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

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