Support MariaDB database

pyproject.toml

@@ -68,6 +68,7 @@ all = [
     "memorydb",
     "alibabacloud_ha3engine_vector",
     "alibabacloud_searchengine20211025",
+    "mariadb",
 ]
 
 qdrant          = [ "qdrant-client" ]
@@ -86,6 +87,7 @@ chromadb        = [ "chromadb" ]
 opensearch      = [ "opensearch-py" ]
 aliyun_opensearch = [ "alibabacloud_ha3engine_vector", "alibabacloud_searchengine20211025"]
 mongodb         = [ "pymongo" ]
+mariadb = [ "mariadb" ]
 
 [project.urls]
 "repository" = "https://github.com/zilliztech/VectorDBBench"

vectordb_bench/backend/clients/__init__.py

@@ -38,6 +38,7 @@ class DB(Enum):
     Chroma = "Chroma"
     AWSOpenSearch = "OpenSearch"
     AliyunElasticsearch = "AliyunElasticsearch"
+    MariaDB = "MariaDB"
     Test = "test"
     AliyunOpenSearch = "AliyunOpenSearch"
     MongoDB = "MongoDB"
@@ -135,6 +136,11 @@ def init_cls(self) -> type[VectorDB]:  # noqa: PLR0911, PLR0912, C901
 
             return MongoDB
 
+        if self == DB.MariaDB:
+            from .mariadb.mariadb import MariaDB
+
+            return MariaDB
+
         if self == DB.Test:
             from .test.test import Test
 
@@ -236,6 +242,10 @@ def config_cls(self) -> type[DBConfig]:  # noqa: PLR0911, PLR0912, C901
 
             return MongoDBConfig
 
+        if self == DB.MariaDB:
+            from .mariadb.config import MariaDBConfig
+            return MariaDBConfig
+
         if self == DB.Test:
             from .test.config import TestConfig
 
@@ -318,6 +328,11 @@ def case_config_cls(  # noqa: PLR0911
 
             return MongoDBIndexConfig
 
+        if self == DB.MariaDB:
+            from .mariadb.config import _mariadb_case_config
+
+            return _mariadb_case_config.get(index_type)
+
         # DB.Pinecone, DB.Chroma, DB.Redis
         return EmptyDBCaseConfig
 

vectordb_bench/backend/clients/mariadb/cli.py

@@ -0,0 +1,107 @@
+from typing import Annotated, Optional, Unpack
+
+import click
+import os
+from pydantic import SecretStr
+
+from ....cli.cli import (
+    CommonTypedDict,
+    HNSWFlavor1,
+    cli,
+    click_parameter_decorators_from_typed_dict,
+    run,
+)
+from vectordb_bench.backend.clients import DB
+
+
+class MariaDBTypedDict(CommonTypedDict):
+    user_name: Annotated[
+        str, click.option("--username",
+                          type=str,
+                          help="Username",
+                          required=True,
+                          ),
+    ]
+    password: Annotated[
+        str, click.option("--password",
+                     type=str,
+                     help="Password",
+                     required=True,
+                     ),
+    ]
+
+    host: Annotated[
+        str, click.option("--host",
+                          type=str,
+                          help="Db host",
+                          default="127.0.0.1",
+                          ),
+    ]
+
+    port: Annotated[
+        int, click.option("--port",
+                          type=int,
+                          default=3306,
+                          help="Db Port",
+                          ),
+    ]
+
+    storage_engine: Annotated[
+        int, click.option("--storage-engine",
+                          type=click.Choice(["InnoDB", "MyISAM"]),
+                          help="DB storage engine",
+                          required=True,
+                          ),
+    ]
+
+class MariaDBHNSWTypedDict(MariaDBTypedDict):
+    ...
+    m: Annotated[
+        Optional[int], click.option("--m",
+                                    type=int,
+                                    help="M parameter in MHNSW vector indexing",
+                                    required=False,
+                                    ),
+    ]
+
+    ef_search: Annotated[
+        Optional[int], click.option("--ef-search",
+                                    type=int,
+                                    help="MariaDB system variable mhnsw_min_limit",
+                                    required=False,
+                                    ),
+    ]
+
+    max_cache_size: Annotated[
+        Optional[int], click.option("--max-cache-size",
+                                    type=int,
+                                    help="MariaDB system variable mhnsw_max_cache_size",
+                                    required=False,
+                                    ),
+    ]
+
+
+@cli.command()
+@click_parameter_decorators_from_typed_dict(MariaDBHNSWTypedDict)
+def MariaDBHNSW(
+    **parameters: Unpack[MariaDBHNSWTypedDict],
+):
+    from .config import MariaDBConfig, MariaDBHNSWConfig
+
+    run(
+        db=DB.MariaDB,
+        db_config=MariaDBConfig(
+            db_label=parameters["db_label"],
+            user_name=parameters["username"],
+            password=SecretStr(parameters["password"]),
+            host=parameters["host"],
+            port=parameters["port"],
+        ),
+        db_case_config=MariaDBHNSWConfig(
+            M=parameters["m"],
+            ef_search=parameters["ef_search"],
+            storage_engine=parameters["storage_engine"],
+            max_cache_size=parameters["max_cache_size"],
+        ),
+        **parameters,
+    )

vectordb_bench/backend/clients/mariadb/config.py

@@ -0,0 +1,71 @@
+from pydantic import SecretStr, BaseModel
+from typing import TypedDict
+from ..api import DBConfig, DBCaseConfig, MetricType, IndexType
+
+class MariaDBConfigDict(TypedDict):
+    """These keys will be directly used as kwargs in mariadb connection string,
+        so the names must match exactly mariadb API"""
+
+    user: str
+    password: str
+    host: str
+    port: int
+
+
+class MariaDBConfig(DBConfig):
+    user_name: str = "root"
+    password: SecretStr
+    host: str = "127.0.0.1"
+    port: int = 3306
+
+    def to_dict(self) -> MariaDBConfigDict:
+        pwd_str = self.password.get_secret_value()
+        return {
+            "host": self.host,
+            "port": self.port,
+            "user": self.user_name,
+            "password": pwd_str,
+        }
+
+
+class MariaDBIndexConfig(BaseModel):
+    """Base config for MariaDB"""
+
+    metric_type: MetricType | None = None
+
+    def parse_metric(self) -> str:
+        if self.metric_type == MetricType.L2:
+            return "euclidean"
+        elif self.metric_type == MetricType.COSINE:
+            return "cosine"
+        else:
+            raise ValueError(f"Metric type {self.metric_type} is not supported!")
+
+class MariaDBHNSWConfig(MariaDBIndexConfig, DBCaseConfig):
+    M: int | None
+    ef_search: int | None
+    index: IndexType = IndexType.HNSW
+    storage_engine: str = "InnoDB"
+    max_cache_size: int | None
+
+    def index_param(self) -> dict:
+        return {
+            "storage_engine": self.storage_engine,
+            "metric_type": self.parse_metric(),
+            "index_type": self.index.value,
+            "M": self.M,
+            "max_cache_size": self.max_cache_size,
+        }
+
+    def search_param(self) -> dict:
+        return {
+            "metric_type": self.parse_metric(),
+            "ef_search": self.ef_search,
+        }
+
+
+_mariadb_case_config = {
+        IndexType.HNSW: MariaDBHNSWConfig,
+}
+
+