update

Author: bowenliang123

.github/workflows/ci.yml

@@ -13,15 +13,31 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
+        image_tag: ["4.4.1.0-100000032025101610"]
+        init_sql: ["ALTER SYSTEM ob_vector_memory_limit_percentage = 30; SET GLOBAL ob_query_timeout=100000000;"]
+        test_filter: ["tests/test_hybrid_search.py::HybridSearchTest"]
         include:
-          - image_tag: "4.3.5.3-103000092025080818"
+          - python-version: 3.12
+            image_tag: "4.3.5.3-103000092025080818"
             init_sql: "ALTER SYSTEM ob_vector_memory_limit_percentage = 30; CREATE USER 'jtuser'@'%'; GRANT SELECT, INSERT, UPDATE, DELETE ON test.* TO 'jtuser'@'%'; FLUSH PRIVILEGES;"
             test_filter: "-k \"not HybridSearchTest\""
-          - image_tag: "4.4.1.0-100000032025101610"
-            init_sql: "ALTER SYSTEM ob_vector_memory_limit_percentage = 30; SET GLOBAL ob_query_timeout=100000000;"
-            test_filter: "tests/test_hybrid_search.py::HybridSearchTest"
 
     steps:
+      - name: Check out code
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: uv sync --dev
+
+      - name: Package build test
+        run: uv build
+
       - name: Free disk space
         uses: kfir4444/free-disk-space@main
         with:
@@ -32,21 +48,6 @@ jobs:
           large-packages: true
           swap-storage: true
 
-      - name: Check out code
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v3
-        with:
-          python-version: '3.x'
-
-      - name: Install uv
-        uses: astral-sh/setup-uv@v6
-
-      - name: Install dependencies
-        run: |
-          uv sync --dev
-
       - name: Start OceanBase container
         uses: oceanbase/setup-oceanbase-ce@v1
         with:

pyobvector/client/collection_schema.py

@@ -1,6 +1,5 @@
 """FieldSchema & CollectionSchema definition module to be compatible with Milvus."""
 import copy
-from typing import Optional, List
 from sqlalchemy import Column
 from .schema_type import DataType, convert_datatype_to_sqltype
 from .exceptions import *
@@ -125,8 +124,8 @@ class CollectionSchema:
     """
     def __init__(
         self,
-        fields: Optional[List[FieldSchema]] = None,
-        partitions: Optional[ObPartition] = None,
+        fields: list[FieldSchema] | None = None,
+        partitions: ObPartition | None = None,
         description: str = "",  # ignored in oceanbase
         **kwargs,
     ):

pyobvector/client/fts_index_param.py

@@ -1,6 +1,5 @@
 """A module to specify fts index parameters"""
 from enum import Enum
-from typing import List, Optional
 
 class FtsParser(Enum):
     IK = 0
@@ -11,8 +10,8 @@ class FtsIndexParam:
     def __init__(
         self,
         index_name: str,
-        field_names: List[str],
-        parser_type: Optional[FtsParser],
+        field_names: list[str],
+        parser_type: FtsParser | None,
     ):
         self.index_name = index_name
         self.field_names = field_names

pyobvector/client/hybrid_search.py

@@ -1,7 +1,7 @@
 """OceanBase Hybrid Search Client."""
 import json
 import logging
-from typing import Dict, Any
+from typing import Any
 
 from sqlalchemy import text
 
@@ -41,7 +41,7 @@ def __init__(
     def search(
         self,
         index: str,
-        body: Dict[str, Any],
+        body: dict[str, Any],
         **kwargs,
     ):
         """Execute hybrid search with parameter compatible with Elasticsearch.
@@ -66,7 +66,7 @@ def search(
     def get_sql(
         self,
         index: str,
-        body: Dict[str, Any],
+        body: dict[str, Any],
     ) -> str:
         """Get the SQL actually to be executed in hybrid search.
 

pyobvector/client/index_param.py

@@ -1,6 +1,5 @@
 """A module to specify vector index parameters for MilvusLikeClient"""
 from enum import Enum
-from typing import Union
 
 class VecIndexType(Enum):
     """Vector index algorithm type"""
@@ -34,7 +33,7 @@ class IndexParam:
     DAAT_ALGO_NAME = "daat"
 
     def __init__(
-        self, index_name: str, field_name: str, index_type: Union[VecIndexType, str], **kwargs
+        self, index_name: str, field_name: str, index_type: VecIndexType | str, **kwargs
     ):
         self.index_name = index_name
         self.field_name = field_name

pyobvector/client/milvus_like_client.py

@@ -1,7 +1,6 @@
 """Milvus Like Client."""
 import logging
 import json
-from typing import Optional, Union, Dict, List
 
 from sqlalchemy.exc import NoSuchTableError
 from sqlalchemy import (
@@ -51,15 +50,15 @@ def create_schema(self, **kwargs) -> CollectionSchema:
     def create_collection(
         self,
         collection_name: str,
-        dimension: Optional[int] = None,
+        dimension: int | None = None,
         primary_field_name: str = "id",
-        id_type: Union[DataType, str] = DataType.INT64,
+        id_type: DataType | str = DataType.INT64,
         vector_field_name: str = "vector",
         metric_type: str = "l2",
         auto_id: bool = False,
-        timeout: Optional[float] = None,
-        schema: Optional[CollectionSchema] = None,  # Used for custom setup
-        index_params: Optional[IndexParams] = None,  # Used for custom setup
+        timeout: float | None = None,
+        schema: CollectionSchema | None = None,  # Used for custom setup
+        index_params: IndexParams | None = None,  # Used for custom setup
         max_length: int = 16384,
         **kwargs,
     ): # pylint: disable=unused-argument
@@ -146,8 +145,8 @@ def create_collection(
             )
 
     def get_collection_stats(
-        self, collection_name: str, timeout: Optional[float] = None # pylint: disable=unused-argument
-    ) -> Dict:
+        self, collection_name: str, timeout: float | None = None # pylint: disable=unused-argument
+    ) -> dict:
         """Get collection row count.
         
         Args:
@@ -166,7 +165,7 @@ def get_collection_stats(
                 return {"row_count": cnt}
 
     def has_collection(
-        self, collection_name: str, timeout: Optional[float] = None # pylint: disable=unused-argument
+        self, collection_name: str, timeout: float | None = None # pylint: disable=unused-argument
     ) -> bool: # pylint: disable=unused-argument
         """Check if collection exists.
 
@@ -188,7 +187,7 @@ def drop_collection(self, collection_name: str) -> None:
         self.drop_table_if_exist(collection_name)
 
     def rename_collection(
-        self, old_name: str, new_name: str, timeout: Optional[float] = None # pylint: disable=unused-argument
+        self, old_name: str, new_name: str, timeout: float | None = None # pylint: disable=unused-argument
     ) -> None:
         """Rename collection.
         
@@ -228,7 +227,7 @@ def create_index(
         self,
         collection_name: str,
         index_params: IndexParams,
-        timeout: Optional[float] = None,
+        timeout: float | None = None,
         **kwargs,
     ): # pylint: disable=unused-argument
         """Create vector index with index params.
@@ -261,7 +260,7 @@ def drop_index(
         self,
         collection_name: str,
         index_name: str,
-        timeout: Optional[float] = None,
+        timeout: float | None = None,
         **kwargs,
     ): # pylint: disable=unused-argument
         """Drop index on specified collection.
@@ -349,17 +348,17 @@ def _parse_value_for_text_sql(
     def search(
         self,
         collection_name: str,
-        data: Union[list, dict],
+        data: list | dict,
         anns_field: str,
         with_dist: bool = False,
         flter=None,
         limit: int = 10,
-        output_fields: Optional[List[str]] = None,
-        search_params: Optional[dict] = None,
-        timeout: Optional[float] = None, # pylint: disable=unused-argument
-        partition_names: Optional[List[str]] = None,
+        output_fields: list[str] | None = None,
+        search_params: dict | None = None,
+        timeout: float | None = None, # pylint: disable=unused-argument
+        partition_names: list[str] | None = None,
         **kwargs, # pylint: disable=unused-argument
-    ) -> List[dict]:
+    ) -> list[dict]:
         """Perform ann search.
         Note: OceanBase does not support batch search now. `data` & the return value is not a batch.
         
@@ -467,11 +466,11 @@ def query(
         self,
         collection_name: str,
         flter=None,
-        output_fields: Optional[List[str]] = None,
-        timeout: Optional[float] = None, # pylint: disable=unused-argument
-        partition_names: Optional[List[str]] = None,
+        output_fields: list[str] | None = None,
+        timeout: float | None = None, # pylint: disable=unused-argument
+        partition_names: list[str] | None = None,
         **kwargs, # pylint: disable=unused-argument
-    ) -> List[dict]:
+    ) -> list[dict]:
         """Query records.
         
         Args:
@@ -532,12 +531,12 @@ def query(
     def get(
         self,
         collection_name: str,
-        ids: Union[list, str, int] = None,
-        output_fields: Optional[List[str]] = None,
-        timeout: Optional[float] = None, # pylint: disable=unused-argument
-        partition_names: Optional[List[str]] = None,
+        ids: list | str | int = None,
+        output_fields: list[str] | None = None,
+        timeout: float | None = None, # pylint: disable=unused-argument
+        partition_names: list[str] | None = None,
         **kwargs, # pylint: disable=unused-argument
-    ) -> List[dict]:
+    ) -> list[dict]:
         """Get records with specified primary field `ids`.
         
         Args:
@@ -575,7 +574,7 @@ def get(
             )
         if isinstance(ids, list):
             where_in_clause = table.c[pkey_names[0]].in_(ids)
-        elif isinstance(ids, (str, int)):
+        elif isinstance(ids, str | int):
             where_in_clause = table.c[pkey_names[0]].in_([ids])
         else:
             raise TypeError("'ids' is not a list/str/int")
@@ -610,10 +609,10 @@ def get(
     def delete(
         self,
         collection_name: str,
-        ids: Optional[Union[list, str, int]] = None,
-        timeout: Optional[float] = None, # pylint: disable=unused-argument
+        ids: list | str | int | None = None,
+        timeout: float | None = None, # pylint: disable=unused-argument
         flter=None,
-        partition_name: Optional[str] = "",
+        partition_name: str | None = "",
         **kwargs, # pylint: disable=unused-argument
     ) -> dict:
         """Delete data in collection.
@@ -648,7 +647,7 @@ def delete(
                 )
             if isinstance(ids, list):
                 where_in_clause = table.c[pkey_names[0]].in_(ids)
-            elif isinstance(ids, (str, int)):
+            elif isinstance(ids, str | int):
                 where_in_clause = table.c[pkey_names[0]].in_([ids])
             else:
                 raise TypeError("'ids' is not a list/str/int")
@@ -672,9 +671,9 @@ def delete(
     def insert(
         self,
         collection_name: str,
-        data: Union[Dict, List[Dict]],
-        timeout: Optional[float] = None,
-        partition_name: Optional[str] = "",
+        data: dict | list[dict],
+        timeout: float | None = None,
+        partition_name: str | None = "",
     ) -> (
         None
     ):  # pylint: disable=unused-argument
@@ -700,10 +699,10 @@ def insert(
     def upsert(
         self,
         collection_name: str,
-        data: Union[Dict, List[Dict]],
-        timeout: Optional[float] = None, # pylint: disable=unused-argument
-        partition_name: Optional[str] = "",
-    ) -> List[Union[str, int]]:
+        data: dict | list[dict],
+        timeout: float | None = None, # pylint: disable=unused-argument
+        partition_name: str | None = "",
+    ) -> list[str | int]:
         """Update data in table. If primary key is duplicated, replace it.
         
         Args: