From 71d2417b922ed712d37ba202839e068606f776da Mon Sep 17 00:00:00 2001
From: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>
Date: Thu, 11 Jan 2024 10:00:58 -0500
Subject: [PATCH] Add examples to get model API (#6128)

* Add examples to get model API

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

* Remove excluding model content because it's excluded by default

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

* Apply suggestions from code review

Co-authored-by: Nathan Bower <nbower@amazon.com>
Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

---------

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>
Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>
Co-authored-by: Nathan Bower <nbower@amazon.com>
---
 .../api/model-apis/get-model.md               | 80 +++++++++++++++++++
 _ml-commons-plugin/cluster-settings.md        |  8 ++
 2 files changed, 88 insertions(+)

diff --git a/_ml-commons-plugin/api/model-apis/get-model.md b/_ml-commons-plugin/api/model-apis/get-model.md
index 454aff27..73513721 100644
--- a/_ml-commons-plugin/api/model-apis/get-model.md
+++ b/_ml-commons-plugin/api/model-apis/get-model.md
@@ -104,6 +104,86 @@ POST /_plugins/_ml/models/_search
 ```
 {% include copy-curl.html %}
 
+#### Example: Excluding model chunks
+
+```json
+GET /_plugins/_ml/models/_search
+{
+  "query": {
+    "bool": {
+      "must_not": {
+        "exists": {
+          "field": "chunk_number"
+        }
+      }
+    }
+  },
+  "sort": [
+    {
+      "created_time": {
+        "order": "desc"
+      }
+    }
+  ]
+}
+```
+{% include copy-curl.html %}
+
+#### Example: Searching for all model chunks
+
+The following query searches for all chunks of the model with the ID `979y9YwBjWKCe6KgNGTm` and sorts the chunks in ascending order:
+
+```json
+GET /_plugins/_ml/models/_search
+{
+  "query": {
+    "bool": {
+      "filter": [
+        {
+          "term": {
+            "model_id": "9r9w9YwBjWKCe6KgyGST"
+          }
+        }
+      ]
+    }
+  },
+  "sort": [
+    {
+      "chunk_number": {
+        "order": "asc"
+      }
+    }
+  ]
+}
+```
+{% include copy-curl.html %}
+
+#### Example: Searching for a model by description
+
+```json
+GET _plugins/_ml/models/_search
+{
+  "query": {
+    "bool": {
+      "should": [
+        {
+          "match": {
+            "description": "sentence transformer"
+          }
+        }
+      ],
+      "must_not": {
+        "exists": {
+          "field": "chunk_number"
+        }
+      }
+    }
+  },
+  "size": 1000
+}
+```
+{% include copy-curl.html %}
+
 #### Example response
 
 ```json
diff --git a/_ml-commons-plugin/cluster-settings.md b/_ml-commons-plugin/cluster-settings.md
index cae56eea..5bf1c135 100644
--- a/_ml-commons-plugin/cluster-settings.md
+++ b/_ml-commons-plugin/cluster-settings.md
@@ -20,10 +20,16 @@ By default, ML tasks and models only run on ML nodes. When configured without th
 node.roles: [ ml ]
 ```
 
+### Setting up a cluster with a dedicated ML node
+
+To set up a cluster with a dedicated ML node, see the sample [Docker compose file](https://github.com/opensearch-project/ml-commons/blob/main/docs/docker/docker-compose.yml).
+
 ## Run tasks and models on ML nodes only
 
 If `true`, ML Commons tasks and models run ML tasks on ML nodes only. If `false`, tasks and models run on ML nodes first. If no ML nodes exist, tasks and models run on data nodes. 
 
+We suggest running ML workloads on a dedicated ML node rather than on data nodes. Starting with OpenSearch 2.5, ML tasks run on ML nodes only by default. To test models on a data node, set `plugins.ml_commons.only_run_on_ml_node` to `false`.
+
 We recommend setting `plugins.ml_commons.only_run_on_ml_node` to `true` on production clusters. 
 {: .tip}
 
@@ -220,6 +226,8 @@ Sets a circuit breaker that checks all system memory usage before running an ML
 
 Values are based on the percentage of memory available. When set to `0`, no ML tasks will run. When set to `100`, the circuit breaker closes and no threshold exists.
 
+Starting with OpenSearch 2.5, ML Commons runs a native memory circuit breaker to avoid an out-of-memory error when loading too many models. By default, the native memory threshold is 90%. If memory usage exceeds the threshold, ML Commons returns an error. For testing purposes, you can disable the circuit breaker by setting `plugins.ml_commons.native_memory_threshold` to 100.
+
 ### Setting
 
 ```