mirror of
https://github.com/elastic/elasticsearch.git
synced 2025-06-30 10:23:41 -04:00
16bfc550ea
This commit adds a new API that users can use calling:
```
POST _ml/trained_models/{model_id}/deployment/_update
{
"number_of_allocations": 4
}
```
This allows a user to update the number of allocations for a deployment
that is `started`.
If the allocations are increased we rebalance and let the assignment
planner find how to allocate the additional allocations.
If the allocations are decreased we cannot use the assignment planner.
Instead, we implement the reduction in a new class `AllocationReducer`
that tries to reduce the allocations so that:
1. availability zone balance is maintained
2. assignments that can be completely stopped are preferred to release memory
25 lines
873 B
Text
25 lines
873 B
Text
[role="xpack"]
|
|
[[ml-df-trained-models-apis]]
|
|
= {ml-cap} trained model APIs
|
|
|
|
You can use the following APIs to perform model management operations:
|
|
|
|
* <<clear-trained-model-deployment-cache>>
|
|
* <<put-trained-models>>
|
|
* <<put-trained-model-definition-part>>
|
|
* <<put-trained-model-vocabulary>>
|
|
* <<put-trained-models-aliases>>
|
|
* <<delete-trained-models>>
|
|
* <<delete-trained-models-aliases>>
|
|
* <<get-trained-models>>
|
|
* <<get-trained-models-stats>>
|
|
* <<infer-trained-model>>
|
|
* <<start-trained-model-deployment>>
|
|
* <<stop-trained-model-deployment>>
|
|
* <<update-trained-model-deployment>>
|
|
|
|
You can deploy a trained model to make predictions in an ingest pipeline or in
|
|
an aggregation. Refer to the following documentation to learn more:
|
|
|
|
* <<search-aggregations-pipeline-inference-bucket-aggregation,{infer-cap} bucket aggregation>>
|
|
* <<inference-processor,{infer-cap} processor>>
|