vectordb-bench 0.0.26__py3-none-any.whl → 0.0.27__py3-none-any.whl

vectordb_bench/backend/dataset.py

@@ -220,10 +220,12 @@ class DatasetManager(BaseModel):
         train_files = utils.compose_train_files(file_count, use_shuffled)
         all_files = train_files
 
-        gt_file, test_file = None, None
+        test_file = "test.parquet"
+        all_files.extend([test_file])
+        gt_file = None
         if self.data.with_gt:
-            gt_file, test_file = utils.compose_gt_file(filters), "test.parquet"
-            all_files.extend([gt_file, test_file])
+            gt_file = utils.compose_gt_file(filters)
+            all_files.extend([gt_file])
 
         if not self.data.is_custom:
             source.reader().read(
@@ -232,8 +234,10 @@ class DatasetManager(BaseModel):
                 local_ds_root=self.data_dir,
             )
 
-        if gt_file is not None and test_file is not None:
+        if test_file is not None:
             self.test_data = self._read_file(test_file)
+
+        if gt_file is not None:
             self.gt_data = self._read_file(gt_file)
 
         prefix = "shuffle_train" if use_shuffled else "train"

vectordb_bench/backend/runner/serial_runner.py

@@ -209,7 +209,8 @@ class SerialSearchRunner:
             ideal_dcg = get_ideal_dcg(self.k)
 
             log.debug(f"test dataset size: {len(test_data)}")
-            log.debug(f"ground truth size: {ground_truth.columns}, shape: {ground_truth.shape}")
+            if ground_truth is not None:
+                log.debug(f"ground truth size: {ground_truth.columns}, shape: {ground_truth.shape}")
 
             latencies, recalls, ndcgs = [], [], []
             for idx, emb in enumerate(test_data):
@@ -228,9 +229,13 @@ class SerialSearchRunner:
 
                 latencies.append(time.perf_counter() - s)
 
-                gt = ground_truth["neighbors_id"][idx]
-                recalls.append(calc_recall(self.k, gt[: self.k], results))
-                ndcgs.append(calc_ndcg(gt[: self.k], results, ideal_dcg))
+                if ground_truth is not None:
+                    gt = ground_truth["neighbors_id"][idx]
+                    recalls.append(calc_recall(self.k, gt[: self.k], results))
+                    ndcgs.append(calc_ndcg(gt[: self.k], results, ideal_dcg))
+                else:
+                    recalls.append(0)
+                    ndcgs.append(0)
 
                 if len(latencies) % 100 == 0:
                     log.debug(

{vectordb_bench-0.0.26.dist-info → vectordb_bench-0.0.27.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vectordb-bench
-Version: 0.0.26
+Version: 0.0.27
 Summary: VectorDBBench is not just an offering of benchmark results for mainstream vector databases and cloud services, it's your go-to tool for the ultimate performance and cost-effectiveness comparison. Designed with ease-of-use in mind, VectorDBBench is devised to help users, even non-professionals, reproduce results or test new systems, making the hunt for the optimal choice amongst a plethora of cloud services and open-source vector databases a breeze.
 Author-email: XuanYang-cn <xuan.yang@zilliz.com>
 Project-URL: repository, https://github.com/zilliztech/VectorDBBench

{vectordb_bench-0.0.26.dist-info → vectordb_bench-0.0.27.dist-info}/RECORD

@@ -9,7 +9,7 @@ vectordb_bench/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3
 vectordb_bench/backend/assembler.py,sha256=6GInRT7yBgfTaIPmo-XMkYX4pA8PJQmjMQInynwaunE,2047
 vectordb_bench/backend/cases.py,sha256=obDdY6g3p9Z2fog7qDwLLDuRMwo3LGQKMHsP66QZd2M,16296
 vectordb_bench/backend/data_source.py,sha256=bfa_Zg4O9fRP2ENmVZ_2-NISKozoFN-TocyxOlw1JtE,5524
-vectordb_bench/backend/dataset.py,sha256=V4OKPt23v0kmdvgJwDr_R2fLJv3lXLZEii992cEM2Q0,8993
+vectordb_bench/backend/dataset.py,sha256=lH2Q01AEJxA-sYfZHzH2BM019mwuy9mB_i0VLhIgDJ8,9020
 vectordb_bench/backend/result_collector.py,sha256=mpROVdZ-HChKBVyMV5TZ5v7YGRb69bvfT7Gezn5F5sY,819
 vectordb_bench/backend/task_runner.py,sha256=vlaXB0_25-G9w1Lj-F0SrvJzhXT7ceDWGIb2aKRXukU,11488
 vectordb_bench/backend/utils.py,sha256=R6THuJdZhiQYSSJTqv0Uegl2B20taV_QjwvFrun2yxE,1949
@@ -83,7 +83,7 @@ vectordb_bench/backend/runner/__init__.py,sha256=mF8YnErTa7MVG37zZb0KFXBSrmMw_af
 vectordb_bench/backend/runner/mp_runner.py,sha256=AJHrQmUADDWDQZ0eZ4aaAH9HOQtZHiafXJYGU5PNq3Y,9645
 vectordb_bench/backend/runner/rate_runner.py,sha256=2coO7qalEh6ZbVKUkyFvip4JWjs1yJM-iiExSrjEp9c,4306
 vectordb_bench/backend/runner/read_write_runner.py,sha256=CXYBXEEkS1S7-NurdzN5Wh6N0Vx-rprM9Qehk1WKwl8,7822
-vectordb_bench/backend/runner/serial_runner.py,sha256=URymqOy-9NdVE3kXWBW3e9R0Oh2sG9zF1vJkV7sk48E,10092
+vectordb_bench/backend/runner/serial_runner.py,sha256=Y4Y2mSK8nU3hml7gliiF6BXUaW49sD-Ueci0xn62IL0,10290
 vectordb_bench/backend/runner/util.py,sha256=tjTFUxth6hNnVrlU82TqkHhfeZo4ymj7WlyK4zFyPTg,522
 vectordb_bench/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 vectordb_bench/cli/cli.py,sha256=cr4BycwIs51YJgNorHplzKP46M474jDTatevPdD-oKE,15434
@@ -142,9 +142,9 @@ vectordb_bench/results/WeaviateCloud/result_20230808_standard_weaviatecloud.json
 vectordb_bench/results/ZillizCloud/result_20230727_standard_zillizcloud.json,sha256=-Mdm4By65XDRCrmVOCF8yQXjcZtH4Xo4shcjoDoBUKU,18293
 vectordb_bench/results/ZillizCloud/result_20230808_standard_zillizcloud.json,sha256=77XlHT5zM_K7mG5HfDQKwXZnSCuR37VUbt6-P3J_amI,15737
 vectordb_bench/results/ZillizCloud/result_20240105_standard_202401_zillizcloud.json,sha256=TualfJ0664Hs-vdIW68bdkqAEYyzotXmu2P0yIN-GHk,42526
-vectordb_bench-0.0.26.dist-info/licenses/LICENSE,sha256=HXbxhrb5u5SegVzeLNF_voVgRsJMavcLaOmD1N0lZkM,1067
-vectordb_bench-0.0.26.dist-info/METADATA,sha256=lsc4Y28tVwbXr3fUrVHbppegppAtYWoH0rEV3pn820g,38061
-vectordb_bench-0.0.26.dist-info/WHEEL,sha256=ck4Vq1_RXyvS4Jt6SI0Vz6fyVs4GWg7AINwpsaGEgPE,91
-vectordb_bench-0.0.26.dist-info/entry_points.txt,sha256=Qzw6gVx96ui8esG21H6yHsI6nboEohRmV424TYhQNrA,113
-vectordb_bench-0.0.26.dist-info/top_level.txt,sha256=jnhZFZAuKX1J60yt-XOeBZ__ctiZMvoC_s0RFq29lpM,15
-vectordb_bench-0.0.26.dist-info/RECORD,,
+vectordb_bench-0.0.27.dist-info/licenses/LICENSE,sha256=HXbxhrb5u5SegVzeLNF_voVgRsJMavcLaOmD1N0lZkM,1067
+vectordb_bench-0.0.27.dist-info/METADATA,sha256=UC8hc6cQKAYshgbSFEBzDPODzeltBiimXbVkrakDLDQ,38061
+vectordb_bench-0.0.27.dist-info/WHEEL,sha256=ooBFpIzZCPdw3uqIQsOo4qqbA4ZRPxHnOH7peeONza0,91
+vectordb_bench-0.0.27.dist-info/entry_points.txt,sha256=Qzw6gVx96ui8esG21H6yHsI6nboEohRmV424TYhQNrA,113
+vectordb_bench-0.0.27.dist-info/top_level.txt,sha256=jnhZFZAuKX1J60yt-XOeBZ__ctiZMvoC_s0RFq29lpM,15
+vectordb_bench-0.0.27.dist-info/RECORD,,

{vectordb_bench-0.0.26.dist-info → vectordb_bench-0.0.27.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.0.0)
+Generator: setuptools (80.0.1)
 Root-Is-Purelib: true
 Tag: py3-none-any