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
Indexed Vector Similarity and kNN Search #35101
Comments
Good to see a soluntion for KNN(maybe ANN sometime later?) |
@qieqieplus Now we also have Lp norms and distance functions: https://presentations.clickhouse.com/release_21.11/#20 Good for non-indexed, brute-force search. |
In fact, we are now working with algorithms for ANN |
Yes I'm aware of that, as I commented in #27933, those functions only work for data type I made a quick benchmark of BF search on With 1Million random generate 256D Uint8 vectors, each query time and memory increased: Test Platform: CPU: Xeon(R) CPU E5-2630 v4 |
@qieqieplus Yes, it makes sense to implement functions on arrays with BLAS, the performance numbers are very impressive. |
@alexey-milovidov I'm glad to. I'll send a PR when ready. |
Wow, clickhouse now is a set of many tools. |
Hi, when is Clickhouse going to launch vector retrieval for KNN or Ann? Any plans? |
ClickHouse For AI presentation: https://presentations.clickhouse.com/meetup74/ai/ |
Attempt to make Annoy index ready to use: #50312 But it is not required, as in the video above, I showed how to construct the same index manually, and it allows tuning between speed and precision dynamically. |
Use case
Search and analytics on datasets with vector embeddings.
Describe the solution you'd like
The solution is being implemented by the team led by @FArthur-cmd
The text was updated successfully, but these errors were encountered: