From 6e225194e6c773718aa1743d96a16b1e2b9a8f98 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Istv=C3=A1n=20Zolt=C3=A1n=20Szab=C3=B3?= Date: Thu, 5 Oct 2023 14:44:09 +0200 Subject: [PATCH] [DOCS] Highlights how to switch to ELSER v2 from v1 (#2555) --- docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc b/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc index ce2299143..a2f469504 100644 --- a/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc +++ b/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc @@ -61,9 +61,16 @@ 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. -IMPORTANT: ELSER v2 is not backward compatible. If you indexed your data with -ELSER v1, you need to reindex it with an ingest pipeline referencing ELSER v2 to -be able to use v2 for search. + +[discrete] +[[upgrade-elser-v2]] +=== Upgrading to ELSER v2 + +ELSER v2 is not backward compatible. If you indexed your data with ELSER v1, you +need to reindex it with an ingest pipeline referencing ELSER v2 to be able to +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. // TO DO // If you want to learn more about the ELSER v2 improvements, refer to this blog