ci: add flag for linter

api/core/ops/ops_trace_manager.py

@@ -7,7 +7,7 @@
 import time
 from collections.abc import Mapping
 from datetime import timedelta
-from typing import TYPE_CHECKING, Any, TypedDict
+from typing import TYPE_CHECKING, Any, TypedDict, override
 from uuid import UUID, uuid4
 
 from cachetools import LRUCache
@@ -221,6 +221,7 @@ class TracingProviderConfigEntry(TypedDict):
 
 
 class OpsTraceProviderConfigMap(collections.UserDict[str, TracingProviderConfigEntry]):
+    @override
     def __getitem__(self, key: str) -> TracingProviderConfigEntry:
         try:
             match key:

api/core/rag/embedding/cached_embedding.py

@@ -1,7 +1,7 @@
 import base64
 import logging
 import pickle
-from typing import Any, cast
+from typing import Any, cast, override
 
 import numpy as np
 from sqlalchemy import select
@@ -25,6 +25,7 @@ class CacheEmbedding(Embeddings):
     def __init__(self, model_instance: ModelInstance):
         self._model_instance = model_instance
 
+    @override
     def embed_documents(self, texts: list[str]) -> list[list[float]]:
         """Embed search docs in batches of 10."""
         # use doc embedding cache or store if not exists
@@ -106,6 +107,7 @@ def embed_documents(self, texts: list[str]) -> list[list[float]]:
 
         return text_embeddings
 
+    @override
     def embed_multimodal_documents(self, multimodel_documents: list[dict[str, Any]]) -> list[list[float]]:
         """Embed file documents."""
         # use doc embedding cache or store if not exists
@@ -189,6 +191,7 @@ def embed_multimodal_documents(self, multimodel_documents: list[dict[str, Any]])
 
         return multimodel_embeddings
 
+    @override
     def embed_query(self, text: str) -> list[float]:
         """Embed query text."""
         # use doc embedding cache or store if not exists
@@ -232,6 +235,7 @@ def embed_query(self, text: str) -> list[float]:
 
         return embedding_results  # type: ignore
 
+    @override
     def embed_multimodal_query(self, multimodel_document: dict[str, Any]) -> list[float]:
         """Embed multimodal documents."""
         # use doc embedding cache or store if not exists

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

@@ -3,7 +3,7 @@
 import logging
 import re
 import uuid
-from typing import Any, TypedDict, cast
+from typing import Any, TypedDict, cast, override
 
 logger = logging.getLogger(__name__)
 
@@ -61,6 +61,7 @@ class ParagraphFormatPreviewDict(TypedDict):
 
 
 class ParagraphIndexProcessor(BaseIndexProcessor):
+    @override
     def extract(self, extract_setting: ExtractSetting, **kwargs) -> list[Document]:
         text_docs = ExtractProcessor.extract(
             extract_setting=extract_setting,
@@ -71,6 +72,7 @@ def extract(self, extract_setting: ExtractSetting, **kwargs) -> list[Document]:
 
         return text_docs
 
+    @override
     def transform(self, documents: list[Document], current_user: Account | None = None, **kwargs) -> list[Document]:
         process_rule = kwargs.get("process_rule")
         if not process_rule:
@@ -120,6 +122,7 @@ def transform(self, documents: list[Document], current_user: Account | None = No
             all_documents.extend(split_documents)
         return all_documents
 
+    @override
     def load(
         self,
         dataset: Dataset,
@@ -142,6 +145,7 @@ def load(
             else:
                 keyword.add_texts(documents)
 
+    @override
     def clean(self, dataset: Dataset, node_ids: list[str] | None, with_keywords: bool = True, **kwargs) -> None:
         # Note: Summary indexes are now disabled (not deleted) when segments are disabled.
         # This method is called for actual deletion scenarios (e.g., when segment is deleted).
@@ -178,6 +182,7 @@ def clean(self, dataset: Dataset, node_ids: list[str] | None, with_keywords: boo
             else:
                 keyword.delete()
 
+    @override
     def retrieve(
         self,
         retrieval_method: RetrievalMethod,
@@ -206,6 +211,7 @@ def retrieve(
                 docs.append(doc)
         return docs
 
+    @override
     def index(self, dataset: Dataset, document: DatasetDocument, chunks: Any) -> None:
         documents: list[Any] = []
         all_multimodal_documents: list[Any] = []
@@ -271,6 +277,7 @@ def index(self, dataset: Dataset, document: DatasetDocument, chunks: Any) -> Non
                 keyword = Keyword(dataset)
                 keyword.add_texts(documents)
 
+    @override
     def format_preview(self, chunks: Any) -> ParagraphFormatPreviewDict:
         if isinstance(chunks, list):
             preview = []
@@ -285,6 +292,7 @@ def format_preview(self, chunks: Any) -> ParagraphFormatPreviewDict:
         else:
             raise ValueError("Chunks is not a list")
 
+    @override
     def generate_summary_preview(
         self,
         tenant_id: str,

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

@@ -3,7 +3,7 @@
 import json
 import logging
 import uuid
-from typing import Any, TypedDict
+from typing import Any, TypedDict, override
 
 from sqlalchemy import delete, select
 
@@ -44,6 +44,7 @@ class ParentChildFormatPreviewDict(TypedDict):
 
 
 class ParentChildIndexProcessor(BaseIndexProcessor):
+    @override
     def extract(self, extract_setting: ExtractSetting, **kwargs) -> list[Document]:
         text_docs = ExtractProcessor.extract(
             extract_setting=extract_setting,
@@ -54,6 +55,7 @@ def extract(self, extract_setting: ExtractSetting, **kwargs) -> list[Document]:
 
         return text_docs
 
+    @override
     def transform(self, documents: list[Document], current_user: Account | None = None, **kwargs) -> list[Document]:
         process_rule = kwargs.get("process_rule")
         if not process_rule:
@@ -129,6 +131,7 @@ def transform(self, documents: list[Document], current_user: Account | None = No
 
         return all_documents
 
+    @override
     def load(
         self,
         dataset: Dataset,
@@ -149,6 +152,7 @@ def load(
             if multimodal_documents and dataset.is_multimodal:
                 vector.create_multimodal(multimodal_documents)
 
+    @override
     def clean(self, dataset: Dataset, node_ids: list[str] | None, with_keywords: bool = True, **kwargs) -> None:
         # node_ids is segment's node_ids
         # Note: Summary indexes are now disabled (not deleted) when segments are disabled.
@@ -219,6 +223,7 @@ def clean(self, dataset: Dataset, node_ids: list[str] | None, with_keywords: boo
                     )
                     db.session.commit()
 
+    @override
     def retrieve(
         self,
         retrieval_method: RetrievalMethod,
@@ -283,6 +288,7 @@ def _split_child_nodes(
                     child_nodes.append(child_document)
         return child_nodes
 
+    @override
     def index(self, dataset: Dataset, document: DatasetDocument, chunks: Any) -> None:
         parent_childs = ParentChildStructureChunk.model_validate(chunks)
         documents = []
@@ -356,6 +362,7 @@ def index(self, dataset: Dataset, document: DatasetDocument, chunks: Any) -> Non
                 if all_multimodal_documents and dataset.is_multimodal:
                     vector.create_multimodal(all_multimodal_documents)
 
+    @override
     def format_preview(self, chunks: Any) -> ParentChildFormatPreviewDict:
         parent_childs = ParentChildStructureChunk.model_validate(chunks)
         preview = []
@@ -369,6 +376,7 @@ def format_preview(self, chunks: Any) -> ParentChildFormatPreviewDict:
         }
         return result
 
+    @override
     def generate_summary_preview(
         self,
         tenant_id: str,

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

@@ -4,7 +4,7 @@
 import re
 import threading
 import uuid
-from typing import Any, TypedDict
+from typing import Any, TypedDict, override
 
 import pandas as pd
 from flask import Flask, current_app
@@ -43,6 +43,7 @@ class QAFormatPreviewDict(TypedDict):
 
 
 class QAIndexProcessor(BaseIndexProcessor):
+    @override
     def extract(self, extract_setting: ExtractSetting, **kwargs) -> list[Document]:
         text_docs = ExtractProcessor.extract(
             extract_setting=extract_setting,
@@ -52,6 +53,7 @@ def extract(self, extract_setting: ExtractSetting, **kwargs) -> list[Document]:
         )
         return text_docs
 
+    @override
     def transform(self, documents: list[Document], current_user: Account | None = None, **kwargs) -> list[Document]:
         preview = kwargs.get("preview")
         process_rule = kwargs.get("process_rule")
@@ -139,6 +141,7 @@ def format_by_template(self, file: FileStorage, **kwargs) -> list[Document]:
             raise ValueError(str(e))
         return text_docs
 
+    @override
     def load(
         self,
         dataset: Dataset,
@@ -153,6 +156,7 @@ def load(
             if multimodal_documents and dataset.is_multimodal:
                 vector.create_multimodal(multimodal_documents)
 
+    @override
     def clean(self, dataset: Dataset, node_ids: list[str] | None, with_keywords: bool = True, **kwargs) -> None:
         # Note: Summary indexes are now disabled (not deleted) when segments are disabled.
         # This method is called for actual deletion scenarios (e.g., when segment is deleted).
@@ -183,6 +187,7 @@ def clean(self, dataset: Dataset, node_ids: list[str] | None, with_keywords: boo
         else:
             vector.delete()
 
+    @override
     def retrieve(
         self,
         retrieval_method: RetrievalMethod,
@@ -211,6 +216,7 @@ def retrieve(
                 docs.append(doc)
         return docs
 
+    @override
     def index(self, dataset: Dataset, document: DatasetDocument, chunks: Any) -> None:
         qa_chunks = QAStructureChunk.model_validate(chunks)
         documents = []
@@ -234,6 +240,7 @@ def index(self, dataset: Dataset, document: DatasetDocument, chunks: Any) -> Non
             else:
                 raise ValueError("Indexing technique must be high quality.")
 
+    @override
     def format_preview(self, chunks: Any) -> QAFormatPreviewDict:
         qa_chunks = QAStructureChunk.model_validate(chunks)
         preview = []
@@ -246,6 +253,7 @@ def format_preview(self, chunks: Any) -> QAFormatPreviewDict:
         }
         return result
 
+    @override
     def generate_summary_preview(
         self,
         tenant_id: str,

api/core/rag/rerank/rerank_model.py

@@ -1,4 +1,5 @@
 import base64
+from typing import override
 
 from core.model_manager import ModelInstance, ModelManager
 from core.rag.index_processor.constant.doc_type import DocType
@@ -16,6 +17,7 @@ class RerankModelRunner(BaseRerankRunner):
     def __init__(self, rerank_model_instance: ModelInstance):
         self.rerank_model_instance = rerank_model_instance
 
+    @override
     def run(
         self,
         query: str,

api/core/rag/rerank/weight_rerank.py

@@ -1,5 +1,6 @@
 import math
 from collections import Counter
+from typing import override
 
 import numpy as np
 
@@ -19,6 +20,7 @@ def __init__(self, tenant_id: str, weights: Weights):
         self.tenant_id = tenant_id
         self.weights = weights
 
+    @override
     def run(
         self,
         query: str,

api/core/rag/splitter/fixed_text_splitter.py

@@ -5,7 +5,7 @@
 import codecs
 import re
 from collections.abc import Set as AbstractSet
-from typing import Any, Literal
+from typing import Any, Literal, override
 
 from core.model_manager import ModelInstance
 from core.rag.splitter.text_splitter import RecursiveCharacterTextSplitter
@@ -51,6 +51,7 @@ def __init__(self, fixed_separator: str = "\n\n", separators: list[str] | None =
         self._fixed_separator = codecs.decode(fixed_separator, "unicode_escape")
         self._separators = separators or ["\n\n", "\n", "。", ". ", " ", ""]
 
+    @override
     def split_text(self, text: str) -> list[str]:
         """Split incoming text and return chunks."""
         if self._fixed_separator:

api/core/rag/splitter/text_splitter.py

@@ -7,7 +7,7 @@
 from collections.abc import Callable, Iterable, Sequence
 from collections.abc import Set as AbstractSet
 from dataclasses import dataclass
-from typing import Any, Literal
+from typing import Any, Literal, override
 
 from core.rag.models.document import BaseDocumentTransformer, Document
 
@@ -148,10 +148,12 @@ def _huggingface_tokenizer_length(text: str) -> int:
             )
         return cls(length_function=lambda x: [_huggingface_tokenizer_length(text) for text in x], **kwargs)
 
+    @override
     def transform_documents(self, documents: Sequence[Document], **kwargs: Any) -> Sequence[Document]:
         """Transform sequence of documents by splitting them."""
         return self.split_documents(list(documents))
 
+    @override
     async def atransform_documents(self, documents: Sequence[Document], **kwargs: Any) -> Sequence[Document]:
         """Asynchronously transform a sequence of documents by splitting them."""
         raise NotImplementedError
@@ -211,6 +213,7 @@ def __init__(
         self._allowed_special: Literal["all"] | AbstractSet[str] = allowed_special
         self._disallowed_special: Literal["all"] | AbstractSet[str] = disallowed_special
 
+    @override
     def split_text(self, text: str) -> list[str]:
         def _encode(_text: str) -> list[int]:
             return self._tokenizer.encode(
@@ -287,5 +290,6 @@ def _split_text(self, text: str, separators: list[str]) -> list[str]:
 
         return final_chunks
 
+    @override
     def split_text(self, text: str) -> list[str]:
         return self._split_text(text, self._separators)

api/core/tools/builtin_tool/provider.py

@@ -1,6 +1,6 @@
 from abc import abstractmethod
 from os import listdir, path
-from typing import Any
+from typing import Any, override
 
 from core.entities.provider_entities import ProviderConfig
 from core.helper.module_import_helper import load_single_subclass_from_source
@@ -105,6 +105,7 @@ def _get_builtin_tools(self) -> list[BuiltinTool]:
         """
         return self.tools
 
+    @override
     def get_credentials_schema(self) -> list[ProviderConfig]:
         """
         returns the credentials schema of the provider
@@ -182,6 +183,7 @@ def need_credentials(self) -> bool:
         )
 
     @property
+    @override
     def provider_type(self) -> ToolProviderType:
         """
         returns the type of the provider

api/core/tools/builtin_tool/providers/audio/audio.py

@@ -1,8 +1,9 @@
-from typing import Any
+from typing import Any, override
 
 from core.tools.builtin_tool.provider import BuiltinToolProviderController
 
 
 class AudioToolProvider(BuiltinToolProviderController):
+    @override
     def _validate_credentials(self, user_id: str, credentials: dict[str, Any]):
         pass