Skip to content

Commit

Permalink
Adds reference to ELSER V2 blog post (#2586) (#2587)
Browse files Browse the repository at this point in the history
* Adds reference to ELSER V2 blog post.

* Relocates link.

(cherry picked from commit 08d90ae)

Co-authored-by: István Zoltán Szabó <[email protected]>
  • Loading branch information
mergify[bot] and szabosteve authored Nov 7, 2023
1 parent bbb08f6 commit 2496d18
Showing 1 changed file with 10 additions and 4 deletions.
14 changes: 10 additions & 4 deletions docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,9 @@ one version which is optimized for Intel® silicon. The **Model Management** >
**Trained Models** page shows you which version of ELSER v2 is recommended to
deploy based on your cluster's hardware.

If you want to learn more about the ELSER V2 improvements, refer to
https://www.elastic.co/search-labs/introducing-elser-v2-part-1[this blog post].


[discrete]
[[upgrade-elser-v2]]
Expand All @@ -89,11 +92,10 @@ use v2 for search. This {ref}/semantic-search-elser.html[tutorial] shows you how
to create an ingest pipeline with an {infer} processor that uses ELSER v2, and
how to reindex your data through the pipeline.

Additionally, the `elasticearch-labs` GitHub repository contains an interactive https://github.com/elastic/elasticsearch-labs/blob/main/notebooks/model-upgrades/upgrading-index-to-use-elser.ipynb[Python notebook] that walks through upgrading an index to ELSER v2.
Additionally, the `elasticearch-labs` GitHub repository contains an interactive
https://github.com/elastic/elasticsearch-labs/blob/main/notebooks/model-upgrades/upgrading-index-to-use-elser.ipynb[Python notebook]
that walks through upgrading an index to ELSER V2.

// TO DO
// If you want to learn more about the ELSER v2 improvements, refer to this blog
// post.

[discrete]
[[download-deploy-elser]]
Expand Down Expand Up @@ -457,6 +459,10 @@ performed on a 16vCPU machine, with all documents containing exactly 256 tokens.
IMPORTANT: The length of the documents in your particular dataset will have a
significant impact on your throughput numbers.

Refer to
https://www.elastic.co/search-labs/introducing-elser-v2-part-1[this blog post]
to learn more about ELSER V2 improved performance.

image::images/ml-nlp-elser-bm-summary.png[alt="Summary of ELSER V1 and V2 benchmark reports",align="center"]

**The platform specific** results show a nearly linear growth up until 8
Expand Down

0 comments on commit 2496d18

Please sign in to comment.