-
Notifications
You must be signed in to change notification settings - Fork 203
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
End-to-end vector search tutorial in docs #1776
End-to-end vector search tutorial in docs #1776
Conversation
@wphicks it would be great if you have cycles to add some verbiage and examples around |
Just pushed some text on |
/ok to test |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I really like this tutorial - I think its very clear and well written, and will be a great introduction on how to use raft for ANN.
Some minor comments:
- There is a great introduction on using RAFT and device_resources in the
cuda development
section - but we don't tie it into the example code using the BF and CAGRA example code blocks later. I think we should add ares.sync_stream()
to the BF/CAGRA example code blocks , and maybe also a snippet that copies the results back to host memory - The section on using a
stream_pool
doesn't need to be here (though this is super useful, and we should keep for other parts of the documentation somewhere). Consumers of our vector search indices don't typically need a stream_pool, so this information might be best put elsewhere
…into doc-vector_search_tutorial
/ok to test |
/merge |
Closes rapidsai#1745 Authors: - Corey J. Nolet (https://github.com/cjnolet) - William Hicks (https://github.com/wphicks) - Divye Gala (https://github.com/divyegala) Approvers: - Ben Frederickson (https://github.com/benfred) URL: rapidsai#1776
Closes #1745