Add blog on binary vector support in KNN #3418
Conversation
heemin32
requested review from
elfisher,
AMoo-Miki,
nknize,
krisfreedain,
peterzhuamazon,
CEHENKLE,
dtaivpp,
kolchfa-aws,
nateynateynate and
natebower
as code owners
heemin32
force-pushed
the
binary
branch
3 times, most recently
from
2a25516 to
7847be7
Compare
Signed-off-by: Heemin Kim <[email protected]>
|
I've reviewed the blog. It looks good in terms of content. |
|
@pajuric Please review this PR. |
Signed-off-by: Fanit Kolchina <[email protected]>
There was a problem hiding this comment.
@kolchfa-aws Editorial review complete. Please see my comments and changes and let me know if you have any questions. Thanks!
_posts/2024-10-30-lower-your-cost-on-opensearch-using-binary-vectors.md
Outdated
Show resolved
Hide resolved
_posts/2024-10-30-lower-your-cost-on-opensearch-using-binary-vectors.md
Outdated
Show resolved
Hide resolved
_posts/2024-10-30-lower-your-cost-on-opensearch-using-binary-vectors.md
Outdated
Show resolved
Hide resolved
_posts/2024-10-30-lower-your-cost-on-opensearch-using-binary-vectors.md
Outdated
Show resolved
Hide resolved
_posts/2024-10-30-lower-your-cost-on-opensearch-using-binary-vectors.md
Outdated
Show resolved
Hide resolved
_posts/2024-10-30-lower-your-cost-on-opensearch-using-binary-vectors.md
Outdated
Show resolved
Hide resolved
_posts/2024-10-30-lower-your-cost-on-opensearch-using-binary-vectors.md
Outdated
Show resolved
Hide resolved
_posts/2024-10-30-lower-your-cost-on-opensearch-using-binary-vectors.md
Outdated
Show resolved
Hide resolved
Co-authored-by: Nathan Bower <[email protected]> Signed-off-by: kolchfa-aws <[email protected]>
…ectors.md Co-authored-by: Nathan Bower <[email protected]> Signed-off-by: kolchfa-aws <[email protected]>
|
@pajuric: I've addressed editorial comments. Could you review/update the meta for this blog, and it'll be ready for publishing. |
Fix typo Signed-off-by: Heemin Kim <[email protected]>
| categories: | ||
| - technical-posts | ||
| meta_keywords: binary vectors, vector search, efficient vector storage, binary vector performance, large-scale search, cost-effective vector scaling, memory-efficient vectors | ||
| meta_description: Binary vectors significantly reduce memory and storage demands by over 90% compared to FP32 vectors, making them a powerful choice for large-scale vector search applications. Binary vectors help manage massive datasets efficiently, improving performance and cutting costs. |
There was a problem hiding this comment.
Please update the meta keywords and description with the following:
meta keywords: vector search, binary vectors in OpenSearch, k-NN plugin, difference between FP32 and binary vectors, Binary vector challenges, HNSW algorithm
meta description: Explore how binary vectors in OpenSearch revolutionize large-scale vector search, offering significant cost savings and performance improvements over traditional FP32 vectors.
Signed-off-by: Heemin Kim <[email protected]>
| - vamshin | ||
| - dylantong | ||
| - kolchfa | ||
| date: 2024-10-30 00:00:00 -0700 |
There was a problem hiding this comment.
Please update the date to 2024-11-21 and we'll publish this on Thursday,
Signed-off-by: Heemin Kim <[email protected]>
| - vamshin | ||
| - dylantong | ||
| - kolchfa | ||
| date: 2024-11-21 00:00:00 -0700 |
There was a problem hiding this comment.
Update to 2024-11-25 and we'll push this now.
_posts/2024-10-30-lower-your-cost-on-opensearch-using-binary-vectors.md
Outdated
Show resolved
Hide resolved
…ectors.md Signed-off-by: kolchfa-aws <[email protected]>
|
Pushing to staging. |
Description
Add blog on binary vector support in KNN
Issues Resolved
#3417
Check List
By submitting this pull request, I confirm that my contribution is made under the terms of the BSD-3-Clause License.