Skip to content

HNSW tuning guide #3684

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

Merged
merged 10 commits into from
Apr 10, 2025
Merged

Conversation

huibinshen
Copy link

Description

We publish a blogpost to make HNSW tuning easier.

Issues Resolved

#3683

Check List

  • Commits are signed per the DCO using --signoff

By submitting this pull request, I confirm that my contribution is made under the terms of the BSD-3-Clause License.

| [NYTimes](https://archive.ics.uci.edu/dataset/164/bag+of+wordsD199572657/) | 16 | 290,000 | 10,000 | 100 | Angular | BoW | Language, news article |
| [SIFT](http://corpus-texmex.irisa.fr/) | 128 | 1,000,000 | 10,000 | 100 | Euclidean | SIFT descriptors | Image |
| [SIFT](https://github.com/erikbern/ann-benchmarks/tree/main) | 256 | 1,000,000 | 10,000 | 100 | Hamming | SIFT descriptors | Image |
| [Last.fm](http://millionsongdataset.com/lastfm/) | 65 | 292,385 | 50,000 | 100 | Inner product | Matric Factorization | Song recommendation |
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@huibinshen Do you mean "matrix factorization"?

@kolchfa-aws
Copy link
Collaborator

@pajuric Could you please update the meta for this blog? Thanks!

@kolchfa-aws
Copy link
Collaborator

@huibinshen Could you also fix DCO for your commits please?

huibishe and others added 6 commits March 31, 2025 10:35
Signed-off-by: huibishe <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
Copy link
Collaborator

@natebower natebower left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@kolchfa-aws @huibinshen Editorial review complete. Please see my comments and changes and let me know if you have any questions. Thanks!

Co-authored-by: Nathan Bower <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>
@kolchfa-aws
Copy link
Collaborator

@pajuric Editorial comments addressed. Please update the meta, and this blog will be ready to publish.

@kolchfa-aws kolchfa-aws removed their assignment Apr 1, 2025
@pajuric
Copy link

pajuric commented Apr 9, 2025

@huibinshen - please update the blog publish date and meta keywords, and then we'll prep this to publish tomorrow.

Signed-off-by: huibishe <[email protected]>
@huibinshen
Copy link
Author

@huibinshen - please update the blog publish date and meta keywords, and then we'll prep this to publish tomorrow.

Publish date updated. The old keywords seem fine to me, if you have other suggestions, let me know.

@pajuric
Copy link

pajuric commented Apr 10, 2025

@nateynateynate @krisfreedain - Please push this one live. Thank you!

Copy link
Member

@krisfreedain krisfreedain left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@krisfreedain krisfreedain merged commit d8900e9 into opensearch-project:main Apr 10, 2025
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants