Get inference trained model API
editGet inference trained model API
editRetrieves configuration information for a trained inference model.
This functionality is in technical preview and may be changed or removed in a future release. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features.
Request
editGET _ml/inference/
GET _ml/inference/<model_id>
GET _ml/inference/_all
GET _ml/inference/<model_id1>,<model_id2>
GET _ml/inference/<model_id_pattern*>
Prerequisites
editRequired privileges which should be added to a custom role:
-
cluster:
monitor_ml
For more information, see Security privileges and Built-in roles.
Description
editYou can get information for multiple trained models in a single API request by using a comma-separated list of model IDs or a wildcard expression.
Path parameters
edit-
<model_id>
- (Optional, string) The unique identifier of the trained inference model.
Query parameters
edit-
allow_no_match
-
(Optional, boolean) Specifies what to do when the request:
- Contains wildcard expressions and there are no data frame analytics jobs that match.
-
Contains the
_all
string or no identifiers and there are no matches. - Contains wildcard expressions and there are only partial matches.
The default value is
true
, which returns an emptydata_frame_analytics
array when there are no matches and the subset of results when there are partial matches. If this parameter isfalse
, the request returns a404
status code when there are no matches or only partial matches. -
decompress_definition
-
(Optional, boolean)
Specifies whether the included model definition should be returned as a JSON map
(
true
) or in a custom compressed format (false
). Defaults totrue
. -
from
-
(Optional, integer)
Skips the specified number of data frame analytics jobs. The default value is
0
. -
include_model_definition
-
(Optional, boolean)
Specifies if the model definition should be returned in the response. Defaults
to
false
. Whentrue
, only a single model must match the ID patterns provided, otherwise a bad request is returned. -
size
-
(Optional, integer)
Specifies the maximum number of data frame analytics jobs to obtain. The default value
is
100
.
Response body
edit-
trained_model_configs
-
(array) An array of trained model resources, which are sorted by the
model_id
value in ascending order.-
model_id
- (string) Idetifier for the trained model.
-
created_by
- (string) Information on the creator of the trained model.
-
version
- (string) The Elasticsearch version number in which the trained model was created.
-
create_time
- (time units) The time when the trained model was created.
-
tags
- (string) A comma delimited string of tags. A inference model can have many tags, or none.
-
metadata
-
(object)
An object containing metadata about the trained model. For example, models
created by data frame analytics contain an
analysis_config
and aninput
object. -
estimated_heap_memory_usage_bytes
- (integer) The estimated heap usage in bytes to keep the trained model in memory.
-
estimated_operations
- (integer) The estimated number of operations to use the trained model.
-
license_level
- (string) The license level of the trained model.
-
Response codes
edit-
400
-
If
include_model_definition
istrue
, this code indicates that more than one models match the ID pattern. -
404
(Missing resources) -
If
allow_no_match
isfalse
, this code indicates that there are no resources that match the request or only partial matches for the request.
Examples
editThe following example gets configuration information for all the trained models:
GET _ml/inference/