add medium and large public dataset

add medium and large dataset to public

Author: Caroline-an777

vectordb_bench/__init__.py

@@ -53,6 +53,7 @@ class config:
     LOAD_TIMEOUT_1536D_500K = 24 * 3600  # 24h
     LOAD_TIMEOUT_1536D_5M = 240 * 3600  # 10d
 
+    LOAD_TIMEOUT_1024D_1M = 24 * 3600  # 24h
     LOAD_TIMEOUT_1024D_10M = 240 * 3600  # 10d
 
     OPTIMIZE_TIMEOUT_DEFAULT = 24 * 3600  # 24h
@@ -64,6 +65,7 @@ class config:
     OPTIMIZE_TIMEOUT_1536D_500K = 24 * 3600  # 24h
     OPTIMIZE_TIMEOUT_1536D_5M = 240 * 3600  # 10d
 
+    OPTIMIZE_TIMEOUT_1024D_1M = 24 * 3600  # 24h
     OPTIMIZE_TIMEOUT_1024D_10M = 240 * 3600  # 10d
 
     def display(self) -> str:

vectordb_bench/backend/cases.py

@@ -42,6 +42,7 @@ class CaseType(Enum):
     Performance1536D500K99P = 14
     Performance1536D5M99P = 15
 
+    Performance1024D1M = 17
     Performance1024D10M = 20
 
     Performance1536D50K = 50
@@ -311,6 +312,18 @@ class Performance1536D5M99P(IntFilterPerformanceCase):
     optimize_timeout: float | int | None = config.OPTIMIZE_TIMEOUT_1536D_5M
 
 
+class Performance1024D1M(PerformanceCase):
+    case_id: CaseType = CaseType.Performance1024D1M
+    filter_rate: float | int | None = None
+    dataset: DatasetManager = Dataset.BIOASQ.manager(1_000_000)
+    name: str = "Search Performance Test (1M Dataset, 1024 Dim)"
+    description: str = """This case tests the search performance of a vector database with a medium 1M dataset
+    (<b>Bioasq 1M vectors</b>, 1024 dimensions), at varying parallel levels. Results will show index building time,
+    recall, and maximum QPS."""
+    load_timeout: float | int = config.LOAD_TIMEOUT_1024D_1M
+    optimize_timeout: float | int | None = config.OPTIMIZE_TIMEOUT_1024D_1M
+
+
 class Performance1024D10M(PerformanceCase):
     case_id: CaseType = CaseType.Performance1024D10M
     filter_rate: float | int | None = None
@@ -511,6 +524,7 @@ def filters(self) -> Filter:
     CaseType.Performance1536D5M1P: Performance1536D5M1P,
     CaseType.Performance1536D500K99P: Performance1536D500K99P,
     CaseType.Performance1536D5M99P: Performance1536D5M99P,
+    CaseType.Performance1024D1M: Performance1024D1M,
     CaseType.Performance1024D10M: Performance1024D10M,
     CaseType.Performance1536D50K: Performance1536D50K,
     CaseType.PerformanceCustomDataset: PerformanceCustomDataset,

vectordb_bench/backend/dataset.py

@@ -173,6 +173,7 @@ class Bioasq(BaseDataset):
     use_shuffled: bool = config.USE_SHUFFLED_DATA
     with_gt: bool = True
     _size_label: dict = {
+        1_000_000: SizeLabel(1_000_000, "MEDIUM", 1),
         10_000_000: SizeLabel(10_000_000, "LARGE", 10),
     }
     with_scalar_labels: bool = True
@@ -390,6 +391,7 @@ class DatasetWithSizeType(Enum):
     CohereSmall = "Small Cohere (768dim, 100K)"
     CohereMedium = "Medium Cohere (768dim, 1M)"
     CohereLarge = "Large Cohere (768dim, 10M)"
+    BioasqMedium = "Medium Bioasq (1024dim, 1M)"
     BioasqLarge = "Large Bioasq (1024dim, 10M)"
     OpenAISmall = "Small OpenAI (1536dim, 50K)"
     OpenAIMedium = "Medium OpenAI (1536dim, 500K)"
@@ -425,6 +427,7 @@ def get_optimize_timeout(self) -> float:
     DatasetWithSizeType.CohereSmall: Dataset.COHERE.manager(100_000),
     DatasetWithSizeType.CohereMedium: Dataset.COHERE.manager(1_000_000),
     DatasetWithSizeType.CohereLarge: Dataset.COHERE.manager(10_000_000),
+    DatasetWithSizeType.BioasqMedium: Dataset.BIOASQ.manager(1_000_000),
     DatasetWithSizeType.BioasqLarge: Dataset.BIOASQ.manager(10_000_000),
     DatasetWithSizeType.OpenAISmall: Dataset.OPENAI.manager(50_000),
     DatasetWithSizeType.OpenAIMedium: Dataset.OPENAI.manager(500_000),

vectordb_bench/frontend/config/dbCaseConfigs.py

@@ -231,6 +231,7 @@ def generate_label_filter_cases(dataset_with_size_type: DatasetWithSizeType) ->
             UICaseItem(cases=generate_normal_cases(CaseType.Performance768D10M)),
             UICaseItem(cases=generate_normal_cases(CaseType.Performance768D1M)),
             UICaseItem(isLine=True),
+            UICaseItem(cases=generate_normal_cases(CaseType.Performance1024D1M)),
             UICaseItem(cases=generate_normal_cases(CaseType.Performance1024D10M)),
             UICaseItem(isLine=True),
             UICaseItem(cases=generate_normal_cases(CaseType.Performance1536D5M)),
@@ -303,6 +304,7 @@ def generate_label_filter_cases(dataset_with_size_type: DatasetWithSizeType) ->
     CaseType.Performance1536D5M,
     CaseType.Performance1536D500K,
     CaseType.Performance1536D50K,
+    CaseType.Performance1024D1M,
     CaseType.Performance1024D10M,
     CaseType.CapacityDim960,
     CaseType.CapacityDim128,