vectordb-bench 0.0.22__py3-none-any.whl → 0.0.24__py3-none-any.whl

vectordb_bench/backend/clients/mariadb/mariadb.py

@@ -0,0 +1,208 @@
+import logging
+from contextlib import contextmanager
+
+import mariadb
+import numpy as np
+
+from ..api import VectorDB
+from .config import MariaDBConfigDict, MariaDBIndexConfig
+
+log = logging.getLogger(__name__)
+
+
+class MariaDB(VectorDB):
+    def __init__(
+        self,
+        dim: int,
+        db_config: MariaDBConfigDict,
+        db_case_config: MariaDBIndexConfig,
+        collection_name: str = "vec_collection",
+        drop_old: bool = False,
+        **kwargs,
+    ):
+        self.name = "MariaDB"
+        self.db_config = db_config
+        self.case_config = db_case_config
+        self.db_name = "vectordbbench"
+        self.table_name = collection_name
+        self.dim = dim
+
+        # construct basic units
+        self.conn, self.cursor = self._create_connection(**self.db_config)
+
+        if drop_old:
+            self._drop_db()
+            self._create_db_table(dim)
+
+        self.cursor.close()
+        self.conn.close()
+        self.cursor = None
+        self.conn = None
+
+    @staticmethod
+    def _create_connection(**kwargs) -> tuple[mariadb.Connection, mariadb.Cursor]:
+        conn = mariadb.connect(**kwargs)
+        cursor = conn.cursor()
+
+        assert conn is not None, "Connection is not initialized"
+        assert cursor is not None, "Cursor is not initialized"
+
+        return conn, cursor
+
+    def _drop_db(self):
+        assert self.conn is not None, "Connection is not initialized"
+        assert self.cursor is not None, "Cursor is not initialized"
+        log.info(f"{self.name} client drop db : {self.db_name}")
+
+        # flush tables before dropping database to avoid some locking issue
+        self.cursor.execute("FLUSH TABLES")
+        self.cursor.execute(f"DROP DATABASE IF EXISTS {self.db_name}")
+        self.cursor.execute("COMMIT")
+        self.cursor.execute("FLUSH TABLES")
+
+    def _create_db_table(self, dim: int):
+        assert self.conn is not None, "Connection is not initialized"
+        assert self.cursor is not None, "Cursor is not initialized"
+
+        index_param = self.case_config.index_param()
+
+        try:
+            log.info(f"{self.name} client create database : {self.db_name}")
+            self.cursor.execute(f"CREATE DATABASE {self.db_name}")
+
+            log.info(f"{self.name} client create table : {self.table_name}")
+            self.cursor.execute(f"USE {self.db_name}")
+
+            self.cursor.execute(
+                f"""
+              CREATE TABLE {self.table_name} (
+                id INT PRIMARY KEY,
+                v VECTOR({self.dim}) NOT NULL
+              ) ENGINE={index_param["storage_engine"]}
+            """
+            )
+            self.cursor.execute("COMMIT")
+
+        except Exception as e:
+            log.warning(f"Failed to create table: {self.table_name} error: {e}")
+            raise e from None
+
+    @contextmanager
+    def init(self):
+        """create and destory connections to database.
+
+        Examples:
+            >>> with self.init():
+            >>>     self.insert_embeddings()
+        """
+        self.conn, self.cursor = self._create_connection(**self.db_config)
+
+        index_param = self.case_config.index_param()
+        search_param = self.case_config.search_param()
+
+        # maximize allowed package size
+        self.cursor.execute("SET GLOBAL max_allowed_packet = 1073741824")
+
+        if index_param["index_type"] == "HNSW":
+            if index_param["max_cache_size"] is not None:
+                self.cursor.execute(f"SET GLOBAL mhnsw_max_cache_size = {index_param['max_cache_size']}")
+            if search_param["ef_search"] is not None:
+                self.cursor.execute(f"SET mhnsw_ef_search = {search_param['ef_search']}")
+            self.cursor.execute("COMMIT")
+
+        self.insert_sql = f"INSERT INTO {self.db_name}.{self.table_name} (id, v) VALUES (%s, %s)"  # noqa: S608
+        self.select_sql = (
+            f"SELECT id FROM {self.db_name}.{self.table_name}"  # noqa: S608
+            f"ORDER by vec_distance_{search_param['metric_type']}(v, %s) LIMIT %d"
+        )
+        self.select_sql_with_filter = (
+            f"SELECT id FROM {self.db_name}.{self.table_name} WHERE id >= %d "  # noqa: S608
+            f"ORDER by vec_distance_{search_param['metric_type']}(v, %s) LIMIT %d"
+        )
+
+        try:
+            yield
+        finally:
+            self.cursor.close()
+            self.conn.close()
+            self.cursor = None
+            self.conn = None
+
+    def ready_to_load(self) -> bool:
+        pass
+
+    def optimize(self) -> None:
+        assert self.conn is not None, "Connection is not initialized"
+        assert self.cursor is not None, "Cursor is not initialized"
+
+        index_param = self.case_config.index_param()
+
+        try:
+            index_options = f"DISTANCE={index_param['metric_type']}"
+            if index_param["index_type"] == "HNSW" and index_param["M"] is not None:
+                index_options += f" M={index_param['M']}"
+
+            self.cursor.execute(
+                f"""
+              ALTER TABLE {self.db_name}.{self.table_name}
+              ADD VECTOR KEY v(v) {index_options}
+            """
+            )
+            self.cursor.execute("COMMIT")
+
+        except Exception as e:
+            log.warning(f"Failed to create index: {self.table_name} error: {e}")
+            raise e from None
+
+    @staticmethod
+    def vector_to_hex(v):  # noqa: ANN001
+        return np.array(v, "float32").tobytes()
+
+    def insert_embeddings(
+        self,
+        embeddings: list[list[float]],
+        metadata: list[int],
+        **kwargs,
+    ) -> tuple[int, Exception]:
+        """Insert embeddings into the database.
+        Should call self.init() first.
+        """
+        assert self.conn is not None, "Connection is not initialized"
+        assert self.cursor is not None, "Cursor is not initialized"
+
+        try:
+            metadata_arr = np.array(metadata)
+            embeddings_arr = np.array(embeddings)
+
+            batch_data = []
+            for i, row in enumerate(metadata_arr):
+                batch_data.append((int(row), self.vector_to_hex(embeddings_arr[i])))
+
+            self.cursor.executemany(self.insert_sql, batch_data)
+            self.cursor.execute("COMMIT")
+            self.cursor.execute("FLUSH TABLES")
+
+            return len(metadata), None
+        except Exception as e:
+            log.warning(f"Failed to insert data into Vector table ({self.table_name}), error: {e}")
+            return 0, e
+
+    def search_embedding(
+        self,
+        query: list[float],
+        k: int = 100,
+        filters: dict | None = None,
+        timeout: int | None = None,
+        **kwargs,
+    ) -> list[int]:
+        assert self.conn is not None, "Connection is not initialized"
+        assert self.cursor is not None, "Cursor is not initialized"
+
+        search_param = self.case_config.search_param()  # noqa: F841
+
+        if filters:
+            self.cursor.execute(self.select_sql_with_filter, (filters.get("id"), self.vector_to_hex(query), k))
+        else:
+            self.cursor.execute(self.select_sql, (self.vector_to_hex(query), k))
+
+        return [id for (id,) in self.cursor.fetchall()]  # noqa: A001

vectordb_bench/backend/clients/milvus/cli.py

@@ -195,6 +195,38 @@ def MilvusGPUIVFFlat(**parameters: Unpack[MilvusGPUIVFTypedDict]):
     )
 
 
+class MilvusGPUBruteForceTypedDict(CommonTypedDict, MilvusTypedDict):
+    metric_type: Annotated[
+        str,
+        click.option("--metric-type", type=str, required=True, help="Metric type for brute force search"),
+    ]
+    limit: Annotated[
+        int,
+        click.option("--limit", type=int, required=True, help="Top-k limit for search"),
+    ]
+
+
+@cli.command()
+@click_parameter_decorators_from_typed_dict(MilvusGPUBruteForceTypedDict)
+def MilvusGPUBruteForce(**parameters: Unpack[MilvusGPUBruteForceTypedDict]):
+    from .config import GPUBruteForceConfig, MilvusConfig
+
+    run(
+        db=DBTYPE,
+        db_config=MilvusConfig(
+            db_label=parameters["db_label"],
+            uri=SecretStr(parameters["uri"]),
+            user=parameters["user_name"],
+            password=SecretStr(parameters["password"]),
+        ),
+        db_case_config=GPUBruteForceConfig(
+            metric_type=parameters["metric_type"],
+            limit=parameters["limit"],  # top-k for search
+        ),
+        **parameters,
+    )
+
+
 class MilvusGPUIVFPQTypedDict(
     CommonTypedDict,
     MilvusTypedDict,

vectordb_bench/backend/clients/milvus/config.py

@@ -40,6 +40,7 @@ class MilvusIndexConfig(BaseModel):
             IndexType.GPU_CAGRA,
             IndexType.GPU_IVF_FLAT,
             IndexType.GPU_IVF_PQ,
+            IndexType.GPU_BRUTE_FORCE,
         ]
 
     def parse_metric(self) -> str:
@@ -184,6 +185,36 @@ class GPUIVFFlatConfig(MilvusIndexConfig, DBCaseConfig):
         }
 
 
+class GPUBruteForceConfig(MilvusIndexConfig, DBCaseConfig):
+    limit: int = 10  # Default top-k for search
+    metric_type: str  # Metric type (e.g., 'L2', 'IP', etc.)
+    index: IndexType = IndexType.GPU_BRUTE_FORCE  # Index type set to GPU_BRUTE_FORCE
+
+    def index_param(self) -> dict:
+        """
+        Returns the parameters for creating the GPU_BRUTE_FORCE index.
+        No additional parameters required for index building.
+        """
+        return {
+            "metric_type": self.parse_metric(),  # Metric type for distance calculation (L2, IP, etc.)
+            "index_type": self.index.value,  # GPU_BRUTE_FORCE index type
+            "params": {},  # No additional parameters for GPU_BRUTE_FORCE
+        }
+
+    def search_param(self) -> dict:
+        """
+        Returns the parameters for performing a search on the GPU_BRUTE_FORCE index.
+        Only metric_type and top-k (limit) are needed for search.
+        """
+        return {
+            "metric_type": self.parse_metric(),  # Metric type for search
+            "params": {
+                "nprobe": 1,  # For GPU_BRUTE_FORCE, set nprobe to 1 (brute force search)
+                "limit": self.limit,  # Top-k for search
+            },
+        }
+
+
 class GPUIVFPQConfig(MilvusIndexConfig, DBCaseConfig):
     nlist: int = 1024
     m: int = 0
@@ -261,4 +292,5 @@ _milvus_case_config = {
     IndexType.GPU_IVF_FLAT: GPUIVFFlatConfig,
     IndexType.GPU_IVF_PQ: GPUIVFPQConfig,
     IndexType.GPU_CAGRA: GPUCAGRAConfig,
+    IndexType.GPU_BRUTE_FORCE: GPUBruteForceConfig,
 }

vectordb_bench/backend/clients/milvus/milvus.py

@@ -155,7 +155,7 @@ class Milvus(VectorDB):
         embeddings: Iterable[list[float]],
         metadata: list[int],
         **kwargs,
-    ) -> (int, Exception):
+    ) -> tuple[int, Exception]:
         """Insert embeddings into Milvus. should call self.init() first"""
         # use the first insert_embeddings to init collection
         assert self.col is not None

vectordb_bench/backend/clients/pgvector/cli.py

@@ -18,8 +18,7 @@ from ....cli.cli import (
 )
 
 
-# ruff: noqa
-def set_default_quantized_fetch_limit(ctx: any, param: any, value: any):
+def set_default_quantized_fetch_limit(ctx: any, param: any, value: any):  # noqa: ARG001
     if ctx.params.get("reranking") and value is None:
         # ef_search is the default value for quantized_fetch_limit as it's bound by ef_search.
         # 100 is default value for quantized_fetch_limit for IVFFlat.
@@ -82,7 +81,17 @@ class PgVectorTypedDict(CommonTypedDict):
         click.option(
             "--quantization-type",
             type=click.Choice(["none", "bit", "halfvec"]),
-            help="quantization type for vectors",
+            help="quantization type for vectors (in index)",
+            required=False,
+        ),
+    ]
+    table_quantization_type: Annotated[
+        str | None,
+        click.option(
+            "--table-quantization-type",
+            type=click.Choice(["none", "bit", "halfvec"]),
+            help="quantization type for vectors (in table). "
+            "If equal to bit, the parameter quantization_type will be set to bit too.",
             required=False,
         ),
     ]
@@ -146,6 +155,7 @@ def PgVectorIVFFlat(
             lists=parameters["lists"],
             probes=parameters["probes"],
             quantization_type=parameters["quantization_type"],
+            table_quantization_type=parameters["table_quantization_type"],
             reranking=parameters["reranking"],
             reranking_metric=parameters["reranking_metric"],
             quantized_fetch_limit=parameters["quantized_fetch_limit"],
@@ -182,6 +192,7 @@ def PgVectorHNSW(
             maintenance_work_mem=parameters["maintenance_work_mem"],
             max_parallel_workers=parameters["max_parallel_workers"],
             quantization_type=parameters["quantization_type"],
+            table_quantization_type=parameters["table_quantization_type"],
             reranking=parameters["reranking"],
             reranking_metric=parameters["reranking_metric"],
             quantized_fetch_limit=parameters["quantized_fetch_limit"],

vectordb_bench/backend/clients/pgvector/config.py

@@ -80,7 +80,12 @@ class PgVectorIndexConfig(BaseModel, DBCaseConfig):
 
         if d.get(self.quantization_type) is None:
             return d.get("_fallback").get(self.metric_type)
-        return d.get(self.quantization_type).get(self.metric_type)
+        metric = d.get(self.quantization_type).get(self.metric_type)
+        # If using binary quantization for the index, use a bit metric
+        # no matter what metric was selected for vector or halfvec data
+        if self.quantization_type == "bit" and metric is None:
+            return "bit_hamming_ops"
+        return metric
 
     def parse_metric_fun_op(self) -> LiteralString:
         if self.quantization_type == "bit":
@@ -168,14 +173,19 @@ class PgVectorIVFFlatConfig(PgVectorIndexConfig):
     maintenance_work_mem: str | None = None
     max_parallel_workers: int | None = None
     quantization_type: str | None = None
+    table_quantization_type: str | None
     reranking: bool | None = None
     quantized_fetch_limit: int | None = None
     reranking_metric: str | None = None
 
     def index_param(self) -> PgVectorIndexParam:
         index_parameters = {"lists": self.lists}
-        if self.quantization_type == "none":
-            self.quantization_type = None
+        if self.quantization_type == "none" or self.quantization_type is None:
+            self.quantization_type = "vector"
+        if self.table_quantization_type == "none" or self.table_quantization_type is None:
+            self.table_quantization_type = "vector"
+        if self.table_quantization_type == "bit":
+            self.quantization_type = "bit"
         return {
             "metric": self.parse_metric(),
             "index_type": self.index.value,
@@ -183,6 +193,7 @@ class PgVectorIVFFlatConfig(PgVectorIndexConfig):
             "maintenance_work_mem": self.maintenance_work_mem,
             "max_parallel_workers": self.max_parallel_workers,
             "quantization_type": self.quantization_type,
+            "table_quantization_type": self.table_quantization_type,
         }
 
     def search_param(self) -> PgVectorSearchParam:
@@ -212,14 +223,19 @@ class PgVectorHNSWConfig(PgVectorIndexConfig):
     maintenance_work_mem: str | None = None
     max_parallel_workers: int | None = None
     quantization_type: str | None = None
+    table_quantization_type: str | None
     reranking: bool | None = None
     quantized_fetch_limit: int | None = None
     reranking_metric: str | None = None
 
     def index_param(self) -> PgVectorIndexParam:
         index_parameters = {"m": self.m, "ef_construction": self.ef_construction}
-        if self.quantization_type == "none":
-            self.quantization_type = None
+        if self.quantization_type == "none" or self.quantization_type is None:
+            self.quantization_type = "vector"
+        if self.table_quantization_type == "none" or self.table_quantization_type is None:
+            self.table_quantization_type = "vector"
+        if self.table_quantization_type == "bit":
+            self.quantization_type = "bit"
         return {
             "metric": self.parse_metric(),
             "index_type": self.index.value,
@@ -227,6 +243,7 @@ class PgVectorHNSWConfig(PgVectorIndexConfig):
             "maintenance_work_mem": self.maintenance_work_mem,
             "max_parallel_workers": self.max_parallel_workers,
             "quantization_type": self.quantization_type,
+            "table_quantization_type": self.table_quantization_type,
         }
 
     def search_param(self) -> PgVectorSearchParam:

vectordb_bench/backend/clients/pgvector/pgvector.py

@@ -94,7 +94,7 @@ class PgVector(VectorDB):
         reranking = self.case_config.search_param()["reranking"]
         column_name = (
             sql.SQL("binary_quantize({0})").format(sql.Identifier("embedding"))
-            if index_param["quantization_type"] == "bit"
+            if index_param["quantization_type"] == "bit" and index_param["table_quantization_type"] != "bit"
             else sql.SQL("embedding")
         )
         search_vector = (
@@ -104,7 +104,8 @@ class PgVector(VectorDB):
         )
 
         # The following sections assume that the quantization_type value matches the quantization function name
-        if index_param["quantization_type"] is not None:
+        if index_param["quantization_type"] != index_param["table_quantization_type"]:
+            # Reranking makes sense only if table quantization is not "bit"
             if index_param["quantization_type"] == "bit" and reranking:
                 # Embeddings needs to be passed to binary_quantize function if quantization_type is bit
                 search_query = sql.Composed(
@@ -113,7 +114,7 @@ class PgVector(VectorDB):
                             """
                             SELECT i.id
                             FROM (
-                                SELECT id, embedding {reranking_metric_fun_op} %s::vector AS distance
+                                SELECT id, embedding {reranking_metric_fun_op} %s::{table_quantization_type} AS distance
                                 FROM public.{table_name} {where_clause}
                                 ORDER BY {column_name}::{quantization_type}({dim})
                             """,
@@ -123,6 +124,8 @@ class PgVector(VectorDB):
                             reranking_metric_fun_op=sql.SQL(
                                 self.case_config.search_param()["reranking_metric_fun_op"],
                             ),
+                            search_vector=search_vector,
+                            table_quantization_type=sql.SQL(index_param["table_quantization_type"]),
                             quantization_type=sql.SQL(index_param["quantization_type"]),
                             dim=sql.Literal(self.dim),
                             where_clause=sql.SQL("WHERE id >= %s") if filtered else sql.SQL(""),
@@ -130,7 +133,7 @@ class PgVector(VectorDB):
                         sql.SQL(self.case_config.search_param()["metric_fun_op"]),
                         sql.SQL(
                             """
-                                {search_vector}
+                                {search_vector}::{quantization_type}({dim})
                                 LIMIT {quantized_fetch_limit}
                             ) i
                             ORDER BY i.distance
@@ -138,6 +141,8 @@ class PgVector(VectorDB):
                             """,
                         ).format(
                             search_vector=search_vector,
+                            quantization_type=sql.SQL(index_param["quantization_type"]),
+                            dim=sql.Literal(self.dim),
                             quantized_fetch_limit=sql.Literal(
                                 self.case_config.search_param()["quantized_fetch_limit"],
                             ),
@@ -160,10 +165,12 @@ class PgVector(VectorDB):
                             where_clause=sql.SQL("WHERE id >= %s") if filtered else sql.SQL(""),
                         ),
                         sql.SQL(self.case_config.search_param()["metric_fun_op"]),
-                        sql.SQL(" {search_vector} LIMIT %s::int").format(
+                        sql.SQL(" {search_vector}::{quantization_type}({dim}) LIMIT %s::int").format(
                             search_vector=search_vector,
+                            quantization_type=sql.SQL(index_param["quantization_type"]),
+                            dim=sql.Literal(self.dim),
                         ),
-                    ],
+                    ]
                 )
         else:
             search_query = sql.Composed(
@@ -175,8 +182,12 @@ class PgVector(VectorDB):
                         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"),
-                ],
+                    sql.SQL(" {search_vector}::{quantization_type}({dim}) LIMIT %s::int").format(
+                        search_vector=search_vector,
+                        quantization_type=sql.SQL(index_param["quantization_type"]),
+                        dim=sql.Literal(self.dim),
+                    ),
+                ]
             )
 
         return search_query
@@ -323,7 +334,7 @@ class PgVector(VectorDB):
                 )
         with_clause = sql.SQL("WITH ({});").format(sql.SQL(", ").join(options)) if any(options) else sql.Composed(())
 
-        if index_param["quantization_type"] is not None:
+        if index_param["quantization_type"] != index_param["table_quantization_type"]:
             index_create_sql = sql.SQL(
                 """
                 CREATE INDEX IF NOT EXISTS {index_name} ON public.{table_name}
@@ -365,14 +376,23 @@ class PgVector(VectorDB):
         assert self.conn is not None, "Connection is not initialized"
         assert self.cursor is not None, "Cursor is not initialized"
 
+        index_param = self.case_config.index_param()
+
         try:
             log.info(f"{self.name} client create table : {self.table_name}")
 
             # 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 {table_quantization_type}({dim}));
+                    """
+                ).format(
+                    table_name=sql.Identifier(self.table_name),
+                    table_quantization_type=sql.SQL(index_param["table_quantization_type"]),
+                    dim=dim,
+                )
             )
             self.cursor.execute(
                 sql.SQL(
@@ -393,18 +413,41 @@ class PgVector(VectorDB):
         assert self.conn is not None, "Connection is not initialized"
         assert self.cursor is not None, "Cursor is not initialized"
 
+        index_param = self.case_config.index_param()
+
         try:
             metadata_arr = np.array(metadata)
             embeddings_arr = np.array(embeddings)
 
-            with self.cursor.copy(
-                sql.SQL("COPY public.{table_name} FROM STDIN (FORMAT BINARY)").format(
-                    table_name=sql.Identifier(self.table_name),
-                ),
-            ) as copy:
-                copy.set_types(["bigint", "vector"])
-                for i, row in enumerate(metadata_arr):
-                    copy.write_row((row, embeddings_arr[i]))
+            if index_param["table_quantization_type"] == "bit":
+                with self.cursor.copy(
+                    sql.SQL("COPY public.{table_name} FROM STDIN (FORMAT TEXT)").format(
+                        table_name=sql.Identifier(self.table_name)
+                    )
+                ) as copy:
+                    # Same logic as pgvector binary_quantize
+                    for i, row in enumerate(metadata_arr):
+                        embeddings_bit = ""
+                        for embedding in embeddings_arr[i]:
+                            if embedding > 0:
+                                embeddings_bit += "1"
+                            else:
+                                embeddings_bit += "0"
+                        copy.write_row((str(row), embeddings_bit))
+            else:
+                with self.cursor.copy(
+                    sql.SQL("COPY public.{table_name} FROM STDIN (FORMAT BINARY)").format(
+                        table_name=sql.Identifier(self.table_name)
+                    )
+                ) as copy:
+                    if index_param["table_quantization_type"] == "halfvec":
+                        copy.set_types(["bigint", "halfvec"])
+                        for i, row in enumerate(metadata_arr):
+                            copy.write_row((row, np.float16(embeddings_arr[i])))
+                    else:
+                        copy.set_types(["bigint", "vector"])
+                        for i, row in enumerate(metadata_arr):
+                            copy.write_row((row, embeddings_arr[i]))
             self.conn.commit()
 
             if kwargs.get("last_batch"):

vectordb_bench/backend/clients/pinecone/pinecone.py

@@ -67,7 +67,7 @@ class Pinecone(VectorDB):
         embeddings: list[list[float]],
         metadata: list[int],
         **kwargs,
-    ) -> (int, Exception):
+    ) -> tuple[int, Exception]:
         assert len(embeddings) == len(metadata)
         insert_count = 0
         try:

vectordb_bench/backend/clients/qdrant_cloud/config.py

@@ -1,4 +1,4 @@
-from pydantic import BaseModel, SecretStr, validator
+from pydantic import BaseModel, SecretStr
 
 from ..api import DBCaseConfig, DBConfig, MetricType
 
@@ -20,14 +20,6 @@ class QdrantConfig(DBConfig):
             "url": self.url.get_secret_value(),
         }
 
-    @validator("*")
-    def not_empty_field(cls, v: any, field: any):
-        if field.name in ["api_key", "db_label"]:
-            return v
-        if isinstance(v, str | SecretStr) and len(v) == 0:
-            raise ValueError("Empty string!")
-        return v
-
 
 class QdrantIndexConfig(BaseModel, DBCaseConfig):
     metric_type: MetricType | None = None

vectordb_bench/backend/clients/qdrant_cloud/qdrant_cloud.py

@@ -111,7 +111,7 @@ class QdrantCloud(VectorDB):
         embeddings: list[list[float]],
         metadata: list[int],
         **kwargs,
-    ) -> (int, Exception):
+    ) -> tuple[int, Exception]:
         """Insert embeddings into Milvus. should call self.init() first"""
         assert self.qdrant_client is not None
         try: