Skip to content

Commit 29a10ed

Browse files
Update "Download and deploy ELSER" snippet with adaptive allocations (#2878) (#2880)
(cherry picked from commit 5740148) Co-authored-by: Liam Thompson <32779855+leemthompo@users.noreply.github.com>
1 parent e72d950 commit 29a10ed

File tree

1 file changed

+6
-1
lines changed

1 file changed

+6
-1
lines changed

docs/en/stack/ml/nlp/ml-nlp-elser.asciidoc

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -124,14 +124,19 @@ PUT _inference/sparse_embedding/my-elser-model
124124
{
125125
"service": "elasticsearch",
126126
"service_settings": {
127-
"num_allocations": 1,
127+
"adaptive_allocations": {
128+
"enabled": true,
129+
"min_number_of_allocations": 1,
130+
"max_number_of_allocations": 10
131+
},
128132
"num_threads": 1,
129133
"model_id": ".elser_model_2_linux-x86_64"
130134
}
131135
}
132136
----------------------------------
133137
--
134138
The API request automatically initiates the model download and then deploy the model.
139+
This example uses <<ml-nlp-auto-scale,autoscaling>> through adaptive allocation.
135140

136141
Refer to the {ref}/infer-service-elser.html[ELSER {infer} service documentation] to learn more about the available settings.
137142

0 commit comments

Comments
 (0)