Merge branch 'zilliztech:main' into aliyun_elasticsearch

README.md

@@ -29,21 +29,19 @@ All the database client supported
 
 | Optional database client | install command                             |
 |--------------------------|---------------------------------------------|
-| pymilvus(*default*)      | `pip install vectordb-bench`                |
-| all                      | `pip install vectordb-bench[all]`           |
+| pymilvus, zilliz_cloud (*default*)     | `pip install vectordb-bench`                |
+| all (*clients requirements might be conflict with each other*) | `pip install vectordb-bench[all]`           |
 | qdrant                   | `pip install vectordb-bench[qdrant]`        |
 | pinecone                 | `pip install vectordb-bench[pinecone]`      |
 | weaviate                 | `pip install vectordb-bench[weaviate]`      |
-| elastic                  | `pip install vectordb-bench[elastic]`       |
-| pgvector                 | `pip install vectordb-bench[pgvector]`      |
+| elastic, aliyun_elasticsearch| `pip install vectordb-bench[elastic]`       |
+| pgvector, pgvectorscale, pgdiskann, alloydb | `pip install vectordb-bench[pgvector]`      |
 | pgvecto.rs               | `pip install vectordb-bench[pgvecto_rs]`    |
-| pgvectorscale            | `pip install vectordb-bench[pgvectorscale]` |
-| pgdiskann                | `pip install vectordb-bench[pgdiskann]`     |
 | redis                    | `pip install vectordb-bench[redis]`         |
 | memorydb                 | `pip install vectordb-bench[memorydb]`      |
 | chromadb                 | `pip install vectordb-bench[chromadb]`      |
-| awsopensearch            | `pip install vectordb-bench[awsopensearch]` |
-| alloydb                  | `pip install vectordb-bench[alloydb]`       |
+| awsopensearch            | `pip install vectordb-bench[opensearch]` |
+| aliyun_opensearch        | `pip install vectordb-bench[aliyun_opensearch]` |
 
 ### Run
 

pyproject.toml

@@ -55,31 +55,35 @@ all = [
     "pinecone-client",
     "weaviate-client",
     "elasticsearch",
-    "pgvector",
-    "pgvecto_rs[psycopg3]>=0.2.2",
     "sqlalchemy",
     "redis",
     "chromadb",
+    "pgvector",
     "psycopg",
     "psycopg-binary",
-    "opensearch-dsl==2.1.0",
-    "opensearch-py==2.6.0",
+    "pgvecto_rs[psycopg3]>=0.2.2",
+    "opensearch-dsl",
+    "opensearch-py",
+    "memorydb",
+    "alibabacloud_ha3engine_vector",
+    "alibabacloud_searchengine20211025",
 ]
 
-qdrant = [ "qdrant-client" ]
-pinecone = [ "pinecone-client" ]
-weaviate = [ "weaviate-client" ]
-elastic = [ "elasticsearch" ]
-pgvector = [ "psycopg", "psycopg-binary", "pgvector" ]
-pgvectorscale = [ "psycopg", "psycopg-binary", "pgvector" ]
-pgdiskann = [ "psycopg", "psycopg-binary", "pgvector" ]
-alloydb = [ "psycopg", "psycopg-binary", "pgvector"]
-pgvecto_rs = [ "pgvecto_rs[psycopg3]>=0.2.2" ]
-redis = [ "redis" ]
-memorydb = [ "memorydb" ]
-chromadb = [ "chromadb" ]
-awsopensearch = [ "awsopensearch" ]
-zilliz_cloud = []
+qdrant          = [ "qdrant-client" ]
+pinecone        = [ "pinecone-client" ]
+weaviate        = [ "weaviate-client" ]
+elastic         = [ "elasticsearch" ]
+# For elastic and aliyun_elasticsearch
+
+pgvector        = [ "psycopg", "psycopg-binary", "pgvector" ]
+# for pgvector, pgvectorscale, pgdiskann, and, alloydb
+
+pgvecto_rs      = [ "pgvecto_rs[psycopg3]>=0.2.2" ]
+redis           = [ "redis" ]
+memorydb        = [ "memorydb" ]
+chromadb        = [ "chromadb" ]
+opensearch      = [ "opensearch-py" ]
+aliyun_opensearch = [ "alibabacloud_ha3engine_vector", "alibabacloud_searchengine20211025"]
 
 [project.urls]
 "repository" = "https://github.com/zilliztech/VectorDBBench"

vectordb_bench/backend/cases.py

@@ -289,7 +289,7 @@ class Performance1536D50K(PerformanceCase):
     description: str = """This case tests the search performance of a vector database with a medium 50K dataset (<b>OpenAI 50K vectors</b>, 1536 dimensions), at varying parallel levels.
 Results will show index building time, recall, and maximum QPS."""
     load_timeout: float | int = 3600
-    optimize_timeout: float | int | None = 15 * 60
+    optimize_timeout: float | int | None = config.OPTIMIZE_TIMEOUT_DEFAULT
 
 
 def metric_type_map(s: str) -> MetricType:

vectordb_bench/backend/clients/__init__.py

@@ -39,6 +39,7 @@ class DB(Enum):
     AWSOpenSearch = "OpenSearch"
     AliyunElasticsearch = "AliyunElasticsearch"
     Test = "test"
+    AliyunOpenSearch = "AliyunOpenSearch"
 
 
     @property
@@ -108,6 +109,10 @@ def init_cls(self) -> Type[VectorDB]:
             from .aliyun_elasticsearch.aliyun_elasticsearch import AliyunElasticsearch
             return AliyunElasticsearch
 
+        if self == DB.AliyunOpenSearch:
+            from .aliyun_opensearch.aliyun_opensearch import AliyunOpenSearch
+            return AliyunOpenSearch
+
     @property
     def config_cls(self) -> Type[DBConfig]:
         """Import while in use"""
@@ -175,6 +180,10 @@ def config_cls(self) -> Type[DBConfig]:
             from .aliyun_elasticsearch.config import AliyunElasticsearchConfig
             return AliyunElasticsearchConfig
 
+        if self == DB.AliyunOpenSearch:
+            from .aliyun_opensearch.config import AliyunOpenSearchConfig
+            return AliyunOpenSearchConfig
+
     def case_config_cls(self, index_type: IndexType | None = None) -> Type[DBCaseConfig]:
         if self == DB.Milvus:
             from .milvus.config import _milvus_case_config
@@ -224,6 +233,10 @@ def case_config_cls(self, index_type: IndexType | None = None) -> Type[DBCaseCon
             from .elastic_cloud.config import ElasticCloudIndexConfig
             return ElasticCloudIndexConfig
 
+        if self == DB.AliyunOpenSearch:
+            from .aliyun_opensearch.config import AliyunOpenSearchIndexConfig
+            return AliyunOpenSearchIndexConfig
+
         # DB.Pinecone, DB.Chroma, DB.Redis
         return EmptyDBCaseConfig