vectordb-bench 0.0.26__tar.gz → 0.0.27__tar.gz

{vectordb_bench-0.0.26 → vectordb_bench-0.0.27}/PKG-INFO

@@ -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 → vectordb_bench-0.0.27}/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-0.0.26 → vectordb_bench-0.0.27}/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 → vectordb_bench-0.0.27}/vectordb_bench.egg-info/PKG-INFO

@@ -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