-
Notifications
You must be signed in to change notification settings - Fork 15
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
bench: Comparison with pgvectorscale #125
Comments
Comparison with pgvectorscaleDataset: laion-5m-768dim Advantages of pgvectorscale✅ Double the capacity To store the whole dataset,
Our scaler8 type might solve it. ✅ Fantastic cold start VectorChord and pgvectorscale have a similar query speed at warm state. For VectorChord, cold start is much slower than warm state, from QPS However, we observed only about 2x accerate from pgvectorscale cold to warm. We can say it doesn't need prewarm at all. Disadvantages of pgvectorscale❌ Slower index build speed
❌ Not better performance With the default argument and both dot/L2 metric on our dataset, we can not find a recall > 0.8 by configure query-time parameters: diskann.query_search_list_size Even the dataset is dot-based, an dot metric is even worse than l2 metric. L2 metric:
Dot metric:
For VectorChord, a typical recall standard is 0.95, the whole result can be found at #42 (comment) . Update: Dot metric with more rerank(default = 500): While change only For default value,
|
What is the memory usage after prewarm? |
Without the recall performance, the speed is useless. |
Does more rerank help in pgvectorscale? |
It is much useful, I have updated the new result.
About |
No description provided.
The text was updated successfully, but these errors were encountered: