Add introducing reciprocal rank fusion for hybrid search blog #3621
Conversation
Signed-off-by: Ryan Bogan <[email protected]>
ryanbogan
requested review from
elfisher,
AMoo-Miki,
nknize,
krisfreedain,
peterzhuamazon,
CEHENKLE,
dtaivpp,
kolchfa-aws,
nateynateynate and
natebower
as code owners
Signed-off-by: Fanit Kolchina <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
There was a problem hiding this comment.
@kolchfa-aws @ryanbogan Editorial review complete. Nice job on this 😄. Please see my comments and changes and let me know if you have any questions. Thanks!
Cc: @pajuric
_posts/2025-02-04-introducing-reciprocal-rank-fusion-hybrid-search.md
Outdated
Show resolved
Hide resolved
_posts/2025-02-04-introducing-reciprocal-rank-fusion-hybrid-search.md
Outdated
Show resolved
Hide resolved
_posts/2025-02-04-introducing-reciprocal-rank-fusion-hybrid-search.md
Outdated
Show resolved
Hide resolved
_posts/2025-02-04-introducing-reciprocal-rank-fusion-hybrid-search.md
Outdated
Show resolved
Hide resolved
_posts/2025-02-04-introducing-reciprocal-rank-fusion-hybrid-search.md
Outdated
Show resolved
Hide resolved
_posts/2025-02-04-introducing-reciprocal-rank-fusion-hybrid-search.md
Outdated
Show resolved
Hide resolved
| ### CPU utilization | ||
|
|
||
| The following table shows CPU utilization measurements on the coordinator node, comparing hybrid and RRF approaches. The percent difference column indicates the relative change in CPU usage between the two methods. | ||
|
|
There was a problem hiding this comment.
I went with italics for the name of the column, but you can choose different formatting if you'd like.
_posts/2025-02-04-introducing-reciprocal-rank-fusion-hybrid-search.md
Outdated
Show resolved
Hide resolved
_posts/2025-02-04-introducing-reciprocal-rank-fusion-hybrid-search.md
Outdated
Show resolved
Hide resolved
_posts/2025-02-04-introducing-reciprocal-rank-fusion-hybrid-search.md
Outdated
Show resolved
Hide resolved
Co-authored-by: Nathan Bower <[email protected]> Signed-off-by: kolchfa-aws <[email protected]>
|
@pajuric Please edit the meta, and this blog will be ready to publish. |
|
@pajuric This is a 2.19 feature so this blog should be published after 2.19 is released. |
|
Let's tentatively schedule this for 2/11 or 2/12, assuming 2.19 goes out the door on time. |
| has_science_table: true | ||
| categories: | ||
| - technical-posts | ||
| meta_keywords: OpenSearch hybrid search, reciprocal rank fusion, RRF, search ranking, score normalization, Min-max normalization, L2 normalization, ranking algorithms, data normalization |
There was a problem hiding this comment.
Please update the meta with the following:
meta_keywords: reciprocal rank fusion, OpenSearch 2.19, neural search plugin, hybrid search, relevance ranking, search normalization, k-nn search, L2 normalization, how reciprocal rank fusion works
meta_description: Learn about reciprocal rank fusion (RRF) using the Neural Search plugin in OpenSearch 2.19. Discover how this new approach to hybrid search merges results from multiple query sources for improved relevance.
Description
Add introducing reciprocal rank fusion for hybrid search blog. Goal for release date is post 2.19 release.
Issues Resolved
#3541
Check List
By submitting this pull request, I confirm that my contribution is made under the terms of the BSD-3-Clause License.