pyobvector 0.2.19__py3-none-any.whl → 0.2.21__py3-none-any.whl

pyobvector/client/collection_schema.py

@@ -1,6 +1,6 @@
 """FieldSchema & CollectionSchema definition module to be compatible with Milvus."""
 import copy
-from typing import Optional, List
+from typing import Optional
 from sqlalchemy import Column
 from .schema_type import DataType, convert_datatype_to_sqltype
 from .exceptions import *
@@ -125,7 +125,7 @@ class CollectionSchema:
     """
     def __init__(
         self,
-        fields: Optional[List[FieldSchema]] = None,
+        fields: Optional[list[FieldSchema]] = None,
         partitions: Optional[ObPartition] = None,
         description: str = "",  # ignored in oceanbase
         **kwargs,

pyobvector/client/exceptions.py

@@ -85,13 +85,13 @@ class ExceptionsMessage:
         "Range expression is necessary when partition type is Range"
     )
     PartitionRangeColNameListMissing = (
-        "Column name list is necessary when parititon type is RangeColumns"
+        "Column name list is necessary when partition type is RangeColumns"
     )
     PartitionListExprMissing = (
         "List expression is necessary when partition type is List"
     )
     PartitionListColNameListMissing = (
-        "Column name list is necessary when parititon type is ListColumns"
+        "Column name list is necessary when partition type is ListColumns"
     )
     PartitionHashNameListAndPartCntMissing = (
         "One of hash_part_name_list and part_count must be set when partition type is Hash"

pyobvector/client/fts_index_param.py

@@ -1,28 +1,58 @@
 """A module to specify fts index parameters"""
 from enum import Enum
-from typing import List, Optional
+from typing import Optional, Union
 
 class FtsParser(Enum):
+    """Built-in full-text search parser types supported by OceanBase"""
     IK = 0
     NGRAM = 1
+    NGRAM2 = 2  # NGRAM2 parser (supported from V4.3.5 BP2+)
+    BASIC_ENGLISH = 3  # Basic English parser
+    JIEBA = 4  # jieba parser
 
 
 class FtsIndexParam:
+    """Full-text search index parameter.
+    
+    Args:
+        index_name: Index name
+        field_names: List of field names to create full-text index on
+        parser_type: Parser type, can be FtsParser enum or string (for custom parsers)
+                    If None, uses default Space parser
+    """
     def __init__(
         self,
         index_name: str,
-        field_names: List[str],
-        parser_type: Optional[FtsParser],
+        field_names: list[str],
+        parser_type: Optional[Union[FtsParser, str]] = None,
     ):
         self.index_name = index_name
         self.field_names = field_names
         self.parser_type = parser_type
 
-    def param_str(self) -> str | None:
-        if self.parser_type == FtsParser.IK:
-            return "ik"
-        if self.parser_type == FtsParser.NGRAM:
-            return "ngram"
+    def param_str(self) -> Optional[str]:
+        """Convert parser type to string format for SQL."""
+        if self.parser_type is None:
+            return None  # Default Space parser, no need to specify
+        
+        if isinstance(self.parser_type, str):
+            # Custom parser name (e.g., "thai_ftparser")
+            return self.parser_type.lower()
+        
+        if isinstance(self.parser_type, FtsParser):
+            if self.parser_type == FtsParser.IK:
+                return "ik"
+            if self.parser_type == FtsParser.NGRAM:
+                return "ngram"
+            if self.parser_type == FtsParser.NGRAM2:
+                return "ngram2"
+            if self.parser_type == FtsParser.BASIC_ENGLISH:
+                return "beng"
+            if self.parser_type == FtsParser.JIEBA:
+                return "jieba"
+            # Raise exception for unrecognized FtsParser enum values
+            raise ValueError(f"Unrecognized FtsParser enum value: {self.parser_type}")
+        
         return None
 
     def __iter__(self):
@@ -34,7 +64,7 @@ class FtsIndexParam:
     def __str__(self):
         return str(dict(self))
 
-    def __eq__(self, other: None):
+    def __eq__(self, other: object) -> bool:
         if isinstance(other, self.__class__):
             return dict(self) == dict(other)
 

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
 
@@ -30,13 +30,9 @@ class HybridSearch(Client):
         
         if self.ob_version < min_required_version:
             # For versions < 4.4.1.0, check if it's SeekDB
-            with self.engine.connect() as conn:
-                with conn.begin():
-                    res = conn.execute(text("SELECT version()"))
-                    version_str = [r[0] for r in res][0]
-                    if "SeekDB" in version_str:
-                        logger.info(f"SeekDB detected in version string: {version_str}, allowing hybrid search")
-                        return
+            if self._is_seekdb():
+                logger.info("SeekDB detected, allowing hybrid search")
+                return
             raise ClusterVersionException(
                 code=ErrorCode.NOT_SUPPORTED,
                 message=ExceptionsMessage.ClusterVersionIsLow % ("Hybrid Search", "4.4.1.0"),
@@ -45,7 +41,7 @@ class HybridSearch(Client):
     def search(
         self,
         index: str,
-        body: Dict[str, Any],
+        body: dict[str, Any],
         **kwargs,
     ):
         """Execute hybrid search with parameter compatible with Elasticsearch.
@@ -70,7 +66,7 @@ class HybridSearch(Client):
     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

@@ -134,8 +134,11 @@ class IndexParam:
                 if 'efSearch' in params:
                     ob_params['ef_search'] = params['efSearch']
         
-        if self.is_index_type_sparse_vector() and ob_params['distance'] != 'inner_product':
-            raise ValueError("Metric type should be 'inner_product' for sparse vector index.")
+        if self.is_index_type_sparse_vector():
+            if ob_params['distance'] != 'inner_product':
+                raise ValueError("Metric type should be 'inner_product' for sparse vector index.")
+            if 'sparse_index_type' in self.kwargs:
+                ob_params['type'] = self.kwargs['sparse_index_type']
         return ob_params
 
     def param_str(self):

pyobvector/client/milvus_like_client.py

@@ -1,7 +1,7 @@
 """Milvus Like Client."""
 import logging
 import json
-from typing import Optional, Union, Dict, List
+from typing import Optional, Union
 
 from sqlalchemy.exc import NoSuchTableError
 from sqlalchemy import (
@@ -147,7 +147,7 @@ class MilvusLikeClient(Client):
 
     def get_collection_stats(
         self, collection_name: str, timeout: Optional[float] = None # pylint: disable=unused-argument
-    ) -> Dict:
+    ) -> dict:
         """Get collection row count.
         
         Args:
@@ -354,12 +354,12 @@ class MilvusLikeClient(Client):
         with_dist: bool = False,
         flter=None,
         limit: int = 10,
-        output_fields: Optional[List[str]] = None,
+        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,
+        partition_names: Optional[list[str]] = 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 +467,11 @@ class MilvusLikeClient(Client):
         self,
         collection_name: str,
         flter=None,
-        output_fields: Optional[List[str]] = None,
+        output_fields: Optional[list[str]] = None,
         timeout: Optional[float] = None, # pylint: disable=unused-argument
-        partition_names: Optional[List[str]] = None,
+        partition_names: Optional[list[str]] = None,
         **kwargs, # pylint: disable=unused-argument
-    ) -> List[dict]:
+    ) -> list[dict]:
         """Query records.
         
         Args:
@@ -533,11 +533,11 @@ class MilvusLikeClient(Client):
         self,
         collection_name: str,
         ids: Union[list, str, int] = None,
-        output_fields: Optional[List[str]] = None,
+        output_fields: Optional[list[str]] = None,
         timeout: Optional[float] = None, # pylint: disable=unused-argument
-        partition_names: Optional[List[str]] = None,
+        partition_names: Optional[list[str]] = None,
         **kwargs, # pylint: disable=unused-argument
-    ) -> List[dict]:
+    ) -> list[dict]:
         """Get records with specified primary field `ids`.
         
         Args:
@@ -672,7 +672,7 @@ class MilvusLikeClient(Client):
     def insert(
         self,
         collection_name: str,
-        data: Union[Dict, List[Dict]],
+        data: Union[dict, list[dict]],
         timeout: Optional[float] = None,
         partition_name: Optional[str] = "",
     ) -> (
@@ -700,10 +700,10 @@ class MilvusLikeClient(Client):
     def upsert(
         self,
         collection_name: str,
-        data: Union[Dict, List[Dict]],
+        data: Union[dict, list[dict]],
         timeout: Optional[float] = None, # pylint: disable=unused-argument
         partition_name: Optional[str] = "",
-    ) -> List[Union[str, int]]:
+    ) -> list[Union[str, int]]:
         """Update data in table. If primary key is duplicated, replace it.
         
         Args:

pyobvector/client/ob_client.py

@@ -1,5 +1,5 @@
 import logging
-from typing import List, Optional, Dict, Union
+from typing import Optional, Union
 from urllib.parse import quote
 
 import sqlalchemy.sql.functions as func_mod
@@ -93,6 +93,26 @@ class ObClient:
             self.metadata_obj.clear()
             self.metadata_obj.reflect(bind=self.engine, extend_existing=True)
 
+    def _is_seekdb(self) -> bool:
+        """Check if the database is SeekDB by querying version.
+        
+        Returns:
+            bool: True if database is SeekDB, False otherwise
+        """
+        is_seekdb = False
+        try:
+            if hasattr(self, '_is_seekdb_cached'):
+                return self._is_seekdb_cached
+            with self.engine.connect() as conn:
+                result = conn.execute(text("SELECT VERSION()"))
+                version_str = [r[0] for r in result][0]
+                is_seekdb = "SeekDB" in version_str
+                self._is_seekdb_cached = is_seekdb
+                logger.debug(f"Version query result: {version_str}, is_seekdb: {is_seekdb}")
+        except Exception as e:
+            logger.warning(f"Failed to query version: {e}")
+        return is_seekdb
+
     def _insert_partition_hint_for_query_sql(self, sql: str, partition_hint: str):
         from_index = sql.find("FROM")
         assert from_index != -1
@@ -121,8 +141,8 @@ class ObClient:
     def create_table(
         self,
         table_name: str,
-        columns: List[Column],
-        indexes: Optional[List[Index]] = None,
+        columns: list[Column],
+        indexes: Optional[list[Index]] = None,
         partitions: Optional[ObPartition] = None,
         **kwargs,
     ):
@@ -188,7 +208,7 @@ class ObClient:
     def insert(
         self,
         table_name: str,
-        data: Union[Dict, List[Dict]],
+        data: Union[dict, list[dict]],
         partition_name: Optional[str] = "",
     ):
         """Insert data into table.
@@ -198,7 +218,7 @@ class ObClient:
             data (Union[Dict, List[Dict]]): data that will be inserted
             partition_name (Optional[str]): limit the query to certain partition
         """
-        if isinstance(data, Dict):
+        if isinstance(data, dict):
             data = [data]
 
         if len(data) == 0:
@@ -220,7 +240,7 @@ class ObClient:
     def upsert(
         self,
         table_name: str,
-        data: Union[Dict, List[Dict]],
+        data: Union[dict, list[dict]],
         partition_name: Optional[str] = "",
     ):
         """Update data in table. If primary key is duplicated, replace it.
@@ -230,7 +250,7 @@ class ObClient:
             data (Union[Dict, List[Dict]]): data that will be upserted
             partition_name (Optional[str]): limit the query to certain partition
         """
-        if isinstance(data, Dict):
+        if isinstance(data, dict):
             data = [data]
 
         if len(data) == 0:
@@ -345,8 +365,8 @@ class ObClient:
         table_name: str,
         ids: Optional[Union[list, str, int]] = None,
         where_clause=None,
-        output_column_name: Optional[List[str]] = None,
-        partition_names: Optional[List[str]] = None,
+        output_column_name: Optional[list[str]] = None,
+        partition_names: Optional[list[str]] = None,
         n_limits: Optional[int] = None,
     ):
         """Get records with specified primary field `ids`.

pyobvector/client/ob_vec_client.py

@@ -1,6 +1,6 @@
 """OceanBase Vector Store Client."""
 import logging
-from typing import List, Optional, Union
+from typing import Optional, Union
 
 import numpy as np
 from sqlalchemy import (
@@ -60,10 +60,10 @@ class ObVecClient(ObClient):
     def create_table_with_index_params(
         self,
         table_name: str,
-        columns: List[Column],
-        indexes: Optional[List[Index]] = None,
+        columns: list[Column],
+        indexes: Optional[list[Index]] = None,
         vidxs: Optional[IndexParams] = None,
-        fts_idxs: Optional[List[FtsIndexParam]] = None,
+        fts_idxs: Optional[list[FtsIndexParam]] = None,
         partitions: Optional[ObPartition] = None,
     ):
         """Create table with optional index_params.
@@ -99,7 +99,11 @@ class ObVecClient(ObClient):
                     create_table_sql = str(CreateTable(table).compile(self.engine))
                     new_sql = create_table_sql[:create_table_sql.rfind(')')]
                     for sparse_vidx in sparse_vidxs:
-                        new_sql += f",\n\tVECTOR INDEX {sparse_vidx.index_name}({sparse_vidx.field_name}) with (distance=inner_product)"
+                        sparse_params = sparse_vidx._parse_kwargs()
+                        if 'type' in sparse_params:
+                            new_sql += f",\n\tVECTOR INDEX {sparse_vidx.index_name}({sparse_vidx.field_name}) with (type={sparse_params['type']}, distance=inner_product)"
+                        else:
+                            new_sql += f",\n\tVECTOR INDEX {sparse_vidx.index_name}({sparse_vidx.field_name}) with (distance=inner_product)"
                     new_sql += "\n)"
                     conn.execute(text(new_sql))
                 else:
@@ -136,7 +140,7 @@ class ObVecClient(ObClient):
         table_name: str,
         is_vec_index: bool,
         index_name: str,
-        column_names: List[str],
+        column_names: list[str],
         vidx_params: Optional[str] = None,
         **kw,
     ):
@@ -270,12 +274,12 @@ class ObVecClient(ObClient):
         distance_func,
         with_dist: bool = False,
         topk: int = 10,
-        output_column_names: Optional[List[str]] = None,
-        output_columns: Optional[Union[List, tuple]] = None,
-        extra_output_cols: Optional[List] = None,
+        output_column_names: Optional[list[str]] = None,
+        output_columns: Optional[Union[list, tuple]] = None,
+        extra_output_cols: Optional[list] = None,
         where_clause=None,
-        partition_names: Optional[List[str]] = None,
-        idx_name_hint: Optional[List[str]] = None,
+        partition_names: Optional[list[str]] = None,
+        idx_name_hint: Optional[list[str]] = None,
         distance_threshold: Optional[float] = None,
         **kwargs,
     ):  # pylint: disable=unused-argument
@@ -399,11 +403,11 @@ class ObVecClient(ObClient):
         distance_func,
         with_dist: bool = False,
         topk: int = 10,
-        output_column_names: Optional[List[str]] = None,
-        extra_output_cols: Optional[List] = None,
+        output_column_names: Optional[list[str]] = None,
+        extra_output_cols: Optional[list] = None,
         where_clause=None,
-        partition_names: Optional[List[str]] = None,
-        str_list: Optional[List[str]] = None,
+        partition_names: Optional[list[str]] = None,
+        str_list: Optional[list[str]] = None,
         **kwargs,
     ):  # pylint: disable=unused-argument
         """Perform post ann search.
@@ -479,7 +483,7 @@ class ObVecClient(ObClient):
         vec_column_name: str,
         distance_func,
         topk: int = 10,
-        output_column_names: Optional[List[str]] = None,
+        output_column_names: Optional[list[str]] = None,
         where_clause=None,
         **kwargs,
     ):  # pylint: disable=unused-argument

pyobvector/client/ob_vec_json_table_client.py

@@ -1,18 +1,16 @@
 import json
 import logging
 import re
-from typing import Dict, List, Optional, Any, Union
+from typing import Optional, Union
 
 from sqlalchemy import Column, Integer, String, JSON, Engine, select, text, func, CursorResult
 from sqlalchemy.dialects.mysql import TINYINT
 from sqlalchemy.orm import declarative_base, sessionmaker, Session
 from sqlglot import parse_one, exp, Expression, to_identifier
-from sqlglot.expressions import Concat
 
 
 from .ob_vec_client import ObVecClient
 from ..json_table import (
-    OceanBase,
     ChangeColumn,
     JsonTableBool,
     JsonTableTimestamp,
@@ -58,7 +56,7 @@ class ObVecJsonTableClient(ObVecClient):
     class JsonTableMetadata: 
         def __init__(self, user_id: str):
             self.user_id = user_id
-            self.meta_cache: Dict[str, List] = {}
+            self.meta_cache: dict[str, list] = {}
 
         @classmethod
         def _parse_col_type(cls, col_type: str):
@@ -319,7 +317,7 @@ class ObVecJsonTableClient(ObVecClient):
     def _check_table_exists(self, jtable_name: str) -> bool:
         return jtable_name in self.jmetadata.meta_cache
     
-    def _check_col_exists(self, jtable_name: str, col_name: str) -> Optional[Dict]:
+    def _check_col_exists(self, jtable_name: str, col_name: str) -> Optional[dict]:
         if not self._check_table_exists(jtable_name):
             return None
         for col_meta in self.jmetadata.meta_cache[jtable_name]:
@@ -339,7 +337,7 @@ class ObVecJsonTableClient(ObVecClient):
             col_type_str += '(' + ','.join(col_type_params_list) + ')'
         return col_type_str
     
-    def _parse_col_constraints(self, expr: Expression) -> Dict:
+    def _parse_col_constraints(self, expr: Expression) -> dict:
         col_has_default = False
         col_nullable = True
         for cons in expr:
@@ -817,11 +815,12 @@ class ObVecJsonTableClient(ObVecClient):
     ):
         real_user_id = opt_user_id or self.user_id
 
-        table_name = ast.args['from'].this.this.this
+        from_key = 'from_' if 'from_' in ast.args else 'from'
+        table_name = ast.args[from_key].this.this.this
         if not self._check_table_exists(table_name):
             raise ValueError(f"Table {table_name} does not exists")
         
-        ast.args['from'].args['this'].args['this'] = to_identifier(name=JSON_TABLE_DATA_TABLE_NAME, quoted=False)
+        ast.args[from_key].args['this'].args['this'] = to_identifier(name=JSON_TABLE_DATA_TABLE_NAME, quoted=False)
 
         col_meta = self.jmetadata.meta_cache[table_name]
         json_table_meta_str = []
@@ -883,12 +882,19 @@ class ObVecJsonTableClient(ObVecClient):
                 identifier.args['quoted'] = False
                 col.args['table'] = identifier
 
-        join_clause = parse_one(f"from t1, {json_table_str}")
-        join_node = join_clause.args['joins'][0]
-        if 'joins' in ast.args.keys():
-            ast.args['joins'].append(join_node)
-        else:
-            ast.args['joins'] = [join_node]
+        # Manually create the JOIN node for json_table
+        # In some versions of sqlglot, comma-separated tables may not be parsed as
+        # explicit JOINS, so we directly parse the json_table expression and create a JOIN node
+        # explicitly
+        json_table_expr = parse_one(json_table_str, dialect="oceanbase")
+        
+        join_node = exp.Join()
+        join_node.args['this'] = json_table_expr
+        join_node.args['kind'] = None  # CROSS JOIN (implicit join with comma)
+        
+        if 'joins' not in ast.args:
+            ast.args['joins'] = []
+        ast.args['joins'].append(join_node)
 
         if real_user_id:
             extra_filter_str = f"{JSON_TABLE_DATA_TABLE_NAME}.user_id = '{real_user_id}' AND {JSON_TABLE_DATA_TABLE_NAME}.jtable_name = '{table_name}'"

pyobvector/client/partitions.py

@@ -1,5 +1,5 @@
 """A module to do compilation of OceanBase Parition Clause."""
-from typing import List, Optional, Union
+from typing import Optional, Union
 import logging
 from dataclasses import dataclass
 from .enum import IntEnum
@@ -69,11 +69,11 @@ class RangeListPartInfo:
         Using 100 / `MAXVALUE` when create Range/RangeColumns partition.
     """
     part_name: str
-    part_upper_bound_expr: Union[List, str, int]
+    part_upper_bound_expr: Union[list, str, int]
 
     def get_part_expr_str(self):
         """Parse part_upper_bound_expr to text SQL."""
-        if isinstance(self.part_upper_bound_expr, List):
+        if isinstance(self.part_upper_bound_expr, list):
             return ",".join([str(v) for v in self.part_upper_bound_expr])
         if isinstance(self.part_upper_bound_expr, str):
             return self.part_upper_bound_expr
@@ -87,9 +87,9 @@ class ObRangePartition(ObPartition):
     def __init__(
         self,
         is_range_columns: bool,
-        range_part_infos: List[RangeListPartInfo],
+        range_part_infos: list[RangeListPartInfo],
         range_expr: Optional[str] = None,
-        col_name_list: Optional[List[str]] = None,
+        col_name_list: Optional[list[str]] = None,
     ):
         super().__init__(PartType.RangeColumns if is_range_columns else PartType.Range)
         self.range_part_infos = range_part_infos
@@ -140,9 +140,9 @@ class ObSubRangePartition(ObRangePartition):
     def __init__(
         self,
         is_range_columns: bool,
-        range_part_infos: List[RangeListPartInfo],
+        range_part_infos: list[RangeListPartInfo],
         range_expr: Optional[str] = None,
-        col_name_list: Optional[List[str]] = None,
+        col_name_list: Optional[list[str]] = None,
     ):
         super().__init__(is_range_columns, range_part_infos, range_expr, col_name_list)
         self.is_sub = True
@@ -176,9 +176,9 @@ class ObListPartition(ObPartition):
     def __init__(
         self,
         is_list_columns: bool,
-        list_part_infos: List[RangeListPartInfo],
+        list_part_infos: list[RangeListPartInfo],
         list_expr: Optional[str] = None,
-        col_name_list: Optional[List[str]] = None,
+        col_name_list: Optional[list[str]] = None,
     ):
         super().__init__(PartType.ListColumns if is_list_columns else PartType.List)
         self.list_part_infos = list_part_infos
@@ -228,9 +228,9 @@ class ObSubListPartition(ObListPartition):
     def __init__(
         self,
         is_list_columns: bool,
-        list_part_infos: List[RangeListPartInfo],
+        list_part_infos: list[RangeListPartInfo],
         list_expr: Optional[str] = None,
-        col_name_list: Optional[List[str]] = None,
+        col_name_list: Optional[list[str]] = None,
     ):
         super().__init__(is_list_columns, list_part_infos, list_expr, col_name_list)
         self.is_sub = True
@@ -263,7 +263,7 @@ class ObHashPartition(ObPartition):
     def __init__(
         self,
         hash_expr: str,
-        hash_part_name_list: List[str] = None,
+        hash_part_name_list: list[str] = None,
         part_count: Optional[int] = None,
     ):
         super().__init__(PartType.Hash)
@@ -308,7 +308,7 @@ class ObSubHashPartition(ObHashPartition):
     def __init__(
         self,
         hash_expr: str,
-        hash_part_name_list: List[str] = None,
+        hash_part_name_list: list[str] = None,
         part_count: Optional[int] = None,
     ):
         super().__init__(hash_expr, hash_part_name_list, part_count)
@@ -334,8 +334,8 @@ class ObKeyPartition(ObPartition):
     """Key partition strategy."""
     def __init__(
         self,
-        col_name_list: List[str],
-        key_part_name_list: List[str] = None,
+        col_name_list: list[str],
+        key_part_name_list: list[str] = None,
         part_count: Optional[int] = None,
     ):
         super().__init__(PartType.Key)
@@ -381,8 +381,8 @@ class ObSubKeyPartition(ObKeyPartition):
     """Key subpartition strategy."""
     def __init__(
         self,
-        col_name_list: List[str],
-        key_part_name_list: List[str] = None,
+        col_name_list: list[str],
+        key_part_name_list: list[str] = None,
         part_count: Optional[int] = None,
     ):
         super().__init__(col_name_list, key_part_name_list, part_count)

pyobvector/json_table/json_value_returning_func.py

@@ -1,10 +1,9 @@
 import logging
 import re
-from typing import Tuple
 
 from sqlalchemy.ext.compiler import compiles
 from sqlalchemy.sql.functions import FunctionElement
-from sqlalchemy import BINARY, Float, Boolean, Text
+from sqlalchemy import Text
 
 logger = logging.getLogger(__name__)
 

pyobvector/json_table/virtual_data_type.py

@@ -2,7 +2,7 @@ from datetime import datetime
 from decimal import Decimal, InvalidOperation, ROUND_DOWN
 from enum import Enum
 from typing import Optional
-from typing_extensions import Annotated
+from typing import Annotated
 
 from pydantic import BaseModel, Field, AfterValidator, create_model
 

pyobvector/schema/array.py

@@ -1,6 +1,7 @@
 """ARRAY: An extended data type for SQLAlchemy"""
 import json
-from typing import Any, List, Optional, Sequence, Union
+from typing import Any, Optional, Union
+from collections.abc import Sequence
 
 from sqlalchemy.sql.type_api import TypeEngine
 from sqlalchemy.types import UserDefinedType, String
@@ -49,7 +50,7 @@ class ARRAY(UserDefinedType):
 
     def _validate_dimension(self, value: list[Any]):
         arr_depth = self._get_list_depth(value)
-        assert arr_depth == self.dim, "Array dimension mismatch, expected {}, got {}".format(self.dim, arr_depth)
+        assert arr_depth == self.dim, f"Array dimension mismatch, expected {self.dim}, got {arr_depth}"
 
     def bind_processor(self, dialect):
         item_type = self.item_type
@@ -58,7 +59,7 @@ class ARRAY(UserDefinedType):
 
         item_proc = item_type.dialect_impl(dialect).bind_processor(dialect)
 
-        def process(value: Optional[Sequence[Any] | str]) -> Optional[str]:
+        def process(value: Optional[Union[Sequence[Any] | str]]) -> Optional[str]:
             if value is None:
                 return None
             if isinstance(value, str):
@@ -85,7 +86,7 @@ class ARRAY(UserDefinedType):
 
         item_proc = item_type.dialect_impl(dialect).result_processor(dialect, coltype)
 
-        def process(value: Optional[str]) -> Optional[List[Any]]:
+        def process(value: Optional[str]) -> Optional[list[Any]]:
             if value is None:
                 return None
 

pyobvector/schema/geo_srid_point.py

@@ -1,5 +1,5 @@
 """Point: OceanBase GIS data type for SQLAlchemy"""
-from typing import Tuple, Optional
+from typing import Optional
 from sqlalchemy.types import UserDefinedType, String
 
 class POINT(UserDefinedType):
@@ -24,7 +24,7 @@ class POINT(UserDefinedType):
         return f"POINT SRID {self.srid}"
 
     @classmethod
-    def to_db(cls, value: Tuple[float, float]):
+    def to_db(cls, value: tuple[float, float]):
         """Parse tuple to POINT literal"""
         return f"POINT({value[0]} {value[1]})"
 

pyobvector/schema/gis_func.py

@@ -1,7 +1,6 @@
 """gis_func: An extended system function in GIS."""
 
 import logging
-from typing import Tuple
 
 from sqlalchemy.ext.compiler import compiles
 from sqlalchemy.sql.functions import FunctionElement
@@ -30,7 +29,7 @@ def compile_ST_GeomFromText(element, compiler, **kwargs): # pylint: disable=unus
     for idx, arg in enumerate(element.args):
         if idx == 0:
             if (
-                (not isinstance(arg, Tuple)) or
+                (not isinstance(arg, tuple)) or
                 (len(arg) != 2) or
                 (not all(isinstance(x, float) for x in arg))
             ):

pyobvector/schema/reflection.py

@@ -35,12 +35,12 @@ class OceanBaseTableDefinitionParser(MySQLTableDefinitionParser):
 
         self._re_array_column = _re_compile(
             r"\s*"
-            r"%(iq)s(?P<name>(?:%(esc_fq)s|[^%(fq)s])+)%(fq)s\s+"
+            r"{iq}(?P<name>(?:{esc_fq}|[^{fq}])+){fq}\s+"
             r"(?P<coltype_with_args>(?i:(?<!\w)array(?!\w))\s*\([^()]*(?:\([^()]*\)[^()]*)*\))"
             r"(?:\s+(?P<notnull>(?:NOT\s+)?NULL))?"
             r"(?:\s+DEFAULT\s+(?P<default>(?:NULL|'(?:''|[^'])*'|\(.+?\)|[\-\w\.\(\)]+)))?"
             r"(?:\s+COMMENT\s+'(?P<comment>(?:''|[^'])*)')?"
-            r"\s*,?\s*$" % quotes
+            r"\s*,?\s*$".format(**quotes)
         )
 
         self._re_key = _re_compile(

pyobvector/util/ob_version.py

@@ -1,6 +1,5 @@
 """OceanBase cluster version module."""
 import copy
-from typing import List
 
 
 class ObVersion:
@@ -9,7 +8,7 @@ class ObVersion:
     Attributes:
         version_nums (List[int]): version number of OceanBase cluster. For example, '4.3.3.0'
     """
-    def __init__(self, version_nums: List[int]):
+    def __init__(self, version_nums: list[int]):
         self.version_nums = copy.deepcopy(version_nums)
 
     @classmethod

{pyobvector-0.2.19.dist-info → pyobvector-0.2.21.dist-info}/METADATA

@@ -1,24 +1,20 @@
 Metadata-Version: 2.4
 Name: pyobvector
-Version: 0.2.19
+Version: 0.2.21
 Summary: A python SDK for OceanBase Vector Store, based on SQLAlchemy, compatible with Milvus API.
+Project-URL: Homepage, https://github.com/oceanbase/pyobvector
+Project-URL: Repository, https://github.com/oceanbase/pyobvector.git
+Author-email: "shanhaikang.shk" <shanhaikang.shk@oceanbase.com>
+License-Expression: Apache-2.0
 License-File: LICENSE
-Author: shanhaikang.shk
-Author-email: shanhaikang.shk@oceanbase.com
-Requires-Python: >=3.9,<4.0
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Programming Language :: Python :: 3.14
-Requires-Dist: aiomysql (>=0.3.2,<0.4.0)
-Requires-Dist: numpy (>=1.17.0)
-Requires-Dist: pydantic (>=2.7.0,<3)
-Requires-Dist: pymysql (>=1.1.1,<2.0.0)
-Requires-Dist: sqlalchemy (>=1.4,<=3)
-Requires-Dist: sqlglot (>=26.0.1)
+Keywords: obvector,oceanbase,vector store
+Requires-Python: >=3.9
+Requires-Dist: aiomysql>=0.3.2
+Requires-Dist: numpy>=1.17.0
+Requires-Dist: pydantic<3,>=2.7.0
+Requires-Dist: pymysql>=1.1.1
+Requires-Dist: sqlalchemy<=3,>=1.4
+Requires-Dist: sqlglot>=26.0.1
 Description-Content-Type: text/markdown
 
 # pyobvector
@@ -32,13 +28,13 @@ A python SDK for OceanBase Multimodal Store (Vector Store / Full Text Search / J
 - git clone this repo, then install with:
 
 ```shell
-poetry install
+uv sync
 ```
 
 - install with pip:
 
 ```shell
-pip install pyobvector==0.2.19
+pip install pyobvector==0.2.21
 ```
 
 ## Build Doc
@@ -234,17 +230,17 @@ res = self.client.ann_search(
 The `ann_search` method supports flexible output column selection through the `output_columns` parameter:
 
 - **`output_columns`** (recommended): Accepts SQLAlchemy Column objects, expressions, or a mix of both
-
+  
   - Column objects: `table.c.id`, `table.c.name`
   - Expressions: `(table.c.age + 10).label('age_plus_10')`
   - JSON queries: `text("JSON_EXTRACT(meta, '$.key') as extracted_key")`
   - String functions: `func.concat(table.c.name, ' (', table.c.age, ')').label('name_age')`
 - **`output_column_names`** (legacy): Accepts list of column name strings
-
+  
   - Example: `['id', 'name', 'meta']`
 - **Parameter Priority**: `output_columns` takes precedence over `output_column_names` when both are provided
 - **`distance_threshold`** (optional): Filter results by distance threshold
-
+  
   - Type: `Optional[float]`
   - Only returns results where `distance <= threshold`
   - Example: `distance_threshold=0.5` returns only results with distance <= 0.5

pyobvector-0.2.21.dist-info/RECORD

@@ -0,0 +1,40 @@
+pyobvector/__init__.py,sha256=5RtWI_ol3qxj_m7UXTQzByTmGZdIiQ0yyCyHZUhRDas,3888
+pyobvector/client/__init__.py,sha256=fDK2FVdSm3-XCwTqsam7zisic5UMhANUq97r29i27nc,2819
+pyobvector/client/collection_schema.py,sha256=lQTlanxhfZ0W74HUEB7XwvnkwJASxNSsxurXCvMv8nw,5532
+pyobvector/client/enum.py,sha256=3lPjSltITSE694-qOAP4yoX6fzCjKD4WAewmIxFs49o,139
+pyobvector/client/exceptions.py,sha256=UxU05Md2ZGFspZ8pd02B8EAhp8PBbOUJFopa28IwAHI,3777
+pyobvector/client/fts_index_param.py,sha256=owpjerUV4MIxB69dzwMsh7XIosgLB0OXgaLghV7wUYQ,2475
+pyobvector/client/hybrid_search.py,sha256=xctd-UMYPT4FTr2hWNf8dHWRyT0GAAqSDy3tz_oTP00,2565
+pyobvector/client/index_param.py,sha256=Tbu_-qg4SIXIzn1qpTg8Zl1L_RCXCUAEsZPKsA0LsNY,7062
+pyobvector/client/milvus_like_client.py,sha256=waOqsgGtc5FSEM-BECBGCa6m81d_Pxf1r40LFU-LrmE,27875
+pyobvector/client/ob_client.py,sha256=BsWCEGR30Klf2OUe88qLhBm7jRPBkgfjylQoy7B8EkM,16975
+pyobvector/client/ob_vec_client.py,sha256=65189GcKo4sj_494XLNhqed_vKyu4sTIp_Tv9-zgBcY,20235
+pyobvector/client/ob_vec_json_table_client.py,sha256=NFj7-1AQpTMk5XllecAgTKSGAq8qMIa36FM2cuhd_fQ,39605
+pyobvector/client/partitions.py,sha256=CfkSe0ftb0jbdgdvNF9_SvXxcDhpOoS3pe7ezMeNI0c,15615
+pyobvector/client/schema_type.py,sha256=gH2YiBsgkryo-R0GB_NYuRXMvzvrSjOamZTy6pwn2n0,1673
+pyobvector/json_table/__init__.py,sha256=X5MmK3f10oyJleUUFZJFeunMEfzmf6P1f_7094b-FZc,554
+pyobvector/json_table/json_value_returning_func.py,sha256=fW5Rk5vrVfyTPJPciPyb64A0CqSJBwBS-PYbcS9LhOY,1815
+pyobvector/json_table/oceanbase_dialect.py,sha256=lxpbWBQdK18LWXLmGyk_-ODv6VfnwGLHbcpsQMElOUo,4480
+pyobvector/json_table/virtual_data_type.py,sha256=ALffzZgByEwMsC-JdL_iEW3kwJcfqNGaNSIY645oUfo,3456
+pyobvector/schema/__init__.py,sha256=OMn7Cd2E8o_tm2ArbAXS_zRbiDW2sj7YKPLnbpmaueg,2405
+pyobvector/schema/array.py,sha256=YiGIyALN1_XxWuz9YyuiqhpyRN1DIu9n286vq6O09_U,4181
+pyobvector/schema/dialect.py,sha256=6D9A7Niqig2mwK7C8sP7mCP7kYr5be2jV0xqL87mlz4,1999
+pyobvector/schema/full_text_index.py,sha256=ohQX8uTPdRswEJONuN5A-bNv203d0N0b2BsJ7etx71g,2071
+pyobvector/schema/geo_srid_point.py,sha256=BZuiySoemvtLBPYoZ_BRQT4Gd7fcU1C2xdQfkxpb0OQ,1203
+pyobvector/schema/gis_func.py,sha256=sDhD701I45sRCXNY_E20ujjxe0ldAXofd6kTAhMW12g,3093
+pyobvector/schema/match_against_func.py,sha256=ExTQJvAXHaZwBo1Sjy6IlnF1nF6D9xGUsF4f7zaP8Q0,1336
+pyobvector/schema/ob_table.py,sha256=wlb6Oo9LG-sr8XnG_wbX1Qi5CgnS0XUzNL5qTdsncoY,392
+pyobvector/schema/reflection.py,sha256=guS74lW1wzBOCv5FWeXS1a_KnS-5Md9C_dYaNqiK2yA,5903
+pyobvector/schema/replace_stmt.py,sha256=FtGLXHz6DwzD0FOZPn1EZgXdbHZu-K9HIHS02rZqYrE,560
+pyobvector/schema/sparse_vector.py,sha256=ojqUrvKUnxQE8FErB2B58KO540otOJBqiPTMlwcUW2M,1061
+pyobvector/schema/vec_dist_func.py,sha256=4GAWSrhFNDYooBpbBg604wDrByPrewp46Y4VeoDxV7Y,2986
+pyobvector/schema/vector.py,sha256=dFKfPcTOto0jNxVjhvDmJM7Q4wwp6Z-HcZ3K6oZxUMc,1120
+pyobvector/schema/vector_index.py,sha256=D1ZnhJEObWUCd9ESO57KN1ctl10tkEIH_gV0kwGrvu8,2250
+pyobvector/util/__init__.py,sha256=-opvZ4Ya0ByTAhls06547-zW3vkdYRkUH6W5OCKUHD4,388
+pyobvector/util/ob_version.py,sha256=69me12REWn_T6oi7XjVAF_Dfq_iiaEVZjiHdjog57zs,1518
+pyobvector/util/sparse_vector.py,sha256=1IG0CRYfC2z39nGwuG43TImQkWiuPAXOlOnYqJ1hA-o,1275
+pyobvector/util/vector.py,sha256=58glSQqjOSTrGyNhUEIrs9r4F9oaYO_SdPNhMfbSnWs,2392
+pyobvector-0.2.21.dist-info/METADATA,sha256=uuBysjcnC3Xb8Nevi8MfkEgqTheVkjdHFKbTuMheld4,14120
+pyobvector-0.2.21.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+pyobvector-0.2.21.dist-info/licenses/LICENSE,sha256=WNHhf_5RCaeuKWyq_K39vmp9F28LxKsB4SpomwSZ2L0,11357
+pyobvector-0.2.21.dist-info/RECORD,,

{pyobvector-0.2.19.dist-info → pyobvector-0.2.21.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.2.1
+Generator: hatchling 1.28.0
 Root-Is-Purelib: true
 Tag: py3-none-any

pyobvector-0.2.19.dist-info/RECORD

@@ -1,40 +0,0 @@
-pyobvector/__init__.py,sha256=5RtWI_ol3qxj_m7UXTQzByTmGZdIiQ0yyCyHZUhRDas,3888
-pyobvector/client/__init__.py,sha256=fDK2FVdSm3-XCwTqsam7zisic5UMhANUq97r29i27nc,2819
-pyobvector/client/collection_schema.py,sha256=a7JQk83ZxMsvMDGt5CC_4lz2-skONqKgk-OGUz297hM,5538
-pyobvector/client/enum.py,sha256=3lPjSltITSE694-qOAP4yoX6fzCjKD4WAewmIxFs49o,139
-pyobvector/client/exceptions.py,sha256=CjoquSCc0H705MtvhpQW_F7_KaviYrKAHkndpF8sJx4,3777
-pyobvector/client/fts_index_param.py,sha256=UvU82p9_x444WAQMqhIUPHbqVHV5B3cFazje1Gw-slo,1105
-pyobvector/client/hybrid_search.py,sha256=xuD3CJh4jxm9EFjee6sx7zDGogvQT0qTni79F9Url7Q,2840
-pyobvector/client/index_param.py,sha256=Dg-FEFQPBRxb7qXChqoLgBSljpdJzF-C7ESUbG9x1mA,6926
-pyobvector/client/milvus_like_client.py,sha256=jHxB-ZmIGZiIDxEpurSlAKffiCF_KFNZP-14_vq1RQM,27887
-pyobvector/client/ob_client.py,sha256=csSRVWqbhnsaN2gj7FSwL7QExh4vbTx6EyqPznKRSz4,16172
-pyobvector/client/ob_vec_client.py,sha256=P6IMtsYxS_S78VsQtltK3UenW91iYfRKa0s1hIc8CI0,19916
-pyobvector/client/ob_vec_json_table_client.py,sha256=rq80AfqAKhosLcrBFROAoINVSkr-48xlRH91Jt4pEwA,39246
-pyobvector/client/partitions.py,sha256=Bxwr5yVNlXwZc7SXBC03NeqL9giy4Fe6S2qZdHD8xGw,15621
-pyobvector/client/schema_type.py,sha256=gH2YiBsgkryo-R0GB_NYuRXMvzvrSjOamZTy6pwn2n0,1673
-pyobvector/json_table/__init__.py,sha256=X5MmK3f10oyJleUUFZJFeunMEfzmf6P1f_7094b-FZc,554
-pyobvector/json_table/json_value_returning_func.py,sha256=NWSV2zhe2-1KhIprQaFqOH3vUVF46YaHIZUqX66WZKM,1864
-pyobvector/json_table/oceanbase_dialect.py,sha256=lxpbWBQdK18LWXLmGyk_-ODv6VfnwGLHbcpsQMElOUo,4480
-pyobvector/json_table/virtual_data_type.py,sha256=uQh6ZQ0UbwpVO9TFegGeu4E8bXW7rdLHAXFQJdiEjLs,3467
-pyobvector/schema/__init__.py,sha256=OMn7Cd2E8o_tm2ArbAXS_zRbiDW2sj7YKPLnbpmaueg,2405
-pyobvector/schema/array.py,sha256=WDWLZbCdu8stK8wlGWfKUjkhWifS8vbsfYUEEJsQOlQ,4163
-pyobvector/schema/dialect.py,sha256=6D9A7Niqig2mwK7C8sP7mCP7kYr5be2jV0xqL87mlz4,1999
-pyobvector/schema/full_text_index.py,sha256=ohQX8uTPdRswEJONuN5A-bNv203d0N0b2BsJ7etx71g,2071
-pyobvector/schema/geo_srid_point.py,sha256=RwEoCgGTmXDc0le1B2E3mZudtqiFdMf2M0Va1ocmVSY,1210
-pyobvector/schema/gis_func.py,sha256=u7bqaB5qIylW8GvRdglLQL2H1SheQZNnAqgZrOGyrks,3118
-pyobvector/schema/match_against_func.py,sha256=ExTQJvAXHaZwBo1Sjy6IlnF1nF6D9xGUsF4f7zaP8Q0,1336
-pyobvector/schema/ob_table.py,sha256=wlb6Oo9LG-sr8XnG_wbX1Qi5CgnS0XUzNL5qTdsncoY,392
-pyobvector/schema/reflection.py,sha256=orA0_lCdcIHw2TumtRCrAH3zG2yAWrGjXOmK5mK9XPw,5903
-pyobvector/schema/replace_stmt.py,sha256=FtGLXHz6DwzD0FOZPn1EZgXdbHZu-K9HIHS02rZqYrE,560
-pyobvector/schema/sparse_vector.py,sha256=ojqUrvKUnxQE8FErB2B58KO540otOJBqiPTMlwcUW2M,1061
-pyobvector/schema/vec_dist_func.py,sha256=4GAWSrhFNDYooBpbBg604wDrByPrewp46Y4VeoDxV7Y,2986
-pyobvector/schema/vector.py,sha256=dFKfPcTOto0jNxVjhvDmJM7Q4wwp6Z-HcZ3K6oZxUMc,1120
-pyobvector/schema/vector_index.py,sha256=D1ZnhJEObWUCd9ESO57KN1ctl10tkEIH_gV0kwGrvu8,2250
-pyobvector/util/__init__.py,sha256=-opvZ4Ya0ByTAhls06547-zW3vkdYRkUH6W5OCKUHD4,388
-pyobvector/util/ob_version.py,sha256=cWkQWoJkIxG6OEF9-gBwJK8LUorltHuKSVAb_NFkpdE,1542
-pyobvector/util/sparse_vector.py,sha256=1IG0CRYfC2z39nGwuG43TImQkWiuPAXOlOnYqJ1hA-o,1275
-pyobvector/util/vector.py,sha256=58glSQqjOSTrGyNhUEIrs9r4F9oaYO_SdPNhMfbSnWs,2392
-pyobvector-0.2.19.dist-info/METADATA,sha256=9r91zFxzOPl3zzhSy521IZKsVWl0oXXzVx7ELQFjsV4,14310
-pyobvector-0.2.19.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-pyobvector-0.2.19.dist-info/licenses/LICENSE,sha256=WNHhf_5RCaeuKWyq_K39vmp9F28LxKsB4SpomwSZ2L0,11357
-pyobvector-0.2.19.dist-info/RECORD,,