From fe25a6b0c77aae02dd46156daa4154619cd4ea2e Mon Sep 17 00:00:00 2001
From: Liam Thompson <32779855+leemthompo@users.noreply.github.com>
Date: Wed, 27 Nov 2024 11:40:54 +0100
Subject: [PATCH] Update "Download and deploy ELSER" snippet with adaptive
 allocations (#2878)

(cherry picked from commit 57401489d311436254246885568b826f34b5cd08)
---
 docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc b/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc
index 7181f463f..b3fb2779d 100644
--- a/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc
+++ b/docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc
@@ -124,7 +124,11 @@ PUT _inference/sparse_embedding/my-elser-model
 {
   "service": "elasticsearch",
   "service_settings": {
-    "num_allocations": 1,
+    "adaptive_allocations": {
+      "enabled": true,
+      "min_number_of_allocations": 1,
+      "max_number_of_allocations": 10
+    },
     "num_threads": 1,
     "model_id": ".elser_model_2_linux-x86_64"
   }
@@ -132,6 +136,7 @@ PUT _inference/sparse_embedding/my-elser-model
 ----------------------------------
 --
 The API request automatically initiates the model download and then deploy the model.
+This example uses <<ml-nlp-auto-scale,autoscaling>> through adaptive allocation.
 
 Refer to the {ref}/infer-service-elser.html[ELSER {infer} service documentation] to learn more about the available settings.