chore: add ast-grep rule to convert Optional[T] to T | None (#25560)

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

api/core/rag/index_processor/index_processor_base.py

@@ -1,7 +1,6 @@
 """Abstract interface for document loader implementations."""
 
 from abc import ABC, abstractmethod
-from typing import Optional
 
 from configs import dify_config
 from core.model_manager import ModelInstance
@@ -31,7 +30,7 @@ class BaseIndexProcessor(ABC):
         raise NotImplementedError
 
     @abstractmethod
-    def clean(self, dataset: Dataset, node_ids: Optional[list[str]], with_keywords: bool = True, **kwargs):
+    def clean(self, dataset: Dataset, node_ids: list[str] | None, with_keywords: bool = True, **kwargs):
         raise NotImplementedError
 
     @abstractmethod
@@ -52,7 +51,7 @@ class BaseIndexProcessor(ABC):
         max_tokens: int,
         chunk_overlap: int,
         separator: str,
-        embedding_model_instance: Optional[ModelInstance],
+        embedding_model_instance: ModelInstance | None,
     ) -> TextSplitter:
         """
         Get the NodeParser object according to the processing rule.

api/core/rag/index_processor/processor/paragraph_index_processor.py

@@ -1,7 +1,6 @@
 """Paragraph index processor."""
 
 import uuid
-from typing import Optional
 
 from core.rag.cleaner.clean_processor import CleanProcessor
 from core.rag.datasource.keyword.keyword_factory import Keyword
@@ -85,7 +84,7 @@ class ParagraphIndexProcessor(BaseIndexProcessor):
             else:
                 keyword.add_texts(documents)
 
-    def clean(self, dataset: Dataset, node_ids: Optional[list[str]], with_keywords: bool = True, **kwargs):
+    def clean(self, dataset: Dataset, node_ids: list[str] | None, with_keywords: bool = True, **kwargs):
         if dataset.indexing_technique == "high_quality":
             vector = Vector(dataset)
             if node_ids:

api/core/rag/index_processor/processor/parent_child_index_processor.py

@@ -1,7 +1,6 @@
 """Paragraph index processor."""
 
 import uuid
-from typing import Optional
 
 from configs import dify_config
 from core.model_manager import ModelInstance
@@ -109,7 +108,7 @@ class ParentChildIndexProcessor(BaseIndexProcessor):
                     ]
                     vector.create(formatted_child_documents)
 
-    def clean(self, dataset: Dataset, node_ids: Optional[list[str]], with_keywords: bool = True, **kwargs):
+    def clean(self, dataset: Dataset, node_ids: list[str] | None, with_keywords: bool = True, **kwargs):
         # node_ids is segment's node_ids
         if dataset.indexing_technique == "high_quality":
             delete_child_chunks = kwargs.get("delete_child_chunks") or False
@@ -187,7 +186,7 @@ class ParentChildIndexProcessor(BaseIndexProcessor):
         document_node: Document,
         rules: Rule,
         process_rule_mode: str,
-        embedding_model_instance: Optional[ModelInstance],
+        embedding_model_instance: ModelInstance | None,
     ) -> list[ChildDocument]:
         if not rules.subchunk_segmentation:
             raise ValueError("No subchunk segmentation found in rules.")

api/core/rag/index_processor/processor/qa_index_processor.py

@@ -4,7 +4,6 @@ import logging
 import re
 import threading
 import uuid
-from typing import Optional
 
 import pandas as pd
 from flask import Flask, current_app
@@ -128,7 +127,7 @@ class QAIndexProcessor(BaseIndexProcessor):
             vector = Vector(dataset)
             vector.create(documents)
 
-    def clean(self, dataset: Dataset, node_ids: Optional[list[str]], with_keywords: bool = True, **kwargs):
+    def clean(self, dataset: Dataset, node_ids: list[str] | None, with_keywords: bool = True, **kwargs):
         vector = Vector(dataset)
         if node_ids:
             vector.delete_by_ids(node_ids)