refac: modernize type annotations (PEP 604 / PEP 585)

backend/open_webui/retrieval/loaders/datalab_marker.py

@@ -1,11 +1,12 @@
+import json
+import logging
 import os
 import time
-import requests
-import logging
-import json
 from typing import List, Optional
-from langchain_core.documents import Document
+
+import requests
 from fastapi import HTTPException, status
+from langchain_core.documents import Document
 
 log = logging.getLogger(__name__)
 

backend/open_webui/retrieval/loaders/external_document.py

@@ -1,8 +1,9 @@
-import requests
-import logging, os
+import logging
+import os
 from typing import Iterator, List, Union
 from urllib.parse import quote
 
+import requests
 from langchain_core.document_loaders import BaseLoader
 from langchain_core.documents import Document
 from open_webui.utils.headers import include_user_info_headers

backend/open_webui/retrieval/loaders/external_web.py

@@ -1,7 +1,7 @@
-import requests
 import logging
 from typing import Iterator, List, Union
 
+import requests
 from langchain_core.document_loaders import BaseLoader
 from langchain_core.documents import Document
 

backend/open_webui/retrieval/loaders/main.py

@@ -1,10 +1,10 @@
 import asyncio
-import requests
-import logging
-import ftfy
-import sys
 import json
+import logging
+import sys
 
+import ftfy
+import requests
 from azure.identity import DefaultAzureCredential
 from langchain_community.document_loaders import (
     AzureAIDocumentIntelligenceLoader,
@@ -17,16 +17,13 @@ from langchain_community.document_loaders import (
     YoutubeLoader,
 )
 from langchain_core.documents import Document
-
-from open_webui.retrieval.loaders.external_document import ExternalDocumentLoader
-
-from open_webui.retrieval.loaders.mistral import MistralLoader
+from open_webui.env import AIOHTTP_CLIENT_SESSION_SSL, GLOBAL_LOG_LEVEL, REQUESTS_VERIFY
 from open_webui.retrieval.loaders.datalab_marker import DatalabMarkerLoader
+from open_webui.retrieval.loaders.external_document import ExternalDocumentLoader
 from open_webui.retrieval.loaders.mineru import MinerULoader
+from open_webui.retrieval.loaders.mistral import MistralLoader
 from open_webui.retrieval.loaders.paddleocr_vl import PaddleOCRVLLoader
 
-from open_webui.env import GLOBAL_LOG_LEVEL, REQUESTS_VERIFY, AIOHTTP_CLIENT_SESSION_SSL
-
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
 log = logging.getLogger(__name__)
 

backend/open_webui/retrieval/loaders/mineru.py

@@ -1,12 +1,13 @@
-import os
-import time
-import requests
 import logging
+import os
 import tempfile
+import time
 import zipfile
 from typing import List, Optional
-from langchain_core.documents import Document
+
+import requests
 from fastapi import HTTPException, status
+from langchain_core.documents import Document
 
 log = logging.getLogger(__name__)
 

backend/open_webui/retrieval/loaders/mistral.py

@@ -1,15 +1,15 @@
-import requests
-import aiohttp
 import asyncio
 import logging
 import os
 import sys
 import time
-from typing import List, Dict, Any
 from contextlib import asynccontextmanager
+from typing import Any, Dict, List
 
+import aiohttp
+import requests
 from langchain_core.documents import Document
-from open_webui.env import GLOBAL_LOG_LEVEL, AIOHTTP_CLIENT_SESSION_SSL
+from open_webui.env import AIOHTTP_CLIENT_SESSION_SSL, GLOBAL_LOG_LEVEL
 
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
 log = logging.getLogger(__name__)

backend/open_webui/retrieval/loaders/paddleocr_vl.py

@@ -1,10 +1,10 @@
 import base64
-import os
-import requests
 import logging
+import os
 import sys
 from typing import List
 
+import requests
 from langchain_core.documents import Document
 from open_webui.env import GLOBAL_LOG_LEVEL
 

backend/open_webui/retrieval/loaders/tavily.py

@@ -1,7 +1,7 @@
-import requests
 import logging
 from typing import Iterator, List, Literal, Union
 
+import requests
 from langchain_core.document_loaders import BaseLoader
 from langchain_core.documents import Document
 

backend/open_webui/retrieval/loaders/youtube.py

@@ -1,8 +1,8 @@
 import logging
-from xml.etree.ElementTree import ParseError
-
 from typing import Any, Dict, Generator, List, Optional, Sequence, Union
 from urllib.parse import parse_qs, urlparse
+from xml.etree.ElementTree import ParseError
+
 from langchain_core.documents import Document
 
 log = logging.getLogger(__name__)

backend/open_webui/retrieval/models/base_reranker.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Optional, List, Tuple
+from typing import List, Optional, Tuple
 
 
 class BaseReranker(ABC):

backend/open_webui/retrieval/models/colbert.py

@@ -1,11 +1,10 @@
-import os
 import logging
-import torch
+import os
+
 import numpy as np
+import torch
 from colbert.infra import ColBERTConfig
 from colbert.modeling.checkpoint import Checkpoint
-
-
 from open_webui.retrieval.models.base_reranker import BaseReranker
 
 log = logging.getLogger(__name__)

backend/open_webui/retrieval/models/external.py

@@ -1,9 +1,8 @@
 import logging
-import requests
-from typing import Optional, List, Tuple
+from typing import List, Optional, Tuple
 from urllib.parse import quote
 
-
+import requests
 from open_webui.env import ENABLE_FORWARD_USER_INFO_HEADERS, REQUESTS_VERIFY
 from open_webui.retrieval.models.base_reranker import BaseReranker
 from open_webui.utils.headers import include_user_info_headers

backend/open_webui/retrieval/utils.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import asyncio
 import hashlib
 import logging
@@ -516,8 +518,11 @@ def get_all_items_from_collections(collection_names: list[str]) -> dict:
 
 
 async def query_collection(
-    request, collection_names: list[str], queries: list[str],
-    embedding_function, k: int,
+    request,
+    collection_names: list[str],
+    queries: list[str],
+    embedding_function,
+    k: int,
 ) -> dict:
     # When request is provided, try hybrid search + reranking if enabled
     if request and request.app.state.config.ENABLE_RAG_HYBRID_SEARCH:
@@ -1109,7 +1114,7 @@ async def get_sources_from_items(
     hybrid_bm25_weight,
     hybrid_search,
     full_context=False,
-    user: Optional[UserModel] = None,
+    user: UserModel | None = None,
 ):
     log.debug(f'items: {items} {queries} {embedding_function} {reranking_function} {full_context}')
 
@@ -1421,7 +1426,7 @@ class RerankCompressor(BaseDocumentCompressor):
         self,
         documents: Sequence[Document],
         query: str,
-        callbacks: Optional[Callbacks] = None,
+        callbacks: Callbacks | None = None,
     ) -> Sequence[Document]:
         """Compress retrieved documents given the query context.
 
@@ -1440,7 +1445,7 @@ class RerankCompressor(BaseDocumentCompressor):
         self,
         documents: Sequence[Document],
         query: str,
-        callbacks: Optional[Callbacks] = None,
+        callbacks: Callbacks | None = None,
     ) -> Sequence[Document]:
         reranking = self.reranking_function is not None
 

backend/open_webui/retrieval/vector/dbs/chroma.py

@@ -1,29 +1,27 @@
-import chromadb
 import logging
-from chromadb import Settings
-from chromadb.utils.batch_utils import create_batches
-
 from typing import Optional
 
-from open_webui.retrieval.vector.main import (
-    VectorDBBase,
-    VectorItem,
-    SearchResult,
-    GetResult,
-)
-from open_webui.retrieval.vector.utils import process_metadata
-
+import chromadb
+from chromadb import Settings
+from chromadb.utils.batch_utils import create_batches
 from open_webui.config import (
+    CHROMA_CLIENT_AUTH_CREDENTIALS,
+    CHROMA_CLIENT_AUTH_PROVIDER,
     CHROMA_DATA_PATH,
+    CHROMA_DATABASE,
+    CHROMA_HTTP_HEADERS,
     CHROMA_HTTP_HOST,
     CHROMA_HTTP_PORT,
-    CHROMA_HTTP_HEADERS,
     CHROMA_HTTP_SSL,
     CHROMA_TENANT,
-    CHROMA_DATABASE,
-    CHROMA_CLIENT_AUTH_PROVIDER,
-    CHROMA_CLIENT_AUTH_CREDENTIALS,
 )
+from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
+    VectorDBBase,
+    VectorItem,
+)
+from open_webui.retrieval.vector.utils import process_metadata
 
 log = logging.getLogger(__name__)
 

backend/open_webui/retrieval/vector/dbs/elasticsearch.py

@@ -2,28 +2,28 @@
 NOTE: This vector database integration is community-supported and maintained on a best-effort basis.
 """
 
-from elasticsearch import Elasticsearch, BadRequestError
-from typing import Optional
 import ssl
-from elasticsearch.helpers import bulk, scan
+from typing import Optional
 
-from open_webui.retrieval.vector.utils import process_metadata
-from open_webui.retrieval.vector.main import (
-    VectorDBBase,
-    VectorItem,
-    SearchResult,
-    GetResult,
-)
+from elasticsearch import BadRequestError, Elasticsearch
+from elasticsearch.helpers import bulk, scan
 from open_webui.config import (
-    ELASTICSEARCH_URL,
-    ELASTICSEARCH_CA_CERTS,
     ELASTICSEARCH_API_KEY,
-    ELASTICSEARCH_USERNAME,
-    ELASTICSEARCH_PASSWORD,
+    ELASTICSEARCH_CA_CERTS,
     ELASTICSEARCH_CLOUD_ID,
     ELASTICSEARCH_INDEX_PREFIX,
+    ELASTICSEARCH_PASSWORD,
+    ELASTICSEARCH_URL,
+    ELASTICSEARCH_USERNAME,
     SSL_ASSERT_FINGERPRINT,
 )
+from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
+    VectorDBBase,
+    VectorItem,
+)
+from open_webui.retrieval.vector.utils import process_metadata
 
 
 class ElasticsearchClient(VectorDBBase):

backend/open_webui/retrieval/vector/dbs/mariadb_vector.py

@@ -13,18 +13,15 @@ import sys
 from contextlib import contextmanager
 from typing import Any, Dict, List, Optional, Tuple
 
-from sqlalchemy import create_engine
-from sqlalchemy.pool import NullPool, QueuePool
-
 from open_webui.config import (
     MARIADB_VECTOR_DB_URL,
     MARIADB_VECTOR_DISTANCE_STRATEGY,
     MARIADB_VECTOR_INDEX_M,
     MARIADB_VECTOR_INITIALIZE_MAX_VECTOR_LENGTH,
-    MARIADB_VECTOR_POOL_SIZE,
     MARIADB_VECTOR_POOL_MAX_OVERFLOW,
-    MARIADB_VECTOR_POOL_TIMEOUT,
     MARIADB_VECTOR_POOL_RECYCLE,
+    MARIADB_VECTOR_POOL_SIZE,
+    MARIADB_VECTOR_POOL_TIMEOUT,
 )
 from open_webui.retrieval.vector.main import (
     GetResult,
@@ -33,6 +30,8 @@ from open_webui.retrieval.vector.main import (
     VectorItem,
 )
 from open_webui.retrieval.vector.utils import process_metadata
+from sqlalchemy import create_engine
+from sqlalchemy.pool import NullPool, QueuePool
 
 log = logging.getLogger(__name__)
 

backend/open_webui/retrieval/vector/dbs/milvus.py

@@ -2,33 +2,31 @@
 NOTE: This vector database integration is community-supported and maintained on a best-effort basis.
 """
 
-from pymilvus import MilvusClient as Client
-from pymilvus import FieldSchema, DataType
-from pymilvus import connections, Collection
-
 import json
 import logging
 from typing import Optional
 
-from open_webui.retrieval.vector.utils import process_metadata
-from open_webui.retrieval.vector.main import (
-    VectorDBBase,
-    VectorItem,
-    SearchResult,
-    GetResult,
-)
 from open_webui.config import (
-    MILVUS_URI,
     MILVUS_DB,
-    MILVUS_TOKEN,
-    MILVUS_INDEX_TYPE,
-    MILVUS_METRIC_TYPE,
-    MILVUS_HNSW_M,
-    MILVUS_HNSW_EFCONSTRUCTION,
-    MILVUS_IVF_FLAT_NLIST,
     MILVUS_DISKANN_MAX_DEGREE,
     MILVUS_DISKANN_SEARCH_LIST_SIZE,
+    MILVUS_HNSW_EFCONSTRUCTION,
+    MILVUS_HNSW_M,
+    MILVUS_INDEX_TYPE,
+    MILVUS_IVF_FLAT_NLIST,
+    MILVUS_METRIC_TYPE,
+    MILVUS_TOKEN,
+    MILVUS_URI,
 )
+from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
+    VectorDBBase,
+    VectorItem,
+)
+from open_webui.retrieval.vector.utils import process_metadata
+from pymilvus import Collection, DataType, FieldSchema, connections
+from pymilvus import MilvusClient as Client
 
 log = logging.getLogger(__name__)
 

backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py

@@ -3,18 +3,18 @@ NOTE: This vector database integration is community-supported and maintained on
 """
 
 import logging
-from typing import Optional, Tuple, List, Dict, Any
+from typing import Any, Dict, List, Optional, Tuple
 
 from open_webui.config import (
-    MILVUS_URI,
-    MILVUS_TOKEN,
-    MILVUS_DB,
     MILVUS_COLLECTION_PREFIX,
-    MILVUS_INDEX_TYPE,
-    MILVUS_METRIC_TYPE,
-    MILVUS_HNSW_M,
+    MILVUS_DB,
     MILVUS_HNSW_EFCONSTRUCTION,
+    MILVUS_HNSW_M,
+    MILVUS_INDEX_TYPE,
     MILVUS_IVF_FLAT_NLIST,
+    MILVUS_METRIC_TYPE,
+    MILVUS_TOKEN,
+    MILVUS_URI,
 )
 from open_webui.retrieval.vector.main import (
     GetResult,
@@ -23,12 +23,12 @@ from open_webui.retrieval.vector.main import (
     VectorItem,
 )
 from pymilvus import (
-    connections,
-    utility,
     Collection,
     CollectionSchema,
-    FieldSchema,
     DataType,
+    FieldSchema,
+    connections,
+    utility,
 )
 
 log = logging.getLogger(__name__)

backend/open_webui/retrieval/vector/dbs/opengauss.py

@@ -2,37 +2,36 @@
 NOTE: This vector database integration is community-supported and maintained on a best-effort basis.
 """
 
-from typing import Optional, List, Dict, Any
+import json
 import logging
 import re
-import json
+from typing import Any, Dict, List, Optional
+
+from pgvector.sqlalchemy import Vector
 from sqlalchemy import (
-    func,
-    literal,
+    Column,
+    Integer,
+    LargeBinary,
+    MetaData,
+    Table,
+    Text,
     cast,
     column,
     create_engine,
-    Column,
-    Integer,
-    MetaData,
-    LargeBinary,
+    func,
+    literal,
     select,
     text,
-    Text,
-    Table,
     values,
 )
-from sqlalchemy.sql import true
-from sqlalchemy.pool import NullPool, QueuePool
-
-from sqlalchemy.orm import declarative_base, scoped_session, sessionmaker
-from sqlalchemy.dialects.postgresql import JSONB, array
-from pgvector.sqlalchemy import Vector
-from sqlalchemy.ext.mutable import MutableDict
-from sqlalchemy.exc import NoSuchTableError
-
-from sqlalchemy.dialects.postgresql.psycopg2 import PGDialect_psycopg2
 from sqlalchemy.dialects import registry
+from sqlalchemy.dialects.postgresql import JSONB, array
+from sqlalchemy.dialects.postgresql.psycopg2 import PGDialect_psycopg2
+from sqlalchemy.exc import NoSuchTableError
+from sqlalchemy.ext.mutable import MutableDict
+from sqlalchemy.orm import declarative_base, scoped_session, sessionmaker
+from sqlalchemy.pool import NullPool, QueuePool
+from sqlalchemy.sql import true
 
 
 class OpenGaussDialect(PGDialect_psycopg2):
@@ -56,23 +55,22 @@ class OpenGaussDialect(PGDialect_psycopg2):
 # Register dialect
 registry.register('opengauss', __name__, 'OpenGaussDialect')
 
-from open_webui.retrieval.vector.utils import process_metadata
-from open_webui.retrieval.vector.main import (
-    VectorDBBase,
-    VectorItem,
-    SearchResult,
-    GetResult,
-)
 from open_webui.config import (
     OPENGAUSS_DB_URL,
     OPENGAUSS_INITIALIZE_MAX_VECTOR_LENGTH,
-    OPENGAUSS_POOL_SIZE,
     OPENGAUSS_POOL_MAX_OVERFLOW,
-    OPENGAUSS_POOL_TIMEOUT,
     OPENGAUSS_POOL_RECYCLE,
+    OPENGAUSS_POOL_SIZE,
+    OPENGAUSS_POOL_TIMEOUT,
 )
-
 from open_webui.env import SRC_LOG_LEVELS
+from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
+    VectorDBBase,
+    VectorItem,
+)
+from open_webui.retrieval.vector.utils import process_metadata
 
 VECTOR_LENGTH = OPENGAUSS_INITIALIZE_MAX_VECTOR_LENGTH
 Base = declarative_base()

backend/open_webui/retrieval/vector/dbs/opensearch.py

@@ -2,24 +2,24 @@
 NOTE: This vector database integration is community-supported and maintained on a best-effort basis.
 """
 
-from opensearchpy import OpenSearch
-from opensearchpy.helpers import bulk
 from typing import Optional
 
-from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.config import (
+    OPENSEARCH_CERT_VERIFY,
+    OPENSEARCH_PASSWORD,
+    OPENSEARCH_SSL,
+    OPENSEARCH_URI,
+    OPENSEARCH_USERNAME,
+)
 from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
     VectorDBBase,
     VectorItem,
-    SearchResult,
-    GetResult,
-)
-from open_webui.config import (
-    OPENSEARCH_URI,
-    OPENSEARCH_SSL,
-    OPENSEARCH_CERT_VERIFY,
-    OPENSEARCH_USERNAME,
-    OPENSEARCH_PASSWORD,
 )
+from open_webui.retrieval.vector.utils import process_metadata
+from opensearchpy import OpenSearch
+from opensearchpy.helpers import bulk
 
 
 class OpenSearchClient(VectorDBBase):

backend/open_webui/retrieval/vector/dbs/oracle23ai.py

@@ -28,34 +28,33 @@ ORACLE_DB_POOL_MAX = 10
 ORACLE_DB_POOL_INCREMENT = 1
 """
 
-from typing import Optional, List, Dict, Any, Union
-from decimal import Decimal
+import array
+import json
 import logging
 import os
 import threading
 import time
-import json
-import array
+from decimal import Decimal
+from typing import Any, Dict, List, Optional, Union
+
 import oracledb
-
-from open_webui.retrieval.vector.main import (
-    VectorDBBase,
-    VectorItem,
-    SearchResult,
-    GetResult,
-)
-
 from open_webui.config import (
+    ORACLE_DB_DSN,
+    ORACLE_DB_PASSWORD,
+    ORACLE_DB_POOL_INCREMENT,
+    ORACLE_DB_POOL_MAX,
+    ORACLE_DB_POOL_MIN,
     ORACLE_DB_USE_WALLET,
     ORACLE_DB_USER,
-    ORACLE_DB_PASSWORD,
-    ORACLE_DB_DSN,
+    ORACLE_VECTOR_LENGTH,
     ORACLE_WALLET_DIR,
     ORACLE_WALLET_PASSWORD,
-    ORACLE_VECTOR_LENGTH,
-    ORACLE_DB_POOL_MIN,
-    ORACLE_DB_POOL_MAX,
-    ORACLE_DB_POOL_INCREMENT,
+)
+from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
+    VectorDBBase,
+    VectorItem,
 )
 
 log = logging.getLogger(__name__)

backend/open_webui/retrieval/vector/dbs/pgvector.py

@@ -1,56 +1,54 @@
-from typing import Optional, List, Dict, Any, Tuple
-import logging
 import json
+import logging
+from typing import Any, Dict, List, Optional, Tuple
+
+from open_webui.config import (
+    PGVECTOR_CREATE_EXTENSION,
+    PGVECTOR_DB_URL,
+    PGVECTOR_HNSW_EF_CONSTRUCTION,
+    PGVECTOR_HNSW_M,
+    PGVECTOR_INDEX_METHOD,
+    PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH,
+    PGVECTOR_IVFFLAT_LISTS,
+    PGVECTOR_PGCRYPTO,
+    PGVECTOR_PGCRYPTO_KEY,
+    PGVECTOR_POOL_MAX_OVERFLOW,
+    PGVECTOR_POOL_RECYCLE,
+    PGVECTOR_POOL_SIZE,
+    PGVECTOR_POOL_TIMEOUT,
+    PGVECTOR_USE_HALFVEC,
+)
+from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
+    VectorDBBase,
+    VectorItem,
+)
+from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.utils.misc import sanitize_text_for_db
+from pgvector.sqlalchemy import HALFVEC, Vector
 from sqlalchemy import (
-    func,
-    literal,
+    Column,
+    Integer,
+    LargeBinary,
+    MetaData,
+    Table,
+    Text,
     cast,
     column,
     create_engine,
-    Column,
-    Integer,
-    MetaData,
-    LargeBinary,
+    func,
+    literal,
     select,
     text,
-    Text,
-    Table,
     values,
 )
-from sqlalchemy.sql import true
-from sqlalchemy.pool import NullPool, QueuePool
-
-from sqlalchemy.orm import declarative_base, scoped_session, sessionmaker
 from sqlalchemy.dialects.postgresql import JSONB, array
-from pgvector.sqlalchemy import Vector, HALFVEC
-from sqlalchemy.ext.mutable import MutableDict
 from sqlalchemy.exc import NoSuchTableError
-
-
-from open_webui.retrieval.vector.utils import process_metadata
-from open_webui.retrieval.vector.main import (
-    VectorDBBase,
-    VectorItem,
-    SearchResult,
-    GetResult,
-)
-from open_webui.utils.misc import sanitize_text_for_db
-from open_webui.config import (
-    PGVECTOR_DB_URL,
-    PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH,
-    PGVECTOR_CREATE_EXTENSION,
-    PGVECTOR_PGCRYPTO,
-    PGVECTOR_PGCRYPTO_KEY,
-    PGVECTOR_POOL_SIZE,
-    PGVECTOR_POOL_MAX_OVERFLOW,
-    PGVECTOR_POOL_TIMEOUT,
-    PGVECTOR_POOL_RECYCLE,
-    PGVECTOR_INDEX_METHOD,
-    PGVECTOR_HNSW_M,
-    PGVECTOR_HNSW_EF_CONSTRUCTION,
-    PGVECTOR_IVFFLAT_LISTS,
-    PGVECTOR_USE_HALFVEC,
-)
+from sqlalchemy.ext.mutable import MutableDict
+from sqlalchemy.orm import declarative_base, scoped_session, sessionmaker
+from sqlalchemy.pool import NullPool, QueuePool
+from sqlalchemy.sql import true
 
 VECTOR_LENGTH = PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH
 USE_HALFVEC = PGVECTOR_USE_HALFVEC

backend/open_webui/retrieval/vector/dbs/pinecone.py

@@ -2,9 +2,10 @@
 NOTE: This vector database integration is community-supported and maintained on a best-effort basis.
 """
 
-from typing import Optional, List, Dict, Any, Union
 import logging
 import time  # for measuring elapsed time
+from typing import Any, Dict, List, Optional, Union
+
 from pinecone import Pinecone, ServerlessSpec
 
 # Add gRPC support for better performance (Pinecone best practice)
@@ -16,24 +17,23 @@ except ImportError:
     GRPC_AVAILABLE = False
 
 import asyncio  # for async upserts
-import functools  # for partial binding in async tasks
-
 import concurrent.futures  # for parallel batch upserts
+import functools  # for partial binding in async tasks
 import random  # for jitter in retry backoff
 
-from open_webui.retrieval.vector.main import (
-    VectorDBBase,
-    VectorItem,
-    SearchResult,
-    GetResult,
-)
 from open_webui.config import (
     PINECONE_API_KEY,
+    PINECONE_CLOUD,
+    PINECONE_DIMENSION,
     PINECONE_ENVIRONMENT,
     PINECONE_INDEX_NAME,
-    PINECONE_DIMENSION,
     PINECONE_METRIC,
-    PINECONE_CLOUD,
+)
+from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
+    VectorDBBase,
+    VectorItem,
 )
 from open_webui.retrieval.vector.utils import process_metadata
 

backend/open_webui/retrieval/vector/dbs/qdrant.py

@@ -2,31 +2,30 @@
 NOTE: This vector database integration is community-supported and maintained on a best-effort basis.
 """
 
-from typing import Optional
 import logging
+from typing import Optional
 from urllib.parse import urlparse
 
+from open_webui.config import (
+    QDRANT_API_KEY,
+    QDRANT_COLLECTION_PREFIX,
+    QDRANT_GRPC_PORT,
+    QDRANT_HNSW_M,
+    QDRANT_ON_DISK,
+    QDRANT_PREFER_GRPC,
+    QDRANT_TIMEOUT,
+    QDRANT_URI,
+)
+from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
+    VectorDBBase,
+    VectorItem,
+)
 from qdrant_client import QdrantClient as Qclient
 from qdrant_client.http.models import PointStruct
 from qdrant_client.models import models
 
-from open_webui.retrieval.vector.main import (
-    VectorDBBase,
-    VectorItem,
-    SearchResult,
-    GetResult,
-)
-from open_webui.config import (
-    QDRANT_URI,
-    QDRANT_API_KEY,
-    QDRANT_ON_DISK,
-    QDRANT_GRPC_PORT,
-    QDRANT_PREFER_GRPC,
-    QDRANT_COLLECTION_PREFIX,
-    QDRANT_TIMEOUT,
-    QDRANT_HNSW_M,
-)
-
 NO_LIMIT = 999999999
 
 log = logging.getLogger(__name__)

backend/open_webui/retrieval/vector/dbs/qdrant_multitenancy.py

@@ -3,19 +3,19 @@ NOTE: This vector database integration is community-supported and maintained on
 """
 
 import logging
-from typing import Optional, Tuple, List, Dict, Any
+from typing import Any, Dict, List, Optional, Tuple
 from urllib.parse import urlparse
 
 import grpc
 from open_webui.config import (
     QDRANT_API_KEY,
+    QDRANT_COLLECTION_PREFIX,
     QDRANT_GRPC_PORT,
+    QDRANT_HNSW_M,
     QDRANT_ON_DISK,
     QDRANT_PREFER_GRPC,
-    QDRANT_URI,
-    QDRANT_COLLECTION_PREFIX,
     QDRANT_TIMEOUT,
-    QDRANT_HNSW_M,
+    QDRANT_URI,
 )
 from open_webui.retrieval.vector.main import (
     GetResult,

backend/open_webui/retrieval/vector/dbs/s3vector.py

@@ -2,17 +2,18 @@
 NOTE: This vector database integration is community-supported and maintained on a best-effort basis.
 """
 
-from open_webui.retrieval.vector.utils import process_metadata
+import logging
+from typing import Any, Dict, List, Optional, Union
+
+import boto3
+from open_webui.config import S3_VECTOR_BUCKET_NAME, S3_VECTOR_REGION
 from open_webui.retrieval.vector.main import (
-    VectorDBBase,
-    VectorItem,
     GetResult,
     SearchResult,
+    VectorDBBase,
+    VectorItem,
 )
-from open_webui.config import S3_VECTOR_BUCKET_NAME, S3_VECTOR_REGION
-from typing import List, Optional, Dict, Any, Union
-import logging
-import boto3
+from open_webui.retrieval.vector.utils import process_metadata
 
 log = logging.getLogger(__name__)
 

backend/open_webui/retrieval/vector/dbs/weaviate.py

@@ -2,28 +2,28 @@
 NOTE: This vector database integration is community-supported and maintained on a best-effort basis.
 """
 
-import weaviate
 import re
 import uuid
 from typing import Any, Dict, List, Optional, Union
 
-from open_webui.retrieval.vector.main import (
-    VectorDBBase,
-    VectorItem,
-    SearchResult,
-    GetResult,
-)
-from open_webui.retrieval.vector.utils import process_metadata
+import weaviate
 from open_webui.config import (
-    WEAVIATE_HTTP_HOST,
-    WEAVIATE_GRPC_HOST,
-    WEAVIATE_HTTP_PORT,
-    WEAVIATE_GRPC_PORT,
     WEAVIATE_API_KEY,
-    WEAVIATE_HTTP_SECURE,
+    WEAVIATE_GRPC_HOST,
+    WEAVIATE_GRPC_PORT,
     WEAVIATE_GRPC_SECURE,
+    WEAVIATE_HTTP_HOST,
+    WEAVIATE_HTTP_PORT,
+    WEAVIATE_HTTP_SECURE,
     WEAVIATE_SKIP_INIT_CHECKS,
 )
+from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
+    VectorDBBase,
+    VectorItem,
+)
+from open_webui.retrieval.vector.utils import process_metadata
 
 
 def _convert_uuids_to_strings(obj: Any) -> Any:

backend/open_webui/retrieval/vector/factory.py

@@ -1,10 +1,10 @@
+from open_webui.config import (
+    ENABLE_MILVUS_MULTITENANCY_MODE,
+    ENABLE_QDRANT_MULTITENANCY_MODE,
+    VECTOR_DB,
+)
 from open_webui.retrieval.vector.main import VectorDBBase
 from open_webui.retrieval.vector.type import VectorType
-from open_webui.config import (
-    VECTOR_DB,
-    ENABLE_QDRANT_MULTITENANCY_MODE,
-    ENABLE_MILVUS_MULTITENANCY_MODE,
-)
 
 
 class Vector:

backend/open_webui/retrieval/vector/main.py

@@ -1,7 +1,8 @@
-from pydantic import BaseModel
 from abc import ABC, abstractmethod
 from typing import Any, Dict, List, Optional, Union
 
+from pydantic import BaseModel
+
 
 class VectorItem(BaseModel):
     id: str

backend/open_webui/retrieval/web/azure.py

@@ -1,5 +1,6 @@
 import logging
 from typing import Optional
+
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)

backend/open_webui/retrieval/web/bing.py

@@ -1,10 +1,11 @@
+import argparse
 import logging
 import os
 from pprint import pprint
 from typing import Optional
+
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-import argparse
 
 log = logging.getLogger(__name__)
 """

backend/open_webui/retrieval/web/bocha.py

@@ -1,8 +1,8 @@
+import json
 import logging
 from typing import Optional
 
 import requests
-import json
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)

backend/open_webui/retrieval/web/brave.py

@@ -8,6 +8,7 @@ from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
 
+
 def search_brave(api_key: str, query: str, count: int, filter_list: list[str | None] = None) -> list[SearchResult]:
     """Search using Brave's Search API and return the results as a list of SearchResult objects.
 

backend/open_webui/retrieval/web/duckduckgo.py

@@ -9,6 +9,7 @@ from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
 
+
 def search_duckduckgo(
     query: str,
     count: int,

backend/open_webui/retrieval/web/external.py

@@ -1,14 +1,11 @@
 import logging
-from typing import Optional, List
+from typing import List, Optional
 
 import requests
-
 from fastapi import Request
-
-
+from open_webui.env import FORWARD_SESSION_INFO_HEADER_CHAT_ID
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 from open_webui.utils.headers import include_user_info_headers
-from open_webui.env import FORWARD_SESSION_INFO_HEADER_CHAT_ID
 
 log = logging.getLogger(__name__)
 

backend/open_webui/retrieval/web/google_pse.py

@@ -7,6 +7,7 @@ from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
 
+
 def search_google_pse(
     api_key: str,
     search_engine_id: str,

backend/open_webui/retrieval/web/jina_search.py

@@ -8,6 +8,7 @@ from yarl import URL
 
 log = logging.getLogger(__name__)
 
+
 def search_jina(api_key: str, query: str, count: int, base_url: str = '') -> list[SearchResult]:
     """
     Search using Jina's Search API and return the results as a list of SearchResult objects.

backend/open_webui/retrieval/web/main.py

@@ -7,6 +7,7 @@ from open_webui.retrieval.web.utils import resolve_hostname
 from open_webui.utils.misc import is_string_allowed
 from pydantic import BaseModel
 
+
 def get_filtered_results(results, filter_list):
     if not filter_list:
         return results
@@ -37,6 +38,7 @@ def get_filtered_results(results, filter_list):
 
     return filtered_results
 
+
 class SearchResult(BaseModel):
     link: str
     title: str | None

backend/open_webui/retrieval/web/mojeek.py

@@ -7,6 +7,7 @@ from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
 
+
 def search_mojeek(api_key: str, query: str, count: int, filter_list: list[str | None] = None) -> list[SearchResult]:
     """Search using Mojeek's Search API and return the results as a list of SearchResult objects.
 

backend/open_webui/retrieval/web/perplexity.py

@@ -1,7 +1,7 @@
 import logging
-from typing import Optional, Literal
-import requests
+from typing import Literal, Optional
 
+import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 MODELS = Literal[

backend/open_webui/retrieval/web/perplexity_search.py

@@ -1,7 +1,7 @@
 import logging
-from typing import Optional, Literal
-import requests
+from typing import Literal, Optional
 
+import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 from open_webui.utils.headers import include_user_info_headers
 

backend/open_webui/retrieval/web/searxng.py

@@ -7,6 +7,7 @@ from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
 
+
 def search_searxng(  # noqa: PLR0913
     query_url: str,
     query: str,

backend/open_webui/retrieval/web/serper.py

@@ -8,6 +8,7 @@ from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
 
+
 def search_serper(api_key: str, query: str, count: int, filter_list: list[str | None] = None) -> list[SearchResult]:
     """Search using serper.dev's API and return the results as a list of SearchResult objects.
 

backend/open_webui/retrieval/web/serply.py

@@ -8,6 +8,7 @@ from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
 
+
 def search_serply(
     api_key: str,
     query: str,

backend/open_webui/retrieval/web/serpstack.py

@@ -7,6 +7,7 @@ from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
 
+
 def search_serpstack(
     api_key: str,
     query: str,

backend/open_webui/retrieval/web/sougou.py

@@ -1,7 +1,6 @@
-import logging
 import json
-from typing import Optional, List
-
+import logging
+from typing import List, Optional
 
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
@@ -15,8 +14,8 @@ def search_sougou(
     count: int,
     filter_list: Optional[List[str]] = None,
 ) -> List[SearchResult]:
-    from tencentcloud.common.common_client import CommonClient
     from tencentcloud.common import credential
+    from tencentcloud.common.common_client import CommonClient
     from tencentcloud.common.exception.tencent_cloud_sdk_exception import (
         TencentCloudSDKException,
     )

backend/open_webui/retrieval/web/tavily.py

@@ -7,6 +7,7 @@ from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
 
+
 def search_tavily(
     api_key: str,
     query: str,

backend/open_webui/retrieval/web/utils.py

@@ -5,8 +5,6 @@ import socket
 import ssl
 import urllib.parse
 import urllib.request
-
-import requests
 from datetime import datetime, time, timedelta
 from typing import (
     Any,
@@ -14,41 +12,41 @@ from typing import (
     Dict,
     Iterator,
     List,
+    Literal,
     Optional,
     Sequence,
     Union,
-    Literal,
 )
 
-from fastapi.concurrency import run_in_threadpool
 import aiohttp
 import certifi
+import requests
 import validators
+from fastapi.concurrency import run_in_threadpool
 from langchain_community.document_loaders import PlaywrightURLLoader, WebBaseLoader
 from langchain_community.document_loaders.base import BaseLoader
 from langchain_core.documents import Document
-
-from open_webui.retrieval.loaders.tavily import TavilyLoader
-from open_webui.retrieval.loaders.external_web import ExternalWebLoader
-from open_webui.retrieval.web.firecrawl import scrape_firecrawl_url
-from open_webui.constants import ERROR_MESSAGES
 from open_webui.config import (
     ENABLE_RAG_LOCAL_WEB_FETCH,
-    PLAYWRIGHT_WS_URL,
-    PLAYWRIGHT_TIMEOUT,
-    WEB_LOADER_ENGINE,
-    WEB_LOADER_TIMEOUT,
+    EXTERNAL_WEB_LOADER_API_KEY,
+    EXTERNAL_WEB_LOADER_URL,
     FIRECRAWL_API_BASE_URL,
     FIRECRAWL_API_KEY,
     FIRECRAWL_TIMEOUT,
+    PLAYWRIGHT_TIMEOUT,
+    PLAYWRIGHT_WS_URL,
     TAVILY_API_KEY,
     TAVILY_EXTRACT_DEPTH,
-    EXTERNAL_WEB_LOADER_URL,
-    EXTERNAL_WEB_LOADER_API_KEY,
     WEB_FETCH_FILTER_LIST,
+    WEB_LOADER_ENGINE,
+    WEB_LOADER_TIMEOUT,
 )
+from open_webui.constants import ERROR_MESSAGES
+from open_webui.env import AIOHTTP_CLIENT_ALLOW_REDIRECTS, AIOHTTP_CLIENT_SESSION_SSL
+from open_webui.retrieval.loaders.external_web import ExternalWebLoader
+from open_webui.retrieval.loaders.tavily import TavilyLoader
+from open_webui.retrieval.web.firecrawl import scrape_firecrawl_url
 from open_webui.utils.misc import is_string_allowed
-from open_webui.env import AIOHTTP_CLIENT_SESSION_SSL, AIOHTTP_CLIENT_ALLOW_REDIRECTS
 
 log = logging.getLogger(__name__)
 

backend/open_webui/retrieval/web/yacy.py

@@ -2,8 +2,8 @@ import logging
 from typing import Optional
 
 import requests
-from requests.auth import HTTPDigestAuth
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
+from requests.auth import HTTPDigestAuth
 
 log = logging.getLogger(__name__)
 

backend/open_webui/retrieval/web/yandex.py

@@ -3,19 +3,16 @@ import io
 import json
 import logging
 import os
-from typing import Optional, List
-
-import requests
-
-from fastapi import Request
-
-from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.utils.headers import include_user_info_headers
-from open_webui.env import FORWARD_SESSION_INFO_HEADER_CHAT_ID
-
+from typing import List, Optional
 from xml.etree import ElementTree as ET
 from xml.etree.ElementTree import Element
 
+import requests
+from fastapi import Request
+from open_webui.env import FORWARD_SESSION_INFO_HEADER_CHAT_ID
+from open_webui.retrieval.web.main import SearchResult, get_filtered_results
+from open_webui.utils.headers import include_user_info_headers
+
 log = logging.getLogger(__name__)
 
 
@@ -122,8 +119,8 @@ def search_yandex(
 
 
 if __name__ == '__main__':
-    from starlette.datastructures import Headers
     from fastapi import FastAPI
+    from starlette.datastructures import Headers
 
     result = search_yandex(
         Request(

backend/open_webui/retrieval/web/ydc.py

@@ -1,5 +1,5 @@
 import logging
-from typing import Optional, List
+from typing import List, Optional
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results