File tree Expand file tree Collapse file tree 1 file changed +7
-2
lines changed
docs/reference/search/search-your-data Expand file tree Collapse file tree 1 file changed +7
-2
lines changed Original file line number Diff line number Diff line change @@ -29,8 +29,13 @@ in your cluster. Refer to the
29
29
deploy the model.
30
30
31
31
NOTE: The minimum dedicated ML node size for deploying and using the ELSER model
32
- is 4 GB. This is a minimum and better performance can be achieved by using
33
- bigger ML nodes.
32
+ is 4 GB in Elasticsearch Service if
33
+ {cloud}/ec-autoscaling.html[deployment autoscaling] is turned off. Turning on
34
+ autoscaling is recommended because it allows your deployment to dynamically
35
+ adjust resources based on demand. Better performance can be achieved by using
36
+ more allocations or more threads per allocation, which requires bigger ML nodes.
37
+ Autoscaling provides bigger nodes when required. If autoscaling is turned off,
38
+ you must provide suitably sized nodes yourself.
34
39
35
40
36
41
[discrete]
You can’t perform that action at this time.
0 commit comments