Add boosting k-NN exact search blog #3448
Conversation
Signed-off-by: Fanit Kolchina <[email protected]>
kolchfa-aws
requested review from
elfisher,
AMoo-Miki,
nknize,
krisfreedain,
peterzhuamazon,
CEHENKLE,
dtaivpp,
nateynateynate and
natebower
as code owners
There was a problem hiding this comment.
@kolchfa-aws Editorial review complete. This is looking good. Please see my comment (just one 😄) 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]>
|
@pajuric Editorial comments addressed. Please review/update the meta. Thanks! |
|
@kolchfa-aws Thanks for raising the PR and making the edits. Would it be possible to remove the 2.14/2.15 table and just have the 2.14/2.17? |
|
|
||
| ### Conclusion | ||
|
|
||
| The tests showed that OpenSearch's new SIMD optimizations resulted in significant latency reductions, especially for the inner product space type, which saw up to an 87% latency reduction at the 99th percentile. |
There was a problem hiding this comment.
Can we generalize SIMD to "new SIMD support and optimized memory access". We added optimized memory access in 2.17
|
|
||
| The following table provides a latency comparison between OpenSearch versions 2.14 and 2.15. | ||
|
|
||
| |Space type |Version |50th percentile latency (ms) |90th percentile latency (ms) |99th percentile latency (ms) | |
There was a problem hiding this comment.
Lets just look at 2.14 vs 2.17 and remove this table.
Signed-off-by: Fanit Kolchina <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
|
@kolchfa-aws - Just confirming that this went through final review with Nathan while I was out. |
|
@pajuric Yes, this has gone through editorial review. |
| - jmazane | ||
| - vamshin | ||
| - kolchfa | ||
| date: 2024-11-13 |
There was a problem hiding this comment.
Please update to today's date - 2024-11-19
| - technical-posts | ||
| has_science_table: true | ||
| meta_keywords: exact k-NN search in OpenSearch, SIMD optimizations, query performance, relevance scoring, latency management | ||
| meta_description: Learn how to achieve precise, high-performance search with exact k-NN in OpenSearch. |
There was a problem hiding this comment.
Please update the meta with the following:
meta _keywords: k-NN search performance, SIMD in OpenSearch, script score queries, performance optimization, machine learning, exact K-NN
meta_description: Boost exact k-NN search performance in OpenSearch using SIMD optimizations and script_score queries. Discover real-world performance gains for efficient vector similarity searches in machine learning applications.
|
@ryanbogan @kolchfa-aws - I updated the date and meta for this blog. Once those changes are made, we'll push it live |
Signed-off-by: kolchfa-aws <[email protected]>
|
@krisfreedain @nateynateynate - Blog is ready to publish. |
Add boosting k-NN exact search blog
Check List
By submitting this pull request, I confirm that my contribution is made under the terms of the BSD-3-Clause License.