Add hybrid search blog #2182
Add hybrid search blog #2182
Conversation
Signed-off-by: Fanit Kolchina <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
kolchfa-aws
requested review from
elfisher,
AMoo-Miki,
nknize,
krisfreedain,
peterzhuamazon,
CEHENKLE,
dtaivpp and
nateynateynate
as code owners
Signed-off-by: Fanit Kolchina <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
| --- | ||
| layout: post | ||
| title: Hybrid search is generally available in OpenSearch 2.10 | ||
| authors: |
There was a problem hiding this comment.
I think we need to add Vamshi as well, @navneet1v what do you think?
Signed-off-by: Fanit Kolchina <[email protected]>
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.
This image has a comment on it, lets fix the image
_posts/2023-09-21-hybrid-search.md
Outdated
| * Executing individual queries in parallel. | ||
| * Adding more configuration options and parameters to the normalization processor to allow more control over combined results. For instance, we can add the ability to specify a minimal score for documents to be returned in the results, which will avoid returning non-competitive hits. | ||
| * Supporting results pagination | ||
| * Supporting filters in the hybrid query clause. It’s possible to define a filter for each inner query individually, but it’s not optimal if a filter condition is the same for all inner queries. | ||
| * Adding more benchmark results for larger datasets so we can provide recommendations for using hybrid search in various configurations. | ||
|
|
There was a problem hiding this comment.
we have github issues around all of them. @martin-gaievski please provide those issues here
There was a problem hiding this comment.
sure, here are the issues I opened for future work:
- [FEATURE] Implement parallel execution of sub-queries for hybrid search neural-search#279
- [FEATURE] Implement pagination for Hybrid Search neural-search#280
- [FEATURE] Provide a way to run Hybrid search in parallel with concurrent search feature neural-search#281
- [FEATURE] Add top level filter clause to hybrid query clause to avoid duplication of filters in sub query clause of hybrid search neural-search#282
- [FEATURE] Add options to configure minimal score and single match score fo normalization processor for Hybrid search neural-search#299
Signed-off-by: Fanit Kolchina <[email protected]>
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 Please see my comments and changes and push to @pajuric once addressed. Thanks!
_posts/2023-09-21-hybrid-search.md
Outdated
|
|
||
| ## References | ||
|
|
||
| 1. The ABCs of semantic search in OpenSearch: Architectures, benchmarks, and combination strategies, https://opensearch.org/blog/semantic-science-benchmarks. |
There was a problem hiding this comment.
| 1. The ABCs of semantic search in OpenSearch: Architectures, benchmarks, and combination strategies, https://opensearch.org/blog/semantic-science-benchmarks. | |
| 1. _The ABCs of semantic search in OpenSearch: Architectures, benchmarks, and combination strategies_. https://opensearch.org/blog/semantic-science-benchmarks. |
_posts/2023-09-21-hybrid-search.md
Outdated
|
|
||
| ## References | ||
|
|
||
| 1. The ABCs of semantic search in OpenSearch: Architectures, benchmarks, and combination strategies, https://opensearch.org/blog/semantic-science-benchmarks. |
There was a problem hiding this comment.
As I've done here, let's put the titles in italics and separate the titles from the links with a period.
Co-authored-by: Nathan Bower <[email protected]> Signed-off-by: kolchfa-aws <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
|
@pajuric This blog has been through editorial review and I've addressed all comments. The only thing missing is the meta/keywords; otherwise it's ready to publish. Thanks! |
_posts/2023-09-21-hybrid-search.md
Outdated
| date: 2023-09-21 | ||
| categories: | ||
| - technical-posts | ||
| meta_keywords: |
There was a problem hiding this comment.
Please update with the following meta:
meta_keywords: Improve search relevance, hybrid search in OpenSearch 2.10, semantic and keyword search
meta_description: Improve search relevance with OpenSearch 2.10 when you tune search relevance by using hybrid search to combine and normalize query relevance scores.
There was a problem hiding this comment.
@pajuric Done, thank you!
Signed-off-by: Fanit Kolchina <[email protected]>
|
@krisfreedain @dtaivpp - We are GTG on pushing this blog live. |
minor edits to date and hyperlinks
|
When the blog going live? |
|
|
||
| The following table provides further details of the test datasets used for benchmarking. | ||
|
|
||
| |Dataset |Average query length |Average query length |Average query length |Average query length |Average query length |Average query length | |
There was a problem hiding this comment.
The headings are all same. :( This needs to be fixed.
There was a problem hiding this comment.
Description
Adds hybrid search blog
Issues Resolved
Fixes #1872
Check List
By submitting this pull request, I confirm that my contribution is made under the terms of the BSD-3-Clause License.