From fde1c53abc5a02ec68bb5c8e29f9be73178aab65 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Istv=C3=A1n=20Zolt=C3=A1n=20Szab=C3=B3?= Date: Thu, 2 Nov 2023 15:39:21 +0100 Subject: [PATCH] Adds note on ELSER V2 is GA and V1 is in preview. (#2581) --- docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc b/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc index a23776378..37838d4b0 100644 --- a/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc +++ b/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc @@ -9,8 +9,6 @@ :frontmatter-tags-content-type: [how-to] :frontmatter-tags-user-goals: [analyze] -experimental[] - Elastic Learned Sparse EncodeR - or ELSER - is a retrieval model trained by Elastic that enables you to perform {ref}/semantic-search-elser.html[semantic search] to retrieve more relevant @@ -20,6 +18,9 @@ meaning and user intent, rather than exact keyword matches. ELSER is an out-of-domain model which means it does not require fine-tuning on your own data, making it adaptable for various use cases out of the box. +IMPORTANT: While ELSER V2 is generally available, ELSER V1 is in experimental:[] +and will remain in technical preview. + [discrete] [[elser-tokens]]