[Feature Request]: Benchmark framework #951
Labels
feature request
New feature or request
Comments
This was referenced Apr 8, 2024
JinHai-CN
added a commit
that referenced
this issue
Apr 8, 2024
### What problem does this PR solve? Initialize the benchmark framework, including base_client.py and README. Issue link:#951 ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Co-authored-by: Jin Hai <haijin.chn@gmail.com>
JinHai-CN
pushed a commit
that referenced
this issue
Apr 11, 2024
### What problem does this PR solve? Provide a json config file example, and implement the basic client of qdrant. Issue link:#951 ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Co-authored-by: salieri <lomlieri@gmail.com>
JinHai-CN
pushed a commit
that referenced
this issue
Apr 19, 2024
### What problem does this PR solve? I implement the basic benchmark, and it now supports sift, gist, geonames datasets. Issue link:#951 ### Type of change - [x] New Feature (non-breaking change which adds functionality)
JinHai-CN
pushed a commit
that referenced
this issue
Apr 22, 2024
### What problem does this PR solve? save results, and measure latency, recall and so on. Issue link:#951 ### Type of change - [x] New Feature (non-breaking change which adds functionality)
JinHai-CN
pushed a commit
that referenced
this issue
Apr 25, 2024
### What problem does this PR solve? modify python benchmark for enwiki fulltext benchmark Issue link:#951 ### Type of change - [x] Refactoring
Ognimalf
pushed a commit
to Ognimalf/infinity
that referenced
this issue
Apr 25, 2024
### What problem does this PR solve? modify python benchmark for enwiki fulltext benchmark Issue link:infiniflow#951 ### Type of change - [x] Refactoring
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Is there an existing issue for the same feature request?
Is your feature request related to a problem?
No response
Describe the feature you'd like
Currently, there is a lack of benchmarks for comparing the vector and full-text search capabilities of various vector databases/search engines. The goal of the issue is to evaluate hybrid search performance under the same hardware conditions using a unified framework.
Describe implementation you've considered
No response
Documentation, adoption, use case
No response
Additional information
No response
The text was updated successfully, but these errors were encountered: