diff --git a/api/core/callback_handler/index_tool_callback_handler.py b/api/core/callback_handler/index_tool_callback_handler.py
index fd818d9a27..13c22213c4 100644
--- a/api/core/callback_handler/index_tool_callback_handler.py
+++ b/api/core/callback_handler/index_tool_callback_handler.py
@@ -1,3 +1,5 @@
+import logging
+
 from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.app.entities.queue_entities import QueueRetrieverResourcesEvent
@@ -7,6 +9,8 @@ from extensions.ext_database import db
 from models.dataset import ChildChunk, DatasetQuery, DocumentSegment
 from models.dataset import Document as DatasetDocument
 
+_logger = logging.getLogger(__name__)
+
 
 class DatasetIndexToolCallbackHandler:
     """Callback handler for dataset tool."""
@@ -42,12 +46,13 @@ class DatasetIndexToolCallbackHandler:
         """Handle tool end."""
         for document in documents:
             if document.metadata is not None:
-                dataset_document = (
-                    db.session.query(DatasetDocument)
-                    .filter(DatasetDocument.id == document.metadata["document_id"])
-                    .first()
-                )
+                document_id = document.metadata["document_id"]
+                dataset_document = db.session.query(DatasetDocument).filter(DatasetDocument.id == document_id).first()
                 if not dataset_document:
+                    _logger.warning(
+                        "Expected DatasetDocument record to exist, but none was found, document_id=%s",
+                        document_id,
+                    )
                     continue
                 if dataset_document.doc_form == IndexType.PARENT_CHILD_INDEX:
                     child_chunk = (
diff --git a/api/schedule/clean_messages.py b/api/schedule/clean_messages.py
index b213b154e7..f41f5264c7 100644
--- a/api/schedule/clean_messages.py
+++ b/api/schedule/clean_messages.py
@@ -1,4 +1,5 @@
 import datetime
+import logging
 import time
 
 import click
@@ -20,6 +21,8 @@ from models.model import (
 from models.web import SavedMessage
 from services.feature_service import FeatureService
 
+_logger = logging.getLogger(__name__)
+
 
 @app.celery.task(queue="dataset")
 def clean_messages():
@@ -48,6 +51,11 @@ def clean_messages():
             plan_sandbox_clean_message_day = message.created_at
             app = db.session.query(App).filter_by(id=message.app_id).first()
             if not app:
+                _logger.warning(
+                    "Expected App record to exist, but none was found, app_id=%s, message_id=%s",
+                    message.app_id,
+                    message.id,
+                )
                 continue
             features_cache_key = f"features:{app.tenant_id}"
             plan_cache = redis_client.get(features_cache_key)
diff --git a/api/services/vector_service.py b/api/services/vector_service.py
index 696bcd2667..18d10cc528 100644
--- a/api/services/vector_service.py
+++ b/api/services/vector_service.py
@@ -1,3 +1,4 @@
+import logging
 from typing import Optional
 
 from core.model_manager import ModelInstance, ModelManager
@@ -12,6 +13,8 @@ from models.dataset import ChildChunk, Dataset, DatasetProcessRule, DocumentSegm
 from models.dataset import Document as DatasetDocument
 from services.entities.knowledge_entities.knowledge_entities import ParentMode
 
+_logger = logging.getLogger(__name__)
+
 
 class VectorService:
     @classmethod
@@ -24,6 +27,11 @@ class VectorService:
             if doc_form == IndexType.PARENT_CHILD_INDEX:
                 document = db.session.query(DatasetDocument).filter_by(id=segment.document_id).first()
                 if not document:
+                    _logger.warning(
+                        "Expected DatasetDocument record to exist, but none was found, document_id=%s, segment_id=%s",
+                        segment.document_id,
+                        segment.id,
+                    )
                     continue
                 # get the process rule
                 processing_rule = (