[DOCS] Adds GET, GET stats and DELETE inference APIs (#50224)

Co-Authored-By: Lisa Cawley <lcawley@elastic.co>

docs/reference/ml/df-analytics/apis/delete-inference-trained-model.asciidoc

@@ -0,0 +1,67 @@
+[role="xpack"]
+[testenv="basic"]
+[[delete-inference]]
+=== Delete {infer} trained model API
+[subs="attributes"]
+++++
+<titleabbrev>Delete {infer} trained model</titleabbrev>
+++++
+
+Deletes an existing trained {infer} model that is currently not referenced by an 
+ingest pipeline.
+
+experimental[]
+
+
+[[ml-delete-inference-request]]
+==== {api-request-title}
+
+`DELETE _ml/inference/<model_id>`
+
+
+[[ml-delete-inference-prereq]]
+==== {api-prereq-title}
+
+* You must have `machine_learning_admin` built-in role to use this API. For more 
+information, see <<security-privileges>> and <<built-in-roles>>.
+
+
+[[ml-delete-inference-path-params]]
+==== {api-path-parms-title}
+
+`<model_id>`::
+(Optional, string) 
+include::{docdir}/ml/ml-shared.asciidoc[tag=model-id]
+
+
+[[ml-delete-inference-response-codes]]
+==== {api-response-codes-title}
+
+`409`::
+  The code indicates that the trained {infer} model is referenced by an ingest 
+  pipeline and cannot be deleted.
+
+
+[[ml-delete-inference-example]]
+==== {api-examples-title}
+
+The following example deletes the `regression-job-one-1574775307356` trained 
+model:
+
+[source,console]
+--------------------------------------------------
+DELETE _ml/inference/regression-job-one-1574775307356
+--------------------------------------------------
+// TEST[skip:TBD]
+
+The API returns the following result:
+
+
+[source,console-result]
+----
+{
+  "acknowledged" : true
+}
+----
+
+

docs/reference/ml/df-analytics/apis/get-inference-trained-model-stats.asciidoc

@@ -0,0 +1,134 @@
+[role="xpack"]
+[testenv="basic"]
+[[get-inference-stats]]
+=== Get {infer} trained model statistics API
+[subs="attributes"]
+++++
+<titleabbrev>Get {infer} trained model stats</titleabbrev>
+++++
+
+Retrieves usage information for trained {infer} models.
+
+experimental[]
+
+
+[[ml-get-inference-stats-request]]
+==== {api-request-title}
+
+`GET _ml/inference/_stats` +
+
+`GET _ml/inference/_all/_stats` +
+
+`GET _ml/inference/<model_id>/_stats` +
+
+`GET _ml/inference/<model_id>,<model_id_2>/_stats` +
+
+`GET _ml/inference/<model_id_pattern*>,<model_id_2>/_stats`
+
+
+[[ml-get-inference-stats-prereq]]
+==== {api-prereq-title}
+
+* You must have `monitor_ml` privilege to use this API. For more information, 
+see <<security-privileges>> and <<built-in-roles>>.
+
+
+[[ml-get-inference-stats-desc]]
+==== {api-description-title}
+
+You can get usage information for multiple trained models in a single API 
+request by using a comma-separated list of model IDs or a wildcard expression.
+
+
+[[ml-get-inference-stats-path-params]]
+==== {api-path-parms-title}
+
+`<model_id>`::
+(Optional, string) 
+include::{docdir}/ml/ml-shared.asciidoc[tag=model-id]
+
+
+[[ml-get-inference-stats-query-params]]
+==== {api-query-parms-title}
+
+`allow_no_match`::
+(Optional, boolean) 
+include::{docdir}/ml/ml-shared.asciidoc[tag=allow-no-match]
+
+`from`::
+(Optional, integer) 
+include::{docdir}/ml/ml-shared.asciidoc[tag=from]
+
+`size`::
+(Optional, integer) 
+include::{docdir}/ml/ml-shared.asciidoc[tag=size]
+
+
+[[ml-get-inference-stats-response-codes]]
+==== {api-response-codes-title}
+
+`404` (Missing resources)::
+  If `allow_no_match` is `false`, this code indicates that there are no
+  resources that match the request or only partial matches for the request.
+  
+
+[[ml-get-inference-stats-example]]
+==== {api-examples-title}
+
+The following example gets usage information for all the trained models:
+
+[source,console]
+--------------------------------------------------
+GET _ml/inference/_stats
+--------------------------------------------------
+// TEST[skip:TBD]
+
+
+The API returns the following results:
+
+[source,console-result]
+----
+{
+  "count": 2,
+  "trained_model_stats": [
+    {
+      "model_id": "flight-delay-prediction-1574775339910",
+      "pipeline_count": 0
+    },
+    {
+      "model_id": "regression-job-one-1574775307356",
+      "pipeline_count": 1,
+      "ingest": {
+        "total": {
+          "count": 178,
+          "time_in_millis": 8,
+          "current": 0,
+          "failed": 0
+        },
+        "pipelines": {
+          "flight-delay": {
+            "count": 178,
+            "time_in_millis": 8,
+            "current": 0,
+            "failed": 0,
+            "processors": [
+              {
+                "inference": {
+                  "type": "inference",
+                  "stats": {
+                    "count": 178,
+                    "time_in_millis": 7,
+                    "current": 0,
+                    "failed": 0
+                  }
+                }
+              }
+            ]
+          }
+        }
+      }
+    }
+  ]
+}
+----
+// NOTCONSOLE

docs/reference/ml/df-analytics/apis/get-inference-trained-model.asciidoc

@@ -0,0 +1,96 @@
+[role="xpack"]
+[testenv="basic"]
+[[get-inference]]
+=== Get {infer} trained model API
+[subs="attributes"]
+++++
+<titleabbrev>Get {infer} trained model</titleabbrev>
+++++
+
+Retrieves configuration information for a trained {infer} model.
+
+experimental[]
+
+
+[[ml-get-inference-request]]
+==== {api-request-title}
+
+`GET _ml/inference/` +
+
+`GET _ml/inference/<model_id>` +
+
+`GET _ml/inference/_all` +
+
+`GET _ml/inference/<model_id1>,<model_id2>` +
+
+`GET _ml/inference/<model_id_pattern*>`
+
+
+[[ml-get-inference-prereq]]
+==== {api-prereq-title}
+
+* You must have `monitor_ml` privilege to use this API. For more information, 
+see <<security-privileges>> and <<built-in-roles>>.
+
+
+[[ml-get-inference-desc]]
+==== {api-description-title}
+
+You 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.
+
+
+[[ml-get-inference-path-params]]
+==== {api-path-parms-title}
+
+`<model_id>`::
+(Optional, string) 
+include::{docdir}/ml/ml-shared.asciidoc[tag=model-id]
+
+
+[[ml-get-inference-query-params]]
+==== {api-query-parms-title}
+
+`allow_no_match`::
+(Optional, boolean) 
+include::{docdir}/ml/ml-shared.asciidoc[tag=allow-no-match]
+
+`decompress_definition`::
+(Optional, boolean)
+include::{docdir}/ml/ml-shared.asciidoc[tag=decompress-definition]
+
+`from`::
+(Optional, integer) 
+include::{docdir}/ml/ml-shared.asciidoc[tag=from]
+
+`include_model_definition`::
+(Optional, boolean)
+include::{docdir}/ml/ml-shared.asciidoc[tag=include-model-definition]
+
+`size`::
+(Optional, integer) 
+include::{docdir}/ml/ml-shared.asciidoc[tag=size]
+
+
+[[ml-get-inference-response-codes]]
+==== {api-response-codes-title}
+
+`400`::
+  If `include_model_definition` is `true`, this code indicates that more than 
+  one models match the ID pattern.
+
+`404` (Missing resources)::
+  If `allow_no_match` is `false`, this code indicates that there are no
+  resources that match the request or only partial matches for the request.
+  
+
+[[ml-get-inference-example]]
+==== {api-examples-title}
+
+The following example gets configuration information for all the trained models:
+
+[source,console]
+--------------------------------------------------
+GET _ml/inference/
+--------------------------------------------------
+// TEST[skip:TBD]

docs/reference/ml/df-analytics/apis/index.asciidoc

@@ -16,12 +16,21 @@ You can use the following APIs to perform {ml} {dfanalytics} activities.
 
 For the `analysis` object resources, check <<ml-dfa-analysis-objects>>.
 
+
+You can use the following APIs to perform {infer} operations.
+
+* <<get-inference>>
+* <<get-inference-stats>>
+* <<delete-inference>>
+
+
 See also <<ml-apis>>.
 
 //CREATE
 include::put-dfanalytics.asciidoc[]
 //DELETE
 include::delete-dfanalytics.asciidoc[]
+include::delete-inference-trained-model.asciidoc[]
 //EVALUATE
 include::evaluate-dfanalytics.asciidoc[]
 //ESTIMATE_MEMORY_USAGE
@@ -29,6 +38,8 @@ include::explain-dfanalytics.asciidoc[]
 //GET
 include::get-dfanalytics.asciidoc[]
 include::get-dfanalytics-stats.asciidoc[]
+include::get-inference-trained-model.asciidoc[]
+include::get-inference-trained-model-stats.asciidoc[]
 //SET/START/STOP
 include::start-dfanalytics.asciidoc[]
 include::stop-dfanalytics.asciidoc[]

docs/reference/ml/ml-shared.asciidoc

@@ -483,6 +483,11 @@ Identifier for the {dfeed}. It can be a {dfeed} identifier or a wildcard
 expression.
 end::datafeed-id-wildcard[]
 
+tag::decompress-definition[]
+Specifies whether the included model definition should be returned as a JSON map (`true`) or 
+in a custom compressed format (`false`). Defaults to `true`.
+end::decompress-definition[]
+
 tag::delayed-data-check-config[]
 Specifies whether the {dfeed} checks for missing data and the size of the
 window. For example: `{"enabled": true, "check_window": "1h"}`.
@@ -688,6 +693,12 @@ tag::groups[]
 A list of job groups. A job can belong to no groups or many.
 end::groups[]
 
+tag::include-model-definition[]
+Specifies if the model definition should be returned in the response. Defaults 
+to `false`. When `true`, only a single model must match the ID patterns 
+provided, otherwise a bad request is returned.
+end::include-model-definition[]
+
 tag::indices[]
 An array of index names. Wildcards are supported. For example:
 `["it_ops_metrics", "server*"]`.
@@ -828,6 +839,10 @@ recommended value.
 --
 end::mode[]
 
+tag::model-id[]
+The unique identifier of the trained {infer} model.
+end::model-id[]
+
 tag::model-memory-limit[]
 The approximate maximum amount of memory resources that are required for 
 analytical processing. Once this limit is approached, data pruning becomes