
 from sqlalchemy.orm import sessionmaker
 
@@ -367,15 +367,12 @@ class KnowledgeRetrievalNode(BaseNode):
                 for record in records:
                     segment = record.segment
                     dataset = db.session.query(Dataset).filter_by(id=segment.dataset_id).first()  # type: ignore
-                    document = (
-                        db.session.query(Document)
-                        .where(
-                            Document.id == segment.document_id,
-                            Document.enabled == True,
-                            Document.archived == False,
-                        )
-                        .first()
+                    stmt = select(Document).where(
+                        Document.id == segment.document_id,
+                        Document.enabled == True,
+                        Document.archived == False,
                     )
+                    document = db.session.scalar(stmt)
                     if dataset and document:
                         source = {
                             "metadata": {
@@ -514,7 +511,8 @@ class KnowledgeRetrievalNode(BaseNode):
         self, dataset_ids: list, query: str, node_data: KnowledgeRetrievalNodeData
     ) -> list[dict[str, Any]]:
         # get all metadata field
-        metadata_fields = db.session.query(DatasetMetadata).where(DatasetMetadata.dataset_id.in_(dataset_ids)).all()
+        stmt = select(DatasetMetadata).where(DatasetMetadata.dataset_id.in_(dataset_ids))
+        metadata_fields = db.session.scalars(stmt).all()
         all_metadata_fields = [metadata_field.name for metadata_field in metadata_fields]
         if node_data.metadata_model_config is None:
             raise ValueError("metadata_model_config is required")