Skip to content
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

Add Faiss byte vector support blog #3458

Merged
merged 6 commits into from
Nov 26, 2024

Conversation

kolchfa-aws
Copy link
Collaborator

Add Faiss byte vector support blog

Closes #3420

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.

Signed-off-by: Fanit Kolchina <[email protected]>
@kolchfa-aws
Copy link
Collaborator Author

@pajuric Please edit the meta when you get a chance. Thank you!

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

Cc: @pajuric

_posts/2024-11-22-faiss-byte-vector.md Outdated Show resolved Hide resolved
_posts/2024-11-22-faiss-byte-vector.md Outdated Show resolved Hide resolved
_posts/2024-11-22-faiss-byte-vector.md Outdated Show resolved Hide resolved
_posts/2024-11-22-faiss-byte-vector.md Outdated Show resolved Hide resolved
_posts/2024-11-22-faiss-byte-vector.md Outdated Show resolved Hide resolved
_posts/2024-11-22-faiss-byte-vector.md Outdated Show resolved Hide resolved
_posts/2024-11-22-faiss-byte-vector.md Outdated Show resolved Hide resolved
_posts/2024-11-22-faiss-byte-vector.md Outdated Show resolved Hide resolved
## Future enhancements

In future versions, we plan to enhance this feature by adding an `on_disk` mode with a `4x` compression level in Faiss. This mode will accept `fp32` vectors as input, perform online training, and quantize the data into byte-sized vectors, eliminating the need for performing external quantization.

Copy link
Collaborator

Choose a reason for hiding this comment

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

Line 185, first sentence: "compression level in Faiss" => "Faiss compression level"?


OpenSearch 2.17 introduced support for Faiss byte vectors, enabling you to store quantized byte vector embeddings efficiently. This reduces memory consumption by up to 75%, lowers costs, and maintains high performance. These advantages make byte vectors an excellent choice for large-scale similarity search applications, especially where memory resources are limited, and applications that handle large volumes of data within the signed byte value range.

## Future enhancements
Copy link
Collaborator

Choose a reason for hiding this comment

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

Nit: This section should probably precede the conclusion.

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Done

kolchfa-aws and others added 2 commits November 25, 2024 11:29
Co-authored-by: Nathan Bower <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
@kolchfa-aws
Copy link
Collaborator Author

@pajuric Editorial comments addressed. This blog will be ready to publish once we update the meta and date. Thanks!

Co-authored-by: Nathan Bower <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>
@nateynateynate nateynateynate merged commit c19d2ea into opensearch-project:main Nov 26, 2024
5 checks passed
@krisfreedain krisfreedain mentioned this pull request Nov 26, 2024
1 task
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.

[BLOG] Introducing Byte Vector Support for Faiss in Opensearch Vector Engine
4 participants