vectordb-bench 0.0.2__py3-none-any.whl → 0.0.3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (34) hide show
  1. vectordb_bench/__init__.py +14 -3
  2. vectordb_bench/backend/cases.py +34 -13
  3. vectordb_bench/backend/clients/__init__.py +6 -1
  4. vectordb_bench/backend/clients/api.py +12 -8
  5. vectordb_bench/backend/clients/elastic_cloud/elastic_cloud.py +4 -2
  6. vectordb_bench/backend/clients/milvus/milvus.py +17 -10
  7. vectordb_bench/backend/clients/pgvector/config.py +49 -0
  8. vectordb_bench/backend/clients/pgvector/pgvector.py +171 -0
  9. vectordb_bench/backend/clients/pinecone/pinecone.py +4 -3
  10. vectordb_bench/backend/clients/qdrant_cloud/config.py +20 -2
  11. vectordb_bench/backend/clients/qdrant_cloud/qdrant_cloud.py +11 -11
  12. vectordb_bench/backend/clients/weaviate_cloud/weaviate_cloud.py +5 -5
  13. vectordb_bench/backend/clients/zilliz_cloud/zilliz_cloud.py +3 -1
  14. vectordb_bench/backend/dataset.py +99 -149
  15. vectordb_bench/backend/result_collector.py +2 -2
  16. vectordb_bench/backend/runner/mp_runner.py +29 -13
  17. vectordb_bench/backend/runner/serial_runner.py +69 -51
  18. vectordb_bench/backend/task_runner.py +43 -48
  19. vectordb_bench/frontend/components/get_results/saveAsImage.py +4 -2
  20. vectordb_bench/frontend/const/dbCaseConfigs.py +35 -4
  21. vectordb_bench/frontend/const/dbPrices.py +5 -33
  22. vectordb_bench/frontend/const/styles.py +9 -3
  23. vectordb_bench/metric.py +0 -1
  24. vectordb_bench/models.py +12 -8
  25. vectordb_bench/results/dbPrices.json +32 -0
  26. vectordb_bench/results/getLeaderboardData.py +52 -0
  27. vectordb_bench/results/leaderboard.json +1 -0
  28. vectordb_bench/results/{result_20230609_standard.json → result_20230705_standard.json} +670 -214
  29. {vectordb_bench-0.0.2.dist-info → vectordb_bench-0.0.3.dist-info}/METADATA +98 -13
  30. {vectordb_bench-0.0.2.dist-info → vectordb_bench-0.0.3.dist-info}/RECORD +34 -29
  31. {vectordb_bench-0.0.2.dist-info → vectordb_bench-0.0.3.dist-info}/LICENSE +0 -0
  32. {vectordb_bench-0.0.2.dist-info → vectordb_bench-0.0.3.dist-info}/WHEEL +0 -0
  33. {vectordb_bench-0.0.2.dist-info → vectordb_bench-0.0.3.dist-info}/entry_points.txt +0 -0
  34. {vectordb_bench-0.0.2.dist-info → vectordb_bench-0.0.3.dist-info}/top_level.txt +0 -0
{vectordb_bench-0.0.2.dist-info → vectordb_bench-0.0.3.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: vectordb-bench
3
- Version: 0.0.2
3
+ Version: 0.0.3
4
4
  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.
5
5
  Author-email: XuanYang-cn <xuan.yang@zilliz.com>
6
6
  Project-URL: repository, https://github.com/zilliztech/VectorDBBench
@@ -27,6 +27,9 @@ Requires-Dist: environs
27
27
  Requires-Dist: scikit-learn
28
28
  Requires-Dist: s3fs
29
29
  Requires-Dist: psutil
30
+ Requires-Dist: polars
31
+ Requires-Dist: pgvector
32
+ Requires-Dist: sqlalchemy
30
33
  Provides-Extra: test
31
34
  Requires-Dist: ruff ; extra == 'test'
32
35
  Requires-Dist: pytest ; extra == 'test'
@@ -36,6 +39,7 @@ Requires-Dist: pytest ; extra == 'test'
36
39
  [![version](https://img.shields.io/pypi/v/vectordb-bench.svg?color=blue)](https://pypi.org/project/vectordb-bench/)
37
40
  [![Downloads](https://pepy.tech/badge/vectordb-bench)](https://pepy.tech/project/vectordb-bench)
38
41
 
42
+ **Leaderboard:** https://zilliz.com/benchmark
39
43
  ## Quick Start
40
44
  ### Prerequirement
41
45
  ``` shell
@@ -60,6 +64,24 @@ Closely mimicking real-world production environments, we've set up diverse testi
60
64
 
61
65
  Prepare to delve into the world of VectorDBBench, and let it guide you in uncovering your perfect vector database match.
62
66
 
67
+ ## Leaderboard
68
+ ### Introduction
69
+ To facilitate the presentation of test results and provide a comprehensive performance analysis report, we offer a [leaderboard page](https://zilliz.com/benchmark). It allows us to choose from QPS, QP$, and latency metrics, and provides a comprehensive assessment of a system's performance based on the test results of various cases and a set of scoring mechanisms (to be introduced later). On this leaderboard, we can select the systems and models to be compared, and filter out cases we do not want to consider. Comprehensive scores are always ranked from best to worst, and the specific test results of each query will be presented in the list below.
70
+
71
+ ### Scoring Rules
72
+
73
+ 1. For each case, select a base value and score each system based on relative values.
74
+ - For QPS and QP$, we use the highest value as the reference, denoted as `base_QPS` or `base_QP$`, and the score of each system is `(QPS/base_QPS) * 100` or `(QP$/base_QP$) * 100`.
75
+ - For Latency, we use the lowest value as the reference, that is, `base_Latency`, and the score of each system is `(Latency + 10ms)/(base_Latency + 10ms)`.
76
+
77
+ We want to give equal weight to different cases, and not let a case with high absolute result values become the sole reason for the overall scoring. Therefore, when scoring different systems in each case, we need to use relative values.
78
+
79
+ Also, for Latency, we add 10ms to the numerator and denominator to ensure that if every system performs particularly well in a case, its advantage will not be infinitely magnified when latency tends to 0.
80
+
81
+ 2. For systems that fail or timeout in a particular case, we will give them a score based on a value worse than the worst result by a factor of two. For example, in QPS or QP$, it would be half the lowest value. For Latency, it would be twice the maximum value.
82
+
83
+ 3. For each system, we will take the geometric mean of its scores in all cases as its comprehensive score for a particular metric.
84
+
63
85
  ## Build on your own
64
86
  ### Install requirements
65
87
  ``` shell
@@ -88,10 +110,12 @@ $ ruff check vectordb_bench --fix
88
110
 
89
111
  ## How does it work?
90
112
  ### Result Page
91
- ![image](https://github.com/zilliztech/VectorDBBench/assets/105927039/66ab83c4-656e-41a8-a643-d9790faccbeb)
113
+ ![image](https://github.com/zilliztech/VectorDBBench/assets/105927039/7f5cdae7-f9f2-4a81-b2e0-e5c6268cd970)
92
114
  This is the main page of VectorDBBench, which displays the standard benchmark results we provide. Additionally, results of all tests performed by users themselves will also be shown here. We also offer the ability to select and compare results from multiple tests simultaneously.
93
115
 
94
116
  The standard benchmark results displayed here include all 9 cases that we currently support for all our clients (Milvus, Zilliz Cloud, Elastic Search, Qdrant Cloud, and Weaviate Cloud). However, as some systems may not be able to complete all the tests successfully due to issues like Out of Memory (OOM) or timeouts, not all clients are included in every case.
117
+
118
+ All standard benchmark results are generated by a client running on an 8 core, 32 GB host, which is located in the same region as the server being tested. The client host is equipped with an `Intel(R) Xeon(R) Platinum 8375C CPU @ 2.90GHz` processor. Also all the servers for the open-source systems tested in our benchmarks run on hosts with the same type of processor.
95
119
  ### Run Test Page
96
120
  ![image](https://github.com/zilliztech/VectorDBBench/assets/105927039/a789099a-3707-4214-8052-b73463b8f2c6)
97
121
  This is the page to run a test:
@@ -121,17 +145,17 @@ We've developed an array of 9 comprehensive benchmark cases to test vector datab
121
145
  - **Medium Dataset, High Filtering Rate:** This case uses a medium dataset (Cohere 1M vectors, 768 dimensions) with a high filtering rate.
122
146
  For a quick reference, here is a table summarizing the key aspects of each case:
123
147
 
124
- Case No. | Case Type | Dataset Size | Dataset Type | Filtering Rate | Results |
125
- |----------|-----------|--------------|--------------|----------------|---------|
126
- 1 | Capacity Case | Large Dim | GIST 100K vectors, 960 dimensions | N/A | Number of inserted vectors |
127
- 2 | Capacity Case | Small Dim | SIFT 100K vectors, 128 dimensions | N/A | Number of inserted vectors |
128
- 3 | Search Performance Case | XLarge Dataset | LAION 100M vectors, 768 dimensions | N/A | Index building time, recall, latency, maximum QPS |
129
- 4 | Search Performance Case | Large Dataset | Cohere 10M vectors, 768 dimensions | N/A | Index building time, recall, latency, maximum QPS |
130
- 5 | Search Performance Case | Medium Dataset | Cohere 1M vectors, 768 dimensions | N/A | Index building time, recall, latency, maximum QPS |
131
- 6 | Filtering Search Performance Case | Large Dataset, Low Filtering Rate | Cohere 10M vectors, 768 dimensions | 1% vectors | Index building time, recall, latency, maximum QPS |
132
- 7 | Filtering Search Performance Case | Medium Dataset, Low Filtering Rate | Cohere 1M vectors, 768 dimensions | 1% vectors | Index building time, recall, latency, maximum QPS |
133
- 8 | Filtering Search Performance Case | Large Dataset, High Filtering Rate | Cohere 10M vectors, 768 dimensions | 99% vectors | Index building time, recall, latency, maximum QPS |
134
- 9 | Filtering Search Performance Case | Medium Dataset, High Filtering Rate | Cohere 1M vectors, 768 dimensions | 99% vectors | Index building time, recall, latency, maximum QPS |
148
+ Case No. | Case Type | Dataset Size | Filtering Rate | Results |
149
+ |----------|-----------|--------------|----------------|---------|
150
+ 1 | Capacity Case | GIST 100K vectors, 960 dimensions | N/A | Number of inserted vectors |
151
+ 2 | Capacity Case | SIFT 100K vectors, 128 dimensions | N/A | Number of inserted vectors |
152
+ 3 | Search Performance Case | LAION 100M vectors, 768 dimensions | N/A | Index building time, recall, latency, maximum QPS |
153
+ 4 | Search Performance Case | Cohere 10M vectors, 768 dimensions | N/A | Index building time, recall, latency, maximum QPS |
154
+ 5 | Search Performance Case | Cohere 1M vectors, 768 dimensions | N/A | Index building time, recall, latency, maximum QPS |
155
+ 6 | Filtering Search Performance Case | Cohere 10M vectors, 768 dimensions | 1% vectors | Index building time, recall, latency, maximum QPS |
156
+ 7 | Filtering Search Performance Case | Cohere 1M vectors, 768 dimensions | 1% vectors | Index building time, recall, latency, maximum QPS |
157
+ 8 | Filtering Search Performance Case | Cohere 10M vectors, 768 dimensions | 99% vectors | Index building time, recall, latency, maximum QPS |
158
+ 9 | Filtering Search Performance Case | Cohere 1M vectors, 768 dimensions | 99% vectors | Index building time, recall, latency, maximum QPS |
135
159
 
136
160
  Each case provides an in-depth examination of a vector database's abilities, providing you a comprehensive view of the database's performance.
137
161
 
@@ -219,3 +243,64 @@ For the Client, we welcome any parameter tuning to obtain better results.
219
243
  Many databases may not be able to complete all test cases due to issues such as Out of Memory (OOM), crashes, or timeouts. In these scenarios, we will clearly state these occurrences in the test results.
220
244
  ### Mistake Or Misrepresentation
221
245
  We strive for accuracy in learning and supporting various vector databases, yet there might be oversights or misapplications. For any such occurrences, feel free to [raise an issue](https://github.com/zilliztech/VectorDBBench/issues/new) or make amendments on our GitHub page.
246
+ ## Timeout
247
+ In our pursuit to ensure that our benchmark reflects the reality of a production environment while guaranteeing the practicality of the system, we have implemented a timeout plan based on our experiences for various tests.
248
+
249
+ **1. Capacity Case:**
250
+ - For Capacity Case, we have assigned an overall timeout.
251
+
252
+ **2. Other Cases:**
253
+
254
+ For other cases, we have set two timeouts:
255
+
256
+ - **Data Loading Timeout:** This timeout is designed to filter out systems that are too slow in inserting data, thus ensuring that we are only considering systems that is able to cope with the demands of a real-world production environment within a reasonable time frame.
257
+
258
+ - **Optimization Preparation Timeout**: This timeout is established to avoid excessive optimization strategies that might work for benchmarks but fail to deliver in real production environments. By doing this, we ensure that the systems we consider are not only suitable for testing environments but also applicable and efficient in production scenarios.
259
+
260
+ This multi-tiered timeout approach allows our benchmark to be more representative of actual production environments and assists us in identifying systems that can truly perform in real-world scenarios.
261
+ <table>
262
+ <tr>
263
+ <th>Case</th>
264
+ <th>Data Size</th>
265
+ <th>Timeout Type</th>
266
+ <th>Value</th>
267
+ </tr>
268
+ <tr>
269
+ <td>Capacity Case</td>
270
+ <td>N/A</td>
271
+ <td>Loading timeout</td>
272
+ <td>24 hours</td>
273
+ </tr>
274
+ <tr>
275
+ <td rowspan="2">Other Cases</td>
276
+ <td rowspan="2">1M vectors, 768 dimensions</td>
277
+ <td>Loading timeout</td>
278
+ <td>2.5 hours</td>
279
+ </tr>
280
+ <tr>
281
+ <td>Optimization timeout</td>
282
+ <td>15 mins</td>
283
+ </tr>
284
+ <tr>
285
+ <td rowspan="2">Other Cases</td>
286
+ <td rowspan="2">10M vectors, 768 dimensions</td>
287
+ <td>Loading timeout</td>
288
+ <td>25 hours</td>
289
+ </tr>
290
+ <tr>
291
+ <td>Optimization timeout</td>
292
+ <td>2.5 hours</td>
293
+ </tr>
294
+ <tr>
295
+ <td rowspan="2">Other Cases</td>
296
+ <td rowspan="2">100M vectors, 768 dimensions</td>
297
+ <td>Loading timeout</td>
298
+ <td>250 hours</td>
299
+ </tr>
300
+ <tr>
301
+ <td>Optimization timeout</td>
302
+ <td>25 hours</td>
303
+ </tr>
304
+ </table>
305
+
306
+ **Note:** Some datapoints in the standard benchmark results that voilate this timeout will be kept for now for reference. We will remove them in the future.
{vectordb_bench-0.0.2.dist-info → vectordb_bench-0.0.3.dist-info}/RECORD RENAMED
@@ -1,34 +1,36 @@
1
- vectordb_bench/__init__.py,sha256=ZsEjMgkjnNDBp41H5lzLYcFqJkZQma-yfSsgHPmS2k0,837
1
+ vectordb_bench/__init__.py,sha256=pNBMwS6NTyl3NK2QTELRtohlrUK0fC4b3TpE3IpbV1M,1224
2
2
  vectordb_bench/__main__.py,sha256=YJOTn5MlbmLyr3PRsecY6fj7igHLB6_D3y1HwF_sO20,848
3
3
  vectordb_bench/base.py,sha256=d34WCGXZI1u5RGQtqrPHd3HbOF5AmioFrM2j30Aj1sY,130
4
4
  vectordb_bench/interface.py,sha256=aa46X4fitgScdHbQn_5naJr77Gb0uPFHoRiOhMAY560,8671
5
5
  vectordb_bench/log_util.py,sha256=YGaaevphwoPD0exF8EX_6hX5_9BoysCcKyHl4Ox5Fbk,2907
6
- vectordb_bench/metric.py,sha256=Bhl672NJbM615dY_g2o-zd7cwOXPSkuknsjAx9Nw_dc,1367
7
- vectordb_bench/models.py,sha256=q_3lL5TUm1RwvwJ311U4RzsDYRjwJoiTCEMzhTbBtz4,6621
6
+ vectordb_bench/metric.py,sha256=-SAcUm2m0OkHcph2QZusx-wZh8wCTrrHMy1Kv0WWL2w,1332
7
+ vectordb_bench/models.py,sha256=pcoEKcKpI8q9EnC3q5l8G6CkmdQ9PLR6-Nnsejbnswk,6711
8
8
  vectordb_bench/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
9
9
  vectordb_bench/backend/assembler.py,sha256=3RA8fMjU5x0FmVrruA_h7dan3YqL7cF4Mlp3o-WumSI,1717
10
- vectordb_bench/backend/cases.py,sha256=30mdgCmsyxGNcaKQYCfqlNjmxq0rIwikV6Ip1fjWB6U,7306
11
- vectordb_bench/backend/dataset.py,sha256=tI4uyy1V54Dphk03uEFtkedQDirF8BvsfmjKZVKhz58,12598
12
- vectordb_bench/backend/result_collector.py,sha256=5pPZNt6pZ6HjYRRrmzQY9ditMo736_VRmdtM8Fo7oJc,435
13
- vectordb_bench/backend/task_runner.py,sha256=Y21C27KTm3sSXPDbMjUc0SINlrqanBlO4szaFdf8uRg,9134
10
+ vectordb_bench/backend/cases.py,sha256=d2p-FqYa9gLgXVA_aQhcf8FU4M3gT-bZdufx_7xc864,8432
11
+ vectordb_bench/backend/dataset.py,sha256=n3ah8Yqvo2H2XpTBZOCRRPLoOVOYZWvf3T5zK6r4tgY,11509
12
+ vectordb_bench/backend/result_collector.py,sha256=nSXheGz8-vQa3frIW_eEKAPaVgqMLXXWPgcVsYgPXho,449
13
+ vectordb_bench/backend/task_runner.py,sha256=IE1e-TwiupBmS9Hm44KeyWS0r0aMVorHll1LSJNxB_A,9217
14
14
  vectordb_bench/backend/utils.py,sha256=YBIoxJIxVUPD-0SpbJwdnswX-nmlR9GPE4fj28M7CMQ,2563
15
- vectordb_bench/backend/clients/__init__.py,sha256=ZwdQ3jqAyedoXbFV7y0X1UD5dZA1OjKfMm54bgNh5Iw,1255
16
- vectordb_bench/backend/clients/api.py,sha256=yz_NgNrm7DKmHYfkziYGWUDZaTKXXgFi7R2StjXS7z8,5436
15
+ vectordb_bench/backend/clients/__init__.py,sha256=FMT1zyi7AbKWhbIi-LbkBioYBGZBLDKOefPSt9sfIDY,1406
16
+ vectordb_bench/backend/clients/api.py,sha256=FcOcp_KU-MAjAC8XO96vGbziFLzblDn991xNgUTASq8,5628
17
17
  vectordb_bench/backend/clients/elastic_cloud/config.py,sha256=xkaBNtsayByelVLda8LiSEwxjQjESpijJ8IFOh03f_0,1598
18
- vectordb_bench/backend/clients/elastic_cloud/elastic_cloud.py,sha256=h8jbLHBTExgAPKk3iN3d3AZeCBexMXPiai8NGiOhN0g,5049
18
+ vectordb_bench/backend/clients/elastic_cloud/elastic_cloud.py,sha256=wo2yb2dsvMTUunbaz9yqOxF9cB6iPYzQlYObSSL5TdY,5071
19
19
  vectordb_bench/backend/clients/milvus/config.py,sha256=_6RsYKI3Ed8exMCWgI7ZdpM8MVzWJlj9mz4iHDVrONc,3152
20
- vectordb_bench/backend/clients/milvus/milvus.py,sha256=ORAZlf_F5tuwnDKSYcnbhVcgvsgBJhpYVqbl6ixbekQ,6413
20
+ vectordb_bench/backend/clients/milvus/milvus.py,sha256=9xBdsJQhg4yzXA0iy-Tv4bOzJXv5mg3cP22lN-BWFrc,6543
21
+ vectordb_bench/backend/clients/pgvector/config.py,sha256=sy1dqNP9CyZdFBsSqE8oNg9dPE57ssIsIUafbvgQW_Q,1510
22
+ vectordb_bench/backend/clients/pgvector/pgvector.py,sha256=_VPuRpO0A94p2Y25YyDwyHRoGGTMiIxloP8ilJImXCU,5414
21
23
  vectordb_bench/backend/clients/pinecone/config.py,sha256=QV3v-mfjxkFeT6jNeOKSywnxDiaCFr1YUXmePxiTC-Q,395
22
- vectordb_bench/backend/clients/pinecone/pinecone.py,sha256=Ydh9KXd4mDC5KzcDH200T5WWpFt6MmuUrDNFp1Uugrk,4077
23
- vectordb_bench/backend/clients/qdrant_cloud/config.py,sha256=_Cok9WOGud0oNOZ-rk_8DJJKrK1jUuXUM_J6lERuF2o,329
24
- vectordb_bench/backend/clients/qdrant_cloud/qdrant_cloud.py,sha256=Fn5yHawnJraEAtDkCeypB60a73pqHojJb1IRIrZ41bM,5260
24
+ vectordb_bench/backend/clients/pinecone/pinecone.py,sha256=U31QbXLuTcNPp7PK24glE6LM23-YpbxK_Kj-NmEwoZY,4078
25
+ vectordb_bench/backend/clients/qdrant_cloud/config.py,sha256=VvPvzkWMYAFixpRCK9Rm5NJZpSPLYE2MPLAmnAO28aQ,892
26
+ vectordb_bench/backend/clients/qdrant_cloud/qdrant_cloud.py,sha256=zuRFHOZ-Rkwu68EWk05V0d4bcbqxLGgAxyuwLXMsFV0,5261
25
27
  vectordb_bench/backend/clients/weaviate_cloud/config.py,sha256=aiW40N6PcMlh_VvbqNJ7iZg2mZu2Omb-PJySLpMGi5I,1292
26
- vectordb_bench/backend/clients/weaviate_cloud/weaviate_cloud.py,sha256=iv-O-Btipci2LOl4KJwni3Ik-CwxBd9ObdVFVrUVDaA,5216
28
+ vectordb_bench/backend/clients/weaviate_cloud/weaviate_cloud.py,sha256=i5RyS4Udim8xgzGSMdEGXSkfS9LMcR5332nv_1FFS0o,5179
27
29
  vectordb_bench/backend/clients/zilliz_cloud/config.py,sha256=sXg6MQr51-XfBS4E92-lksP4bxXY2BIPSERrmSEXsfc,816
28
- vectordb_bench/backend/clients/zilliz_cloud/zilliz_cloud.py,sha256=Z1c8kaIVMPPhW396S6RI-1Vh7SST2e1EmUkXktMHQE4,973
30
+ vectordb_bench/backend/clients/zilliz_cloud/zilliz_cloud.py,sha256=b_IwKKUssmErHUAze4y-fWcA_3dZDLqza3A4b7I5o8w,1015
29
31
  vectordb_bench/backend/runner/__init__.py,sha256=5dZfPky8pY9Bi9HD5GZ3Fge8V2FJWrkGkQUkNL2v1t0,230
30
- vectordb_bench/backend/runner/mp_runner.py,sha256=3s5IlJN7uttIC9x3xghjilIo-zSffqOPd1t0I69CYdw,4406
31
- vectordb_bench/backend/runner/serial_runner.py,sha256=9BLTM3sQMeApoBQavqetdDnOCRKhU9y7apMHxbPDi2w,8593
32
+ vectordb_bench/backend/runner/mp_runner.py,sha256=amvLKrSyM0g0dUtOZmzdlksdVfhIF49URnJ2IA_WQPU,5009
33
+ vectordb_bench/backend/runner/serial_runner.py,sha256=855WozDesngoNQJ2DqoM5jvXnrGHP31A4PBwZIctb_k,9290
32
34
  vectordb_bench/frontend/utils.py,sha256=BzKR1kMX1ErlXAzkFUb06O2mIcxBbquRzJtxoHgRnKs,162
33
35
  vectordb_bench/frontend/vdb_benchmark.py,sha256=qmhj-UUq5Ra8MnLiiCDAkueZoha5IV6ZdtBGt64LJg0,1545
34
36
  vectordb_bench/frontend/components/check_results/charts.py,sha256=zbtEyUSk2FJbSlaGw1LH4boSljFXfhVZlC8rrIgVw_4,5113
@@ -40,7 +42,7 @@ vectordb_bench/frontend/components/check_results/headerIcon.py,sha256=Q0mbnav2FW
40
42
  vectordb_bench/frontend/components/check_results/nav.py,sha256=DQl74rujw70ayh37PQaiO4AdtVZ95-OtTMEtw_Ui7hE,685
41
43
  vectordb_bench/frontend/components/check_results/priceTable.py,sha256=E7sxhSCjkBOMlQFHe6zFizhQLsJ-mUcXUbNj4FpqSUE,1308
42
44
  vectordb_bench/frontend/components/check_results/stPageConfig.py,sha256=rAL2prWx0hT7Q3QWz6ALyKUMNladX6U48GlKvVq3DFA,429
43
- vectordb_bench/frontend/components/get_results/saveAsImage.py,sha256=WvnCT_AOCCA5yCnoc2vQzB-NMn0xp3fVzJ3uQLaD2D0,1415
45
+ vectordb_bench/frontend/components/get_results/saveAsImage.py,sha256=MdQCqjrX5rQyK34XfTkVykVLOcOouIz4enMR1P5GBiY,1457
44
46
  vectordb_bench/frontend/components/run_test/autoRefresh.py,sha256=ofsl2sdmBd2y9O_xaJDr58NPycJsDwCdf2rEyE_f6e8,288
45
47
  vectordb_bench/frontend/components/run_test/caseSelector.py,sha256=F06V0Fabp7NohIRwZLktB6tarVDGG--ftH6P2NA0qsk,3609
46
48
  vectordb_bench/frontend/components/run_test/dbConfigSetting.py,sha256=_2mSi7If5Xme84Bk6spklD6pa4b0Fw0MnS2JaFgW6mg,2126
@@ -48,15 +50,18 @@ vectordb_bench/frontend/components/run_test/dbSelector.py,sha256=r8ABYpu6aWA94Fi
48
50
  vectordb_bench/frontend/components/run_test/generateTasks.py,sha256=tqjhMWm1HTkxPlQClr5pVcMMyf3_Zg1SKt8Bw7L4w3I,706
49
51
  vectordb_bench/frontend/components/run_test/hideSidebar.py,sha256=vb5kzIMmbMqWX67qFEHek21X4sGO_tPyn_uPqUEtp3Q,234
50
52
  vectordb_bench/frontend/components/run_test/submitTask.py,sha256=4dvlS1Frf32Cqc4yiVmbLnUPqOxgoFLKJ8pdxYvY7uI,2322
51
- vectordb_bench/frontend/const/dbCaseConfigs.py,sha256=f6OhWmpUSKIPk0xDMmurm8CWczBNDj9o3VxHv1hEZak,7270
52
- vectordb_bench/frontend/const/dbPrices.py,sha256=G71Jrovmgif86cg-KIieKnnGIz0imgKq5RfTI74MREU,765
53
- vectordb_bench/frontend/const/styles.py,sha256=hrC72dttsgHnCs7vgBlH2YXf32WDedxx47f1CyAAPes,1568
53
+ vectordb_bench/frontend/const/dbCaseConfigs.py,sha256=XQkmKiGtxd4cC0r1aWgBWbSrsJWTBYJ_11VBqRBHg3Y,8382
54
+ vectordb_bench/frontend/const/dbPrices.py,sha256=10aBKjVcEg8y7TPSda28opmBM1KmXNrvbU9WM_BsZcE,176
55
+ vectordb_bench/frontend/const/styles.py,sha256=3xpIV7YfD19y_qLz73m19YpeU0gAY1HRURmJwWjGVIc,1935
54
56
  vectordb_bench/frontend/pages/quries_per_dollar.py,sha256=SpXwKwdarwPz7RtF_qxyODfwARBb3VI9iKElYtnwEVs,2422
55
57
  vectordb_bench/frontend/pages/run_test.py,sha256=nkXTVBauuCgkJ6WRSQ_-qa83RAmc0Z3VH2uTDrNCQL8,2045
56
- vectordb_bench/results/result_20230609_standard.json,sha256=cpk6Xx0sey5O2CWwFhnUwTnko3xDSBLixuK1BXgSItw,86206
57
- vectordb_bench-0.0.2.dist-info/LICENSE,sha256=HXbxhrb5u5SegVzeLNF_voVgRsJMavcLaOmD1N0lZkM,1067
58
- vectordb_bench-0.0.2.dist-info/METADATA,sha256=hTU6eNGQC0aq4A5roGDshqXfj368JGhUjsRwMZ0XDpA,14289
59
- vectordb_bench-0.0.2.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
60
- vectordb_bench-0.0.2.dist-info/entry_points.txt,sha256=RVG6ppvzIsstAM199pDqeKu8lnxntjwYapn0smVQY7A,60
61
- vectordb_bench-0.0.2.dist-info/top_level.txt,sha256=jnhZFZAuKX1J60yt-XOeBZ__ctiZMvoC_s0RFq29lpM,15
62
- vectordb_bench-0.0.2.dist-info/RECORD,,
58
+ vectordb_bench/results/dbPrices.json,sha256=VoaOjqbWyTdEMLXuzerL5xR46QbxOWFmxCf2mPhjJV4,576
59
+ vectordb_bench/results/getLeaderboardData.py,sha256=5aWBNb7hfp2rGjOrBTKeHUA8Uyr0MsDNUuHDF6u1DPQ,1707
60
+ vectordb_bench/results/leaderboard.json,sha256=QRE1S8FSIduD4hMqohKuibmcqHnNR61tRFkA4HKgOk4,26502
61
+ vectordb_bench/results/result_20230705_standard.json,sha256=qzCAfyBL4tk2eyhMDo8PM6tK2xklr3RpFztwCbNceNg,96237
62
+ vectordb_bench-0.0.3.dist-info/LICENSE,sha256=HXbxhrb5u5SegVzeLNF_voVgRsJMavcLaOmD1N0lZkM,1067
63
+ vectordb_bench-0.0.3.dist-info/METADATA,sha256=iULpZuFtVq34JXEL1Y8ipRC1gXwxYfnf3vtLupzzT5k,18933
64
+ vectordb_bench-0.0.3.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
65
+ vectordb_bench-0.0.3.dist-info/entry_points.txt,sha256=RVG6ppvzIsstAM199pDqeKu8lnxntjwYapn0smVQY7A,60
66
+ vectordb_bench-0.0.3.dist-info/top_level.txt,sha256=jnhZFZAuKX1J60yt-XOeBZ__ctiZMvoC_s0RFq29lpM,15
67
+ vectordb_bench-0.0.3.dist-info/RECORD,,