vectordb-bench 0.0.30__py3-none-any.whl → 1.0.1__py3-none-any.whl

vectordb_bench/results/dbPrices.json

@@ -11,13 +11,16 @@
     "bus_crit": 32.6
   },
   "ElasticCloud": {
-    "upTo2.5c8g": 0.4793
+    "upTo2.5c8g": 0.4793,
+    "8c60g": 1.26,
+    "8c60g-force_merge": 1.26
   },
   "QdrantCloud": {
     "0.5c4g-1node": 0.052,
     "2c8g-1node": 0.166,
     "4c16g-1node": 0.2852,
-    "4c16g-5node": 1.426
+    "4c16g-5node": 1.426,
+    "16c64g": 1.14
   },
   "Pinecone": {
     "s1.x1": 0.0973,
@@ -26,7 +29,12 @@
     "p2.x1": 0.146,
     "p2.x1-8node": 1.168,
     "p1.x1-8node": 0.779,
-    "s1.x1-2node": 0.195
+    "s1.x1-2node": 0.195,
+    "p2.x8-1node": 1.31
   },
-  "PgVector": {}
+  "PgVector": {},
+  "OpenSearch": {
+    "16c128g": 1.418,
+    "16c128g-force_merge": 1.418
+  }
 }

vectordb_bench/results/getLeaderboardDataV2.py

@@ -0,0 +1,59 @@
+import json
+import logging
+
+
+from vectordb_bench.backend.cases import CaseType
+from vectordb_bench.backend.clients import DB
+from vectordb_bench.models import CaseResult
+from vectordb_bench import config
+
+logging.basicConfig(level=logging.DEBUG, format="%(asctime)s - %(levelname)s - %(message)s")
+
+from vectordb_bench.interface import BenchMarkRunner
+
+
+def get_standard_2025_results() -> list[CaseResult]:
+    all_results = BenchMarkRunner.get_results()
+    standard_2025_case_results = []
+    for result in all_results:
+        if result.task_label == "standard_2025":
+            standard_2025_case_results += result.results
+    return standard_2025_case_results
+
+
+def save_to_json(data: list[dict], file_name: str):
+    with open(file_name, "w") as f:
+        json.dump(data, f, indent=4)
+
+
+def main():
+    standard_2025_case_results = get_standard_2025_results()
+    data = []
+    for case_result in standard_2025_case_results:
+        db = case_result.task_config.db
+        label = case_result.task_config.db_config.db_label
+        metrics = case_result.metrics
+        qps = metrics.qps
+        latency = metrics.serial_latency_p99
+        recall = metrics.recall
+        case = case_result.task_config.case_config.case
+        filter_ratio = case.filters.filter_rate
+        dataset = case.dataset.data.full_name
+        if case.case_id != CaseType.StreamingPerformanceCase:
+            data.append(
+                {
+                    "dataset": dataset,
+                    "db": db.value,
+                    "label": label,
+                    "db_name": f"{db.value}-{label}",
+                    "qps": round(qps, 4),
+                    "latency": round(latency, 4),
+                    "recall": round(recall, 4),
+                    "filter_ratio": round(filter_ratio, 2),
+                }
+            )
+    save_to_json(data, config.RESULTS_LOCAL_DIR / "leaderboard_v2.json")
+
+
+if __name__ == "__main__":
+    main()