From 53c4a8787f13b5e2d53664a4fc982ba816de877b Mon Sep 17 00:00:00 2001
From: -LAN- <laipz8200@outlook.com>
Date: Thu, 4 Sep 2025 09:35:32 +0800
Subject: [PATCH] [Chore/Refactor] Improve type safety and resolve type
 checking issues (#25104)

---
 .../rag/datasource/vdb/tablestore/tablestore_vector.py | 10 ++++++++--
 .../storage/clickzetta_volume/file_lifecycle.py        |  4 ++--
 api/pyrightconfig.json                                 |  1 -
 api/services/dataset_service.py                        |  2 +-
 4 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/api/core/rag/datasource/vdb/tablestore/tablestore_vector.py b/api/core/rag/datasource/vdb/tablestore/tablestore_vector.py
index dbb25d289..9c5535152 100644
--- a/api/core/rag/datasource/vdb/tablestore/tablestore_vector.py
+++ b/api/core/rag/datasource/vdb/tablestore/tablestore_vector.py
@@ -1,6 +1,7 @@
 import json
 import logging
 import math
+from collections.abc import Iterable
 from typing import Any, Optional
 
 import tablestore  # type: ignore
@@ -102,9 +103,12 @@ class TableStoreVector(BaseVector):
         return uuids
 
     def text_exists(self, id: str) -> bool:
-        _, return_row, _ = self._tablestore_client.get_row(
+        result = self._tablestore_client.get_row(
             table_name=self._table_name, primary_key=[("id", id)], columns_to_get=["id"]
         )
+        assert isinstance(result, tuple | list)
+        # Unpack the tuple result
+        _, return_row, _ = result
 
         return return_row is not None
 
@@ -169,6 +173,7 @@ class TableStoreVector(BaseVector):
 
     def _create_search_index_if_not_exist(self, dimension: int) -> None:
         search_index_list = self._tablestore_client.list_search_index(table_name=self._table_name)
+        assert isinstance(search_index_list, Iterable)
         if self._index_name in [t[1] for t in search_index_list]:
             logger.info("Tablestore system index[%s] already exists", self._index_name)
             return None
@@ -212,6 +217,7 @@ class TableStoreVector(BaseVector):
 
     def _delete_table_if_exist(self):
         search_index_list = self._tablestore_client.list_search_index(table_name=self._table_name)
+        assert isinstance(search_index_list, Iterable)
         for resp_tuple in search_index_list:
             self._tablestore_client.delete_search_index(resp_tuple[0], resp_tuple[1])
             logger.info("Tablestore delete index[%s] successfully.", self._index_name)
@@ -269,7 +275,7 @@ class TableStoreVector(BaseVector):
             )
 
             if search_response is not None:
-                rows.extend([row[0][0][1] for row in search_response.rows])
+                rows.extend([row[0][0][1] for row in list(search_response.rows)])
 
             if search_response is None or search_response.next_token == b"":
                 break
diff --git a/api/extensions/storage/clickzetta_volume/file_lifecycle.py b/api/extensions/storage/clickzetta_volume/file_lifecycle.py
index f5d6fd6f2..c41344774 100644
--- a/api/extensions/storage/clickzetta_volume/file_lifecycle.py
+++ b/api/extensions/storage/clickzetta_volume/file_lifecycle.py
@@ -1,8 +1,8 @@
 """ClickZetta Volume file lifecycle management
 
 This module provides file lifecycle management features including version control,
-automatic cleanup, backup and restore. Supports complete lifecycle management for
-knowledge base files.
+automatic cleanup, backup and restore.
+Supports complete lifecycle management for knowledge base files.
 """
 
 import json
diff --git a/api/pyrightconfig.json b/api/pyrightconfig.json
index 28ccbafd0..80fd10558 100644
--- a/api/pyrightconfig.json
+++ b/api/pyrightconfig.json
@@ -5,7 +5,6 @@
   "pythonVersion": "3.11",
   "pythonPlatform": "All",
   "reportMissingTypeStubs": false,
-  "reportGeneralTypeIssues": "none",
   "reportOptionalMemberAccess": "none",
   "reportOptionalIterable": "none",
   "reportOptionalOperand": "none",
diff --git a/api/services/dataset_service.py b/api/services/dataset_service.py
index 2e057b81c..a5550c701 100644
--- a/api/services/dataset_service.py
+++ b/api/services/dataset_service.py
@@ -1093,7 +1093,7 @@ class DocumentService:
         account: Account | Any,
         dataset_process_rule: Optional[DatasetProcessRule] = None,
         created_from: str = "web",
-    ):
+    ) -> tuple[list[Document], str]:
         # check doc_form
         DatasetService.check_doc_form(dataset, knowledge_config.doc_form)
         # check document limit