vectordb-bench 0.0.19__py3-none-any.whl → 0.0.21__py3-none-any.whl

vectordb_bench/backend/clients/alloydb/alloydb.py

@@ -1,9 +1,9 @@
 """Wrapper around the alloydb vector database over VectorDB"""
 
 import logging
-import pprint
+from collections.abc import Generator, Sequence
 from contextlib import contextmanager
-from typing import Any, Generator, Optional, Tuple, Sequence
+from typing import Any
 
 import numpy as np
 import psycopg
@@ -11,7 +11,7 @@ from pgvector.psycopg import register_vector
 from psycopg import Connection, Cursor, sql
 
 from ..api import VectorDB
-from .config import AlloyDBConfigDict, AlloyDBIndexConfig, AlloyDBScaNNConfig
+from .config import AlloyDBConfigDict, AlloyDBIndexConfig
 
 log = logging.getLogger(__name__)
 
@@ -56,13 +56,14 @@ class AlloyDB(VectorDB):
             (
                 self.case_config.create_index_before_load,
                 self.case_config.create_index_after_load,
-            )
+            ),
         ):
-            err = f"{self.name} config must create an index using create_index_before_load or create_index_after_load"
-            log.error(err)
-            raise RuntimeError(
-                f"{err}\n{pprint.pformat(self.db_config)}\n{pprint.pformat(self.case_config)}"
+            msg = (
+                f"{self.name} config must create an index using create_index_before_load or create_index_after_load"
+                "\n{pprint.pformat(self.db_config)}\n{pprint.pformat(self.case_config)}"
             )
+            log.warning(msg)
+            raise RuntimeError(msg)
 
         if drop_old:
             self._drop_index()
@@ -77,7 +78,7 @@ class AlloyDB(VectorDB):
         self.conn = None
 
     @staticmethod
-    def _create_connection(**kwargs) -> Tuple[Connection, Cursor]:
+    def _create_connection(**kwargs) -> tuple[Connection, Cursor]:
         conn = psycopg.connect(**kwargs)
         register_vector(conn)
         conn.autocommit = False
@@ -86,21 +87,20 @@ class AlloyDB(VectorDB):
         assert conn is not None, "Connection is not initialized"
         assert cursor is not None, "Cursor is not initialized"
         return conn, cursor
-    
-    def _generate_search_query(self, filtered: bool=False) -> sql.Composed:
-        search_query = sql.Composed(
+
+    def _generate_search_query(self, filtered: bool = False) -> sql.Composed:
+        return sql.Composed(
             [
                 sql.SQL(
-                    "SELECT id FROM public.{table_name} {where_clause} ORDER BY embedding "
+                    "SELECT id FROM public.{table_name} {where_clause} ORDER BY embedding ",
                 ).format(
                     table_name=sql.Identifier(self.table_name),
                     where_clause=sql.SQL("WHERE id >= %s") if filtered else sql.SQL(""),
                 ),
                 sql.SQL(self.case_config.search_param()["metric_fun_op"]),
                 sql.SQL(" %s::vector LIMIT %s::int"),
-            ]
+            ],
         )
-        return search_query
 
     @contextmanager
     def init(self) -> Generator[None, None, None]:
@@ -119,8 +119,8 @@ class AlloyDB(VectorDB):
         if len(session_options) > 0:
             for setting in session_options:
                 command = sql.SQL("SET {setting_name} " + "= {val};").format(
-                    setting_name=sql.Identifier(setting['parameter']['setting_name']),
-                    val=sql.Identifier(str(setting['parameter']['val'])),
+                    setting_name=sql.Identifier(setting["parameter"]["setting_name"]),
+                    val=sql.Identifier(str(setting["parameter"]["val"])),
                 )
                 log.debug(command.as_string(self.cursor))
                 self.cursor.execute(command)
@@ -144,15 +144,12 @@ class AlloyDB(VectorDB):
 
         self.cursor.execute(
             sql.SQL("DROP TABLE IF EXISTS public.{table_name}").format(
-                table_name=sql.Identifier(self.table_name)
-            )
+                table_name=sql.Identifier(self.table_name),
+            ),
         )
         self.conn.commit()
 
-    def ready_to_load(self):
-        pass
-
-    def optimize(self):
+    def optimize(self, data_size: int | None = None):
         self._post_insert()
 
     def _post_insert(self):
@@ -167,7 +164,7 @@ class AlloyDB(VectorDB):
         log.info(f"{self.name} client drop index : {self._index_name}")
 
         drop_index_sql = sql.SQL("DROP INDEX IF EXISTS {index_name}").format(
-            index_name=sql.Identifier(self._index_name)
+            index_name=sql.Identifier(self._index_name),
         )
         log.debug(drop_index_sql.as_string(self.cursor))
         self.cursor.execute(drop_index_sql)
@@ -181,78 +178,64 @@ class AlloyDB(VectorDB):
 
         if index_param["enable_pca"] is not None:
             self.cursor.execute(
-                sql.SQL("SET scann.enable_pca TO {};").format(
-                    index_param["enable_pca"]
-                )
+                sql.SQL("SET scann.enable_pca TO {};").format(index_param["enable_pca"]),
             )
             self.cursor.execute(
                 sql.SQL("ALTER USER {} SET scann.enable_pca TO {};").format(
                     sql.Identifier(self.db_config["user"]),
                     index_param["enable_pca"],
-                )
+                ),
             )
             self.conn.commit()
 
         if index_param["maintenance_work_mem"] is not None:
             self.cursor.execute(
                 sql.SQL("SET maintenance_work_mem TO {};").format(
-                    index_param["maintenance_work_mem"]
-                )
+                    index_param["maintenance_work_mem"],
+                ),
             )
             self.cursor.execute(
                 sql.SQL("ALTER USER {} SET maintenance_work_mem TO {};").format(
                     sql.Identifier(self.db_config["user"]),
                     index_param["maintenance_work_mem"],
-                )
+                ),
             )
             self.conn.commit()
 
         if index_param["max_parallel_workers"] is not None:
             self.cursor.execute(
                 sql.SQL("SET max_parallel_maintenance_workers TO '{}';").format(
-                    index_param["max_parallel_workers"]
-                )
+                    index_param["max_parallel_workers"],
+                ),
             )
             self.cursor.execute(
-                sql.SQL(
-                    "ALTER USER {} SET max_parallel_maintenance_workers TO '{}';"
-                ).format(
+                sql.SQL("ALTER USER {} SET max_parallel_maintenance_workers TO '{}';").format(
                     sql.Identifier(self.db_config["user"]),
                     index_param["max_parallel_workers"],
-                )
+                ),
             )
             self.cursor.execute(
                 sql.SQL("SET max_parallel_workers TO '{}';").format(
-                    index_param["max_parallel_workers"]
-                )
+                    index_param["max_parallel_workers"],
+                ),
             )
             self.cursor.execute(
-                sql.SQL(
-                    "ALTER USER {} SET max_parallel_workers TO '{}';"
-                ).format(
+                sql.SQL("ALTER USER {} SET max_parallel_workers TO '{}';").format(
                     sql.Identifier(self.db_config["user"]),
                     index_param["max_parallel_workers"],
-                )
+                ),
             )
             self.cursor.execute(
-                sql.SQL(
-                    "ALTER TABLE {} SET (parallel_workers = {});"
-                ).format(
+                sql.SQL("ALTER TABLE {} SET (parallel_workers = {});").format(
                     sql.Identifier(self.table_name),
                     index_param["max_parallel_workers"],
-                )
+                ),
             )
             self.conn.commit()
 
-        results = self.cursor.execute(
-            sql.SQL("SHOW max_parallel_maintenance_workers;")
-        ).fetchall()
-        results.extend(
-            self.cursor.execute(sql.SQL("SHOW max_parallel_workers;")).fetchall()
-        )
-        results.extend(
-            self.cursor.execute(sql.SQL("SHOW maintenance_work_mem;")).fetchall()
-        )
+        results = self.cursor.execute(sql.SQL("SHOW max_parallel_maintenance_workers;")).fetchall()
+        results.extend(self.cursor.execute(sql.SQL("SHOW max_parallel_workers;")).fetchall())
+        results.extend(self.cursor.execute(sql.SQL("SHOW maintenance_work_mem;")).fetchall())
         log.info(f"{self.name} parallel index creation parameters: {results}")
 
     def _create_index(self):
@@ -264,23 +247,20 @@ class AlloyDB(VectorDB):
         self._set_parallel_index_build_param()
         options = []
         for option in index_param["index_creation_with_options"]:
-            if option['val'] is not None:
+            if option["val"] is not None:
                 options.append(
                     sql.SQL("{option_name} = {val}").format(
-                        option_name=sql.Identifier(option['option_name']),
-                        val=sql.Identifier(str(option['val'])),
-                    )
+                        option_name=sql.Identifier(option["option_name"]),
+                        val=sql.Identifier(str(option["val"])),
+                    ),
                 )
-        if any(options):
-            with_clause = sql.SQL("WITH ({});").format(sql.SQL(", ").join(options))
-        else:
-            with_clause = sql.Composed(())
+        with_clause = sql.SQL("WITH ({});").format(sql.SQL(", ").join(options)) if any(options) else sql.Composed(())
 
         index_create_sql = sql.SQL(
             """
-            CREATE INDEX IF NOT EXISTS {index_name} ON public.{table_name} 
+            CREATE INDEX IF NOT EXISTS {index_name} ON public.{table_name}
             USING {index_type} (embedding {embedding_metric})
-            """
+            """,
         ).format(
             index_name=sql.Identifier(self._index_name),
             table_name=sql.Identifier(self.table_name),
@@ -288,9 +268,7 @@ class AlloyDB(VectorDB):
             embedding_metric=sql.Identifier(index_param["metric"]),
         )
 
-        index_create_sql_with_with_clause = (
-            index_create_sql + with_clause
-        ).join(" ")
+        index_create_sql_with_with_clause = (index_create_sql + with_clause).join(" ")
         log.debug(index_create_sql_with_with_clause.as_string(self.cursor))
         self.cursor.execute(index_create_sql_with_with_clause)
         self.conn.commit()
@@ -305,14 +283,12 @@ class AlloyDB(VectorDB):
             # create table
             self.cursor.execute(
                 sql.SQL(
-                    "CREATE TABLE IF NOT EXISTS public.{table_name} (id BIGINT PRIMARY KEY, embedding vector({dim}));"
-                ).format(table_name=sql.Identifier(self.table_name), dim=dim)
+                    "CREATE TABLE IF NOT EXISTS public.{table_name} (id BIGINT PRIMARY KEY, embedding vector({dim}));",
+                ).format(table_name=sql.Identifier(self.table_name), dim=dim),
             )
             self.conn.commit()
         except Exception as e:
-            log.warning(
-                f"Failed to create alloydb table: {self.table_name} error: {e}"
-            )
+            log.warning(f"Failed to create alloydb table: {self.table_name} error: {e}")
             raise e from None
 
     def insert_embeddings(
@@ -320,7 +296,7 @@ class AlloyDB(VectorDB):
         embeddings: list[list[float]],
         metadata: list[int],
         **kwargs: Any,
-    ) -> Tuple[int, Optional[Exception]]:
+    ) -> tuple[int, Exception | None]:
         assert self.conn is not None, "Connection is not initialized"
         assert self.cursor is not None, "Cursor is not initialized"
 
@@ -330,8 +306,8 @@ class AlloyDB(VectorDB):
 
             with self.cursor.copy(
                 sql.SQL("COPY public.{table_name} FROM STDIN (FORMAT BINARY)").format(
-                    table_name=sql.Identifier(self.table_name)
-                )
+                    table_name=sql.Identifier(self.table_name),
+                ),
             ) as copy:
                 copy.set_types(["bigint", "vector"])
                 for i, row in enumerate(metadata_arr):
@@ -343,9 +319,7 @@ class AlloyDB(VectorDB):
 
             return len(metadata), None
         except Exception as e:
-            log.warning(
-                f"Failed to insert data into alloydb table ({self.table_name}), error: {e}"
-            )
+            log.warning(f"Failed to insert data into alloydb table ({self.table_name}), error: {e}")
             return 0, e
 
     def search_embedding(
@@ -362,11 +336,12 @@ class AlloyDB(VectorDB):
         if filters:
             gt = filters.get("id")
             result = self.cursor.execute(
-                self._filtered_search, (gt, q, k), prepare=True, binary=True
+                self._filtered_search,
+                (gt, q, k),
+                prepare=True,
+                binary=True,
             )
         else:
-            result = self.cursor.execute(
-                self._unfiltered_search, (q, k), prepare=True, binary=True
-            )
+            result = self.cursor.execute(self._unfiltered_search, (q, k), prepare=True, binary=True)
 
         return [int(i[0]) for i in result.fetchall()]

vectordb_bench/backend/clients/alloydb/cli.py

@@ -1,10 +1,10 @@
-from typing import Annotated, Optional, TypedDict, Unpack
+import os
+from typing import Annotated, Unpack
 
 import click
-import os
 from pydantic import SecretStr
 
-from vectordb_bench.backend.clients.api import MetricType
+from vectordb_bench.backend.clients import DB
 
 from ....cli.cli import (
     CommonTypedDict,
@@ -13,31 +13,28 @@ from ....cli.cli import (
     get_custom_case_config,
     run,
 )
-from vectordb_bench.backend.clients import DB
 
 
 class AlloyDBTypedDict(CommonTypedDict):
     user_name: Annotated[
-        str, click.option("--user-name", type=str, help="Db username", required=True)
+        str,
+        click.option("--user-name", type=str, help="Db username", required=True),
     ]
     password: Annotated[
         str,
-        click.option("--password",
-                     type=str,
-                     help="Postgres database password",
-                     default=lambda: os.environ.get("POSTGRES_PASSWORD", ""),
-                     show_default="$POSTGRES_PASSWORD",
-                     ),
+        click.option(
+            "--password",
+            type=str,
+            help="Postgres database password",
+            default=lambda: os.environ.get("POSTGRES_PASSWORD", ""),
+            show_default="$POSTGRES_PASSWORD",
+        ),
     ]
 
-    host: Annotated[
-        str, click.option("--host", type=str, help="Db host", required=True)
-    ]
-    db_name: Annotated[
-        str, click.option("--db-name", type=str, help="Db name", required=True)
-    ]
+    host: Annotated[str, click.option("--host", type=str, help="Db host", required=True)]
+    db_name: Annotated[str, click.option("--db-name", type=str, help="Db name", required=True)]
     maintenance_work_mem: Annotated[
-        Optional[str],
+        str | None,
         click.option(
             "--maintenance-work-mem",
             type=str,
@@ -49,7 +46,7 @@ class AlloyDBTypedDict(CommonTypedDict):
         ),
     ]
     max_parallel_workers: Annotated[
-        Optional[int],
+        int | None,
         click.option(
             "--max-parallel-workers",
             type=int,
@@ -58,32 +55,51 @@ class AlloyDBTypedDict(CommonTypedDict):
         ),
     ]
 
-    
 
 class AlloyDBScaNNTypedDict(AlloyDBTypedDict):
     num_leaves: Annotated[
         int,
-        click.option("--num-leaves", type=int, help="Number of leaves", required=True)
+        click.option("--num-leaves", type=int, help="Number of leaves", required=True),
     ]
     num_leaves_to_search: Annotated[
         int,
-        click.option("--num-leaves-to-search", type=int, help="Number of leaves to search", required=True)
+        click.option(
+            "--num-leaves-to-search",
+            type=int,
+            help="Number of leaves to search",
+            required=True,
+        ),
     ]
     pre_reordering_num_neighbors: Annotated[
         int,
-        click.option("--pre-reordering-num-neighbors", type=int, help="Pre-reordering number of neighbors", default=200)
+        click.option(
+            "--pre-reordering-num-neighbors",
+            type=int,
+            help="Pre-reordering number of neighbors",
+            default=200,
+        ),
     ]
     max_top_neighbors_buffer_size: Annotated[
         int,
-        click.option("--max-top-neighbors-buffer-size", type=int, help="Maximum top neighbors buffer size", default=20_000)
+        click.option(
+            "--max-top-neighbors-buffer-size",
+            type=int,
+            help="Maximum top neighbors buffer size",
+            default=20_000,
+        ),
     ]
     num_search_threads: Annotated[
         int,
-        click.option("--num-search-threads", type=int, help="Number of search threads", default=2)
+        click.option("--num-search-threads", type=int, help="Number of search threads", default=2),
     ]
     max_num_prefetch_datasets: Annotated[
         int,
-        click.option("--max-num-prefetch-datasets", type=int, help="Maximum number of prefetch datasets", default=100)
+        click.option(
+            "--max-num-prefetch-datasets",
+            type=int,
+            help="Maximum number of prefetch datasets",
+            default=100,
+        ),
     ]
     quantizer: Annotated[
         str,
@@ -91,16 +107,17 @@ class AlloyDBScaNNTypedDict(AlloyDBTypedDict):
             "--quantizer",
             type=click.Choice(["SQ8", "FLAT"]),
             help="Quantizer type",
-            default="SQ8"
-        )
+            default="SQ8",
+        ),
     ]
     enable_pca: Annotated[
-        bool, click.option(
+        bool,
+        click.option(
             "--enable-pca",
             type=click.Choice(["on", "off"]),
             help="Enable PCA",
-            default="on"
-        )
+            default="on",
+        ),
     ]
     max_num_levels: Annotated[
         int,
@@ -108,8 +125,8 @@ class AlloyDBScaNNTypedDict(AlloyDBTypedDict):
             "--max-num-levels",
             type=click.Choice(["1", "2"]),
             help="Maximum number of levels",
-            default=1
-        )
+            default=1,
+        ),
     ]
 
 
@@ -144,4 +161,4 @@ def AlloyDBScaNN(
             maintenance_work_mem=parameters["maintenance_work_mem"],
         ),
         **parameters,
-    )
+    )

vectordb_bench/backend/clients/alloydb/config.py

@@ -1,7 +1,9 @@
 from abc import abstractmethod
-from typing import Any, Mapping, Optional, Sequence, TypedDict
+from collections.abc import Mapping, Sequence
+from typing import Any, LiteralString, TypedDict
+
 from pydantic import BaseModel, SecretStr
-from typing_extensions import LiteralString
+
 from ..api import DBCaseConfig, DBConfig, IndexType, MetricType
 
 POSTGRE_URL_PLACEHOLDER = "postgresql://%s:%s@%s/%s"
@@ -9,7 +11,7 @@ POSTGRE_URL_PLACEHOLDER = "postgresql://%s:%s@%s/%s"
 
 class AlloyDBConfigDict(TypedDict):
     """These keys will be directly used as kwargs in psycopg connection string,
-        so the names must match exactly psycopg API"""
+    so the names must match exactly psycopg API"""
 
     user: str
     password: str
@@ -41,8 +43,8 @@ class AlloyDBIndexParam(TypedDict):
     metric: str
     index_type: str
     index_creation_with_options: Sequence[dict[str, Any]]
-    maintenance_work_mem: Optional[str]
-    max_parallel_workers: Optional[int]
+    maintenance_work_mem: str | None
+    max_parallel_workers: int | None
 
 
 class AlloyDBSearchParam(TypedDict):
@@ -61,31 +63,30 @@ class AlloyDBIndexConfig(BaseModel, DBCaseConfig):
     def parse_metric(self) -> str:
         if self.metric_type == MetricType.L2:
             return "l2"
-        elif self.metric_type == MetricType.DP:
+        if self.metric_type == MetricType.DP:
             return "dot_product"
         return "cosine"
 
     def parse_metric_fun_op(self) -> LiteralString:
         if self.metric_type == MetricType.L2:
             return "<->"
-        elif self.metric_type == MetricType.IP:
+        if self.metric_type == MetricType.IP:
             return "<#>"
         return "<=>"
 
     @abstractmethod
-    def index_param(self) -> AlloyDBIndexParam:
-        ...
+    def index_param(self) -> AlloyDBIndexParam: ...
 
     @abstractmethod
-    def search_param(self) -> AlloyDBSearchParam:
-        ...
+    def search_param(self) -> AlloyDBSearchParam: ...
 
     @abstractmethod
-    def session_param(self) -> AlloyDBSessionCommands:
-        ...
+    def session_param(self) -> AlloyDBSessionCommands: ...
 
     @staticmethod
-    def _optionally_build_with_options(with_options: Mapping[str, Any]) -> Sequence[dict[str, Any]]:
+    def _optionally_build_with_options(
+        with_options: Mapping[str, Any],
+    ) -> Sequence[dict[str, Any]]:
         """Walk through mappings, creating a List of {key1 = value} pairs. That will be used to build a where clause"""
         options = []
         for option_name, value in with_options.items():
@@ -94,24 +95,25 @@ class AlloyDBIndexConfig(BaseModel, DBCaseConfig):
                     {
                         "option_name": option_name,
                         "val": str(value),
-                    }
+                    },
                 )
         return options
 
     @staticmethod
     def _optionally_build_set_options(
-        set_mapping: Mapping[str, Any]
+        set_mapping: Mapping[str, Any],
     ) -> Sequence[dict[str, Any]]:
         """Walk through options, creating 'SET 'key1 = "value1";' list"""
         session_options = []
         for setting_name, value in set_mapping.items():
             if value:
                 session_options.append(
-                    {"parameter": {
+                    {
+                        "parameter": {
                             "setting_name": setting_name,
                             "val": str(value),
                         },
-                    }
+                    },
                 )
         return session_options
 
@@ -124,22 +126,22 @@ class AlloyDBScaNNConfig(AlloyDBIndexConfig):
     max_num_levels: int | None
     num_leaves_to_search: int | None
     max_top_neighbors_buffer_size: int | None
-    pre_reordering_num_neighbors: int |  None
-    num_search_threads: int  | None
+    pre_reordering_num_neighbors: int | None
+    num_search_threads: int | None
     max_num_prefetch_datasets: int | None
-    maintenance_work_mem: Optional[str] = None
-    max_parallel_workers: Optional[int] = None
+    maintenance_work_mem: str | None = None
+    max_parallel_workers: int | None = None
 
     def index_param(self) -> AlloyDBIndexParam:
         index_parameters = {
-            "num_leaves": self.num_leaves, "max_num_levels": self.max_num_levels, "quantizer": self.quantizer,
+            "num_leaves": self.num_leaves,
+            "max_num_levels": self.max_num_levels,
+            "quantizer": self.quantizer,
         }
         return {
             "metric": self.parse_metric(),
             "index_type": self.index.value,
-            "index_creation_with_options": self._optionally_build_with_options(
-                index_parameters
-            ),
+            "index_creation_with_options": self._optionally_build_with_options(index_parameters),
             "maintenance_work_mem": self.maintenance_work_mem,
             "max_parallel_workers": self.max_parallel_workers,
             "enable_pca": self.enable_pca,
@@ -158,11 +160,9 @@ class AlloyDBScaNNConfig(AlloyDBIndexConfig):
             "scann.num_search_threads": self.num_search_threads,
             "scann.max_num_prefetch_datasets": self.max_num_prefetch_datasets,
         }
-        return {
-            "session_options": self._optionally_build_set_options(session_parameters)
-        }
+        return {"session_options": self._optionally_build_set_options(session_parameters)}
 
 
 _alloydb_case_config = {
-        IndexType.SCANN: AlloyDBScaNNConfig,
+    IndexType.SCANN: AlloyDBScaNNConfig,
 }