From a3be34b1c80416dd384157fdb0307e6abda6af81 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <naarcha@amazon.com>
Date: Tue, 18 Apr 2023 09:28:20 -0500
Subject: [PATCH 01/16] Add ML fault tolerance

Signed-off-by: Naarcha-AWS <naarcha@amazon.com>
---
 _ml-commons-plugin/api.md              | 37 ++++++++++++++++++++++++++
 _ml-commons-plugin/cluster-settings.md | 32 ++++++++++++++++++++++
 2 files changed, 69 insertions(+)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index 0b11a63fbe..4b8799a004 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -494,6 +494,43 @@ GET /_plugins/_ml/profile
 }
 ```
 
+### Example: Return auto deploy and node information
+
+The profile API returns additional information when the [auto redeploy]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api#enable-auto-redeploy) cluster setting is set to `true`.
+
+```json
+{
+  "name": "all-mpnet-base-v2",
+  "algorithm": "TEXT_EMBEDDING",
+  "model_version": "1",
+  "model_format": "TORCH_SCRIPT",
+  "model_state": "DEPLOYED",
+  "model_content_size_in_bytes": 404999545,
+  "model_content_hash_value": "fe72818b76a91e154776e4737b1fb0db255c091e8123117ad8758d9f7be6e594",
+  "model_config": {
+    "model_type": "bert",
+    "embedding_dimension": 768,
+    "framework_type": "SENTENCE_TRANSFORMERS"
+  },
+  "created_time": 1681642820665,
+  "last_updated_time": 1681646576370,
+  "last_registered_time": 1681642837416,
+  "last_deployed_time": 1681646576370,
+  "auto_redeploy_retry_times": 0,
+  "total_chunks": 41,
+  "planning_worker_node_count": 6,
+  "current_worker_node_count": 6,
+  "planning_worker_nodes": [
+    "Liz28BgFTo--u0ZXVtmOaQ",
+    "jPPe_s9vQq-cKgZrn6hN-w",
+    "gN8IFfxdT4mnPdc6WW9ung",
+    "lCUgCEiASWKfRNTYoKo9Ng",
+    "ZCBneXv6SG2VdHQvLAnEUg",
+    "F483VPEbQlaQoEW_F2H-gQ"
+  ]
+}
+```
+
 
 ## Predict
 
diff --git a/_ml-commons-plugin/cluster-settings.md b/_ml-commons-plugin/cluster-settings.md
index 660c9e5c18..edde914145 100644
--- a/_ml-commons-plugin/cluster-settings.md
+++ b/_ml-commons-plugin/cluster-settings.md
@@ -186,3 +186,35 @@ plugins.ml_commons.native_memory_threshold: 90
 
 - Default value: 90
 - Value range: [0, 100]
+
+## Enable auto redeploy
+
+Automatically redeploys previously deployed models upon cluster failure. 
+
+### Setting
+
+```
+plugins.ml_commons.model_auto_redeploy.enable: false
+```
+
+### Values
+
+- Default value: false
+- Value range: [false, true]
+
+## Set retires for auto redeploy
+
+Sets the limit for the number of times a previously deployed model will try and redeploy upon cluster failure.
+
+### Setting
+
+```
+plugins.ml_commons.model_auto_redeploy.lifetime_retry_times: 3
+```
+
+### Values
+
+- Default value: 3
+- Value range: [0, 100]
+
+

From 73e41e360fb44e970a4c99cc3ed5d732789987f1 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <naarcha@amazon.com>
Date: Tue, 18 Apr 2023 09:45:37 -0500
Subject: [PATCH 02/16] Rework Profile API sentence

Signed-off-by: Naarcha-AWS <naarcha@amazon.com>
---
 _ml-commons-plugin/api.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index 4b8799a004..96daebe8f5 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -496,7 +496,7 @@ GET /_plugins/_ml/profile
 
 ### Example: Return auto deploy and node information
 
-The profile API returns additional information when the [auto redeploy]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api#enable-auto-redeploy) cluster setting is set to `true`.
+When the [auto redeploy]({{site.url}}{{site.baseurl}}/ml-commons-plugin/cluster-setting#enable-auto-redeploy) cluster setting is set to `true`, the profile API returns additional deployment information, including deployment time, retry count, and worker node IDs where the model is deployed.
 
 ```json
 {

From c09c4a68fea131d8dd23e7285abf90ad5857ccf0 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <naarcha@amazon.com>
Date: Tue, 18 Apr 2023 10:03:09 -0500
Subject: [PATCH 03/16] Fix link

Signed-off-by: Naarcha-AWS <naarcha@amazon.com>
---
 _ml-commons-plugin/api.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index 96daebe8f5..6d16d808cf 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -496,7 +496,7 @@ GET /_plugins/_ml/profile
 
 ### Example: Return auto deploy and node information
 
-When the [auto redeploy]({{site.url}}{{site.baseurl}}/ml-commons-plugin/cluster-setting#enable-auto-redeploy) cluster setting is set to `true`, the profile API returns additional deployment information, including deployment time, retry count, and worker node IDs where the model is deployed.
+When the [auto redeploy]({{site.url}}{{site.baseurl}}/ml-commons-plugin/cluster-settings#enable-auto-redeploy) cluster setting is set to `true`, the profile API returns additional deployment information, including deployment time, retry count, and worker node IDs where the model is deployed.
 
 ```json
 {

From 82ac08edbb15f1b5343f0cdd32ee8deb71f07c78 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <naarcha@amazon.com>
Date: Tue, 18 Apr 2023 11:59:18 -0500
Subject: [PATCH 04/16] Add review feedback

Signed-off-by: Naarcha-AWS <naarcha@amazon.com>
---
 _ml-commons-plugin/cluster-settings.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_ml-commons-plugin/cluster-settings.md b/_ml-commons-plugin/cluster-settings.md
index edde914145..e4ea19d0ba 100644
--- a/_ml-commons-plugin/cluster-settings.md
+++ b/_ml-commons-plugin/cluster-settings.md
@@ -189,7 +189,7 @@ plugins.ml_commons.native_memory_threshold: 90
 
 ## Enable auto redeploy
 
-Automatically redeploys previously deployed models upon cluster failure. 
+Automatically redeploys deployed or partially deployed models upon cluster failure. If all ML nodes inside inside a cluster crash, auto model redeployment fails, and the model must be deployed manually.
 
 ### Setting
 

From f254342f6caadb0e4c5590bc0106b8aa90c1574c Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <naarcha@amazon.com>
Date: Tue, 25 Apr 2023 11:09:14 -0500
Subject: [PATCH 05/16] Add technical feedback for ML. Change API names

Signed-off-by: Naarcha-AWS <naarcha@amazon.com>
---
 _ml-commons-plugin/api.md              | 70 +++++++++++++-------------
 _ml-commons-plugin/cluster-settings.md | 20 ++++++--
 2 files changed, 52 insertions(+), 38 deletions(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index 6d16d808cf..bef374e680 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -115,12 +115,12 @@ The API returns information on the model, the algorithm used, and the content fo
 }
 ```
 
-## Upload a model
+## Register a model
 
-Use the upload operation to upload a custom model to a model index. ML Commons splits the model into smaller chunks and saves those chunks in the model's index.
+Use the Register operation to register a custom model to a model index. ML Commons splits the model into smaller chunks and saves those chunks in the model's index.
 
 ```json
-POST /_plugins/_ml/models/_upload
+POST /_plugins/_ml/models/_register
 ```
 
 ### Request fields
@@ -137,10 +137,10 @@ Field | Data type | Description
 
 ### Example
 
-The following example request uploads version `1.0.0` of an NLP sentence transformation model named `all-MiniLM-L6-v2`.
+The following example request registers a version `1.0.0` of an NLP sentence transformation model named `all-MiniLM-L6-v2`.
 
 ```json
-POST /_plugins/_ml/models/_upload
+POST /_plugins/_ml/models/_register
 {
   "name": "all-MiniLM-L6-v2",
   "version": "1.0.0",
@@ -166,14 +166,14 @@ OpenSearch responds with the `task_id` and task `status`.
 }
 ```
 
-To see the status of your model upload, enter the `task_id` into the [task API]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api#get-task-information). Use the `model_id` from the task response once the upload is complete. For example:
+To see the status of your model registation, enter the `task_id` into the [task API]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api#get-task-information). Use the `model_id` from the task response once the registration is complete. For example:
 
 ```json
 {
   "model_id" : "WWQI44MBbzI2oUKAvNUt", 
   "task_type" : "UPLOAD_MODEL",
   "function_name" : "TEXT_EMBEDDING",
-  "state" : "COMPLETED",
+  "state" : "REGISTERED",
   "worker_node" : "KzONM8c8T4Od-NoUANQNGg",
   "create_time" : 1665961344003,
   "last_update_time" : 1665961373047,
@@ -181,28 +181,28 @@ To see the status of your model upload, enter the `task_id` into the [task API](
 }
 ```
 
-## Load model
+## Deploy model
 
-The load model operation reads the model's chunks from the model index, then creates an instance of the model to cache into memory. This operation requires the `model_id`.
+The deploy model operation reads the model's chunks from the model index, then creates an instance of the model to cache into memory. This operation requires the `model_id`.
 
 ```json
-POST /_plugins/_ml/models/<model_id>/_load
+POST /_plugins/_ml/models/<model_id>/_deploy
 ```
 
-### Example: Load into all available ML nodes
+### Example: Deploy into all available ML nodes
 
-In this example request, OpenSearch loads the model into any available OpenSearch ML node:
+In this example request, OpenSearch deploys the model into any available OpenSearch ML node:
 
 ```json
-POST /_plugins/_ml/models/WWQI44MBbzI2oUKAvNUt/_load
+POST /_plugins/_ml/models/WWQI44MBbzI2oUKAvNUt/_deploy
 ```
 
-### Example: Load into a specific node
+### Example: Deploy into a specific node
 
-If you want to reserve the memory of other ML nodes within your cluster, you can load your model into a specific node(s) by specifying the `node_ids` in the request body:
+If you want to reserve the memory of other ML nodes within your cluster, you can deploy your model into a specific node(s) by specifying the `node_ids` in the request body:
 
 ```json
-POST /_plugins/_ml/models/WWQI44MBbzI2oUKAvNUt/_load
+POST /_plugins/_ml/models/WWQI44MBbzI2oUKAvNUt/_deploy
 {
     "node_ids": ["4PLK7KJWReyX0oWKnBA8nA"]
 }
@@ -213,40 +213,40 @@ POST /_plugins/_ml/models/WWQI44MBbzI2oUKAvNUt/_load
 ```json
 {
   "task_id" : "hA8P44MBhyWuIwnfvTKP",
-  "status" : "CREATED"
+  "status" : "DEPLOYING"
 }
 ```
 
-## Unload a model
+## Undeploy a model
 
-To unload a model from memory, use the unload operation.
+To undeploy a model from memory, use the undeploy operation.
 
 ```json
-POST /_plugins/_ml/models/<model_id>/_unload
+POST /_plugins/_ml/models/<model_id>/_undeploy
 ```
 
-### Example: Unload model from all ML nodes
+### Example: Undeploy model from all ML nodes
 
 ```json
-POST /_plugins/_ml/models/MGqJhYMBbbh0ushjm8p_/_unload
+POST /_plugins/_ml/models/MGqJhYMBbbh0ushjm8p_/_undeploy
 ```
 
-### Response: Unload model from all ML nodes
+### Response: Undeploy model from all ML nodes
 
 ```json
 {
     "s5JwjZRqTY6nOT0EvFwVdA": {
         "stats": {
-            "MGqJhYMBbbh0ushjm8p_": "unloaded"
+            "MGqJhYMBbbh0ushjm8p_": "UNDEPLOYED"
         }
     }
 }
 ```
 
-### Example: Unload specific models from specific nodes
+### Example: Undeploy specific models from specific nodes
 
 ```json
-POST /_plugins/_ml/models/_unload
+POST /_plugins/_ml/models/_undeploy
 {
   "node_ids": ["sv7-3CbwQW-4PiIsDOfLxQ"],
   "model_ids": ["KDo2ZYQB-v9VEDwdjkZ4"]
@@ -254,32 +254,32 @@ POST /_plugins/_ml/models/_unload
 ```
 
 
-### Response:  Unload specific models from specific nodes
+### Response: Undeploy specific models from specific nodes
 
 ```json
 {
   "sv7-3CbwQW-4PiIsDOfLxQ" : {
     "stats" : {
-      "KDo2ZYQB-v9VEDwdjkZ4" : "unloaded"
+      "KDo2ZYQB-v9VEDwdjkZ4" : "UNDEPLOYED"
     }
   }
 }
 ```
 
-### Response: Unload all models from specific nodes
+### Response: undeploy all models from specific nodes
 
 ```json
 {
   "sv7-3CbwQW-4PiIsDOfLxQ" : {
     "stats" : {
-      "KDo2ZYQB-v9VEDwdjkZ4" : "unloaded",
-      "-8o8ZYQBvrLMaN0vtwzN" : "unloaded"
+      "KDo2ZYQB-v9VEDwdjkZ4" : "UNDEPLOYED",
+      "-8o8ZYQBvrLMaN0vtwzN" : "UNDEPLOYED"
     }
   }
 }
 ```
 
-### Example: Unload specific models from all nodes
+### Example: undeploy specific models from all nodes
 
 ```json
 {
@@ -287,13 +287,13 @@ POST /_plugins/_ml/models/_unload
 }
 ```
 
-### Response: Unload specific models from all nodes
+### Response: undeploy specific models from all nodes
 
 ```json
 {
   "sv7-3CbwQW-4PiIsDOfLxQ" : {
     "stats" : {
-      "KDo2ZYQB-v9VEDwdjkZ4" : "unloaded"
+      "KDo2ZYQB-v9VEDwdjkZ4" : "UNDEPLOYED"
     }
   }
 }
@@ -473,7 +473,7 @@ GET /_plugins/_ml/profile
     "KzONM8c8T4Od-NoUANQNGg" : { # node id
       "models" : {
         "WWQI44MBbzI2oUKAvNUt" : { # model id
-          "model_state" : "LOADED", # model status
+          "model_state" : "DEPLOYED", # model status
           "predictor" : "org.opensearch.ml.engine.algorithms.text_embedding.TextEmbeddingModel@592814c9",
           "worker_nodes" : [ # routing table
             "KzONM8c8T4Od-NoUANQNGg"
diff --git a/_ml-commons-plugin/cluster-settings.md b/_ml-commons-plugin/cluster-settings.md
index e4ea19d0ba..209adbdccc 100644
--- a/_ml-commons-plugin/cluster-settings.md
+++ b/_ml-commons-plugin/cluster-settings.md
@@ -187,9 +187,24 @@ plugins.ml_commons.native_memory_threshold: 90
 - Default value: 90
 - Value range: [0, 100]
 
+## Allow custom deployment plans
+
+When enabled, grants users the ability to deploy models to specific ML nodes according to that user's permissions.
+
+### Setting
+
+```
+plugins.ml_commons.allow_custom_deployment_plan: false
+```
+
+### Values
+
+- Default value: false
+- Value range: [false, true]
+
 ## Enable auto redeploy
 
-Automatically redeploys deployed or partially deployed models upon cluster failure. If all ML nodes inside inside a cluster crash, auto model redeployment fails, and the model must be deployed manually.
+Automatically redeploys deployed or partially deployed models upon cluster failure. If all ML nodes inside a cluster crash, the model switches to the `DEPLOYED_FAILED` state, and the model must be deployed manually.
 
 ### Setting
 
@@ -204,7 +219,7 @@ plugins.ml_commons.model_auto_redeploy.enable: false
 
 ## Set retires for auto redeploy
 
-Sets the limit for the number of times a previously deployed model will try and redeploy upon cluster failure.
+Sets the limit for the number of times a deployed or partially deployed model will try and redeploy upon cluster failure.
 
 ### Setting
 
@@ -217,4 +232,3 @@ plugins.ml_commons.model_auto_redeploy.lifetime_retry_times: 3
 - Default value: 3
 - Value range: [0, 100]
 
-

From c51962d73683a87d94c12278a4a65f2c4892a978 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <naarcha@amazon.com>
Date: Tue, 25 Apr 2023 12:11:44 -0500
Subject: [PATCH 06/16] Add final ML node setting

Signed-off-by: Naarcha-AWS <naarcha@amazon.com>
---
 _ml-commons-plugin/cluster-settings.md | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/_ml-commons-plugin/cluster-settings.md b/_ml-commons-plugin/cluster-settings.md
index 209adbdccc..4c9aa10217 100644
--- a/_ml-commons-plugin/cluster-settings.md
+++ b/_ml-commons-plugin/cluster-settings.md
@@ -59,7 +59,7 @@ plugins.ml_commons.max_ml_task_per_node: 10
 
 ## Set number of ML models per node
 
-Sets the number of ML models that can be loaded on to each ML node. When set to `0`, no ML models can load on any node.
+Sets the number of ML models that can be deployed on to each ML node. When set to `0`, no ML models can deploy on any node.
 
 ### Setting
 
@@ -74,7 +74,7 @@ plugins.ml_commons.max_model_on_node: 10
 
 ## Set sync job intervals 
 
-When returning runtime information with the [profile API]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api#profile), ML Commons will run a regular job to sync newly loaded or unloaded models on each node. When set to `0`, ML Commons immediately stops sync up jobs.
+When returning runtime information with the [profile API]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api#profile), ML Commons will run a regular job to sync newly deployed or undeployed models on each node. When set to `0`, ML Commons immediately stops sync up jobs.
 
 
 ### Setting
@@ -232,3 +232,17 @@ plugins.ml_commons.model_auto_redeploy.lifetime_retry_times: 3
 - Default value: 3
 - Value range: [0, 100]
 
+## Set auto redeploy success ratio
+
+Sets the ratio of success for the auto redeployment of a model based on the available ML nodes in the cluster. For example, if ML nodes crash inside a cluster, the auto redeploy protocol adds another node or retires a crashed node. If our ratio is `0.7` and 70% of all ML nodes successfully redeploy the model on auto redeploy activation, the redeployment is a success. If the model redeploys on less the 70% of available ML nodes, the auto redeploy retries until the redeployment succeeds or OpenSearch reaches [the maximum number of retries](#set-retires-for-auto-redeploy).
+
+### Setting
+
+```
+plugins.ml_commons.model_auto_redeploy_success_ratio: 0.8
+```
+
+### Values
+
+- Default value: 0.8
+- Value range: [0, 1]
\ No newline at end of file

From 7f58d1e306702fb91ed59da5c4b263a8c98a8e03 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <naarcha@amazon.com>
Date: Tue, 25 Apr 2023 12:43:35 -0500
Subject: [PATCH 07/16] Add more technical feedback

Signed-off-by: Naarcha-AWS <naarcha@amazon.com>
---
 _ml-commons-plugin/api.md | 45 ++++-----------------------------------
 1 file changed, 4 insertions(+), 41 deletions(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index bef374e680..85468e7714 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -266,7 +266,7 @@ POST /_plugins/_ml/models/_undeploy
 }
 ```
 
-### Response: undeploy all models from specific nodes
+### Response: Undeploy all models from specific nodes
 
 ```json
 {
@@ -279,7 +279,7 @@ POST /_plugins/_ml/models/_undeploy
 }
 ```
 
-### Example: undeploy specific models from all nodes
+### Example: Undeploy specific models from all nodes
 
 ```json
 {
@@ -287,7 +287,7 @@ POST /_plugins/_ml/models/_undeploy
 }
 ```
 
-### Response: undeploy specific models from all nodes
+### Response: Undeploy specific models from all nodes
 
 ```json
 {
@@ -390,7 +390,7 @@ POST /_plugins/_ml/models/_search
 
 ## Delete model
 
-Deletes a model based on the model_id
+Deletes a model based on the `model_id`.
 
 ```json
 DELETE /_plugins/_ml/models/<model_id>
@@ -494,43 +494,6 @@ GET /_plugins/_ml/profile
 }
 ```
 
-### Example: Return auto deploy and node information
-
-When the [auto redeploy]({{site.url}}{{site.baseurl}}/ml-commons-plugin/cluster-settings#enable-auto-redeploy) cluster setting is set to `true`, the profile API returns additional deployment information, including deployment time, retry count, and worker node IDs where the model is deployed.
-
-```json
-{
-  "name": "all-mpnet-base-v2",
-  "algorithm": "TEXT_EMBEDDING",
-  "model_version": "1",
-  "model_format": "TORCH_SCRIPT",
-  "model_state": "DEPLOYED",
-  "model_content_size_in_bytes": 404999545,
-  "model_content_hash_value": "fe72818b76a91e154776e4737b1fb0db255c091e8123117ad8758d9f7be6e594",
-  "model_config": {
-    "model_type": "bert",
-    "embedding_dimension": 768,
-    "framework_type": "SENTENCE_TRANSFORMERS"
-  },
-  "created_time": 1681642820665,
-  "last_updated_time": 1681646576370,
-  "last_registered_time": 1681642837416,
-  "last_deployed_time": 1681646576370,
-  "auto_redeploy_retry_times": 0,
-  "total_chunks": 41,
-  "planning_worker_node_count": 6,
-  "current_worker_node_count": 6,
-  "planning_worker_nodes": [
-    "Liz28BgFTo--u0ZXVtmOaQ",
-    "jPPe_s9vQq-cKgZrn6hN-w",
-    "gN8IFfxdT4mnPdc6WW9ung",
-    "lCUgCEiASWKfRNTYoKo9Ng",
-    "ZCBneXv6SG2VdHQvLAnEUg",
-    "F483VPEbQlaQoEW_F2H-gQ"
-  ]
-}
-```
-
 
 ## Predict
 

From d40ad63b74e0914b7395ffab2ffe7a65359b7281 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
Date: Wed, 26 Apr 2023 09:26:53 -0500
Subject: [PATCH 08/16] Apply suggestions from code review

Co-authored-by: Chris Moore <107723039+cwillum@users.noreply.github.com>
Signed-off-by: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
---
 _ml-commons-plugin/api.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index 85468e7714..3936f3cc82 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -166,7 +166,7 @@ OpenSearch responds with the `task_id` and task `status`.
 }
 ```
 
-To see the status of your model registation, enter the `task_id` into the [task API]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api#get-task-information). Use the `model_id` from the task response once the registration is complete. For example:
+To see the status of your model registation, enter the `task_id` in the [task API] ...
 
 ```json
 {

From 90e8bb5bf5637f4d0f09d088d2d354364fcfafa4 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
Date: Wed, 26 Apr 2023 09:28:17 -0500
Subject: [PATCH 09/16] Update cluster-settings.md

Signed-off-by: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
---
 _ml-commons-plugin/cluster-settings.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/_ml-commons-plugin/cluster-settings.md b/_ml-commons-plugin/cluster-settings.md
index 4c9aa10217..d2431607f6 100644
--- a/_ml-commons-plugin/cluster-settings.md
+++ b/_ml-commons-plugin/cluster-settings.md
@@ -219,7 +219,7 @@ plugins.ml_commons.model_auto_redeploy.enable: false
 
 ## Set retires for auto redeploy
 
-Sets the limit for the number of times a deployed or partially deployed model will try and redeploy upon cluster failure.
+Sets the limit for the number of times a deployed or partially deployed model will try and redeploy when ML nodes in a cluster fail or new ML nodes join the cluster.
 
 ### Setting
 
@@ -245,4 +245,4 @@ plugins.ml_commons.model_auto_redeploy_success_ratio: 0.8
 ### Values
 
 - Default value: 0.8
-- Value range: [0, 1]
\ No newline at end of file
+- Value range: [0, 1]

From ced1a8e399abc9d88eee7300a9946ca9fbf05d83 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
Date: Wed, 26 Apr 2023 11:38:10 -0500
Subject: [PATCH 10/16] Update _ml-commons-plugin/api.md

Co-authored-by: Nathan Bower <nbower@amazon.com>
Signed-off-by: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
---
 _ml-commons-plugin/api.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index 3936f3cc82..855888ec0e 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -166,7 +166,7 @@ OpenSearch responds with the `task_id` and task `status`.
 }
 ```
 
-To see the status of your model registation, enter the `task_id` in the [task API] ...
+To see the status of your model registration, enter the `task_id` in the [task API] ...
 
 ```json
 {

From 75136073913c3e7e10ab018da74e1020d1f7b171 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
Date: Wed, 26 Apr 2023 11:40:07 -0500
Subject: [PATCH 11/16] Update _ml-commons-plugin/api.md

Signed-off-by: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
---
 _ml-commons-plugin/api.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index 855888ec0e..6a320f295d 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -217,7 +217,7 @@ POST /_plugins/_ml/models/WWQI44MBbzI2oUKAvNUt/_deploy
 }
 ```
 
-## Undeploy a model
+## Undeploying a model
 
 To undeploy a model from memory, use the undeploy operation.
 

From ed8e832a9be309af718bb3513c8c21cfd892aa40 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
Date: Wed, 26 Apr 2023 11:44:19 -0500
Subject: [PATCH 12/16] Apply suggestions from code review

Co-authored-by: Nathan Bower <nbower@amazon.com>
Signed-off-by: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
---
 _ml-commons-plugin/api.md              | 16 ++++++++--------
 _ml-commons-plugin/cluster-settings.md | 12 ++++++------
 2 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index 6a320f295d..c0a8a16c57 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -183,23 +183,23 @@ To see the status of your model registration, enter the `task_id` in the [task A
 
 ## Deploy model
 
-The deploy model operation reads the model's chunks from the model index, then creates an instance of the model to cache into memory. This operation requires the `model_id`.
+The deploy model operation reads the model's chunks from the model index and then creates an instance of the model to cache into memory. This operation requires the `model_id`.
 
 ```json
 POST /_plugins/_ml/models/<model_id>/_deploy
 ```
 
-### Example: Deploy into all available ML nodes
+### Example: Deploy to all available ML nodes
 
-In this example request, OpenSearch deploys the model into any available OpenSearch ML node:
+In this example request, OpenSearch deploys the model to any available OpenSearch ML node:
 
 ```json
 POST /_plugins/_ml/models/WWQI44MBbzI2oUKAvNUt/_deploy
 ```
 
-### Example: Deploy into a specific node
+### Example: Deploy to a specific node
 
-If you want to reserve the memory of other ML nodes within your cluster, you can deploy your model into a specific node(s) by specifying the `node_ids` in the request body:
+If you want to reserve the memory of other ML nodes within your cluster, you can deploy your model to a specific node(s) by specifying the `node_ids` in the request body:
 
 ```json
 POST /_plugins/_ml/models/WWQI44MBbzI2oUKAvNUt/_deploy
@@ -219,13 +219,13 @@ POST /_plugins/_ml/models/WWQI44MBbzI2oUKAvNUt/_deploy
 
 ## Undeploying a model
 
-To undeploy a model from memory, use the undeploy operation.
+To undeploy a model from memory, use the undeploy operation:
 
 ```json
 POST /_plugins/_ml/models/<model_id>/_undeploy
 ```
 
-### Example: Undeploy model from all ML nodes
+### Example: Undeploying model from all ML nodes
 
 ```json
 POST /_plugins/_ml/models/MGqJhYMBbbh0ushjm8p_/_undeploy
@@ -254,7 +254,7 @@ POST /_plugins/_ml/models/_undeploy
 ```
 
 
-### Response: Undeploy specific models from specific nodes
+### Response: Undeploying specific models from specific nodes
 
 ```json
 {
diff --git a/_ml-commons-plugin/cluster-settings.md b/_ml-commons-plugin/cluster-settings.md
index d2431607f6..31f0abc559 100644
--- a/_ml-commons-plugin/cluster-settings.md
+++ b/_ml-commons-plugin/cluster-settings.md
@@ -59,7 +59,7 @@ plugins.ml_commons.max_ml_task_per_node: 10
 
 ## Set number of ML models per node
 
-Sets the number of ML models that can be deployed on to each ML node. When set to `0`, no ML models can deploy on any node.
+Sets the number of ML models that can be deployed to each ML node. When set to `0`, no ML models can deploy on any node.
 
 ### Setting
 
@@ -74,7 +74,7 @@ plugins.ml_commons.max_model_on_node: 10
 
 ## Set sync job intervals 
 
-When returning runtime information with the [profile API]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api#profile), ML Commons will run a regular job to sync newly deployed or undeployed models on each node. When set to `0`, ML Commons immediately stops sync up jobs.
+When returning runtime information with the [Profile API]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api#profile), ML Commons will run a regular job to sync newly deployed or undeployed models on each node. When set to `0`, ML Commons immediately stops sync-up jobs.
 
 
 ### Setting
@@ -189,7 +189,7 @@ plugins.ml_commons.native_memory_threshold: 90
 
 ## Allow custom deployment plans
 
-When enabled, grants users the ability to deploy models to specific ML nodes according to that user's permissions.
+When enabled, this setting grants users the ability to deploy models to specific ML nodes according to that user's permissions.
 
 ### Setting
 
@@ -204,7 +204,7 @@ plugins.ml_commons.allow_custom_deployment_plan: false
 
 ## Enable auto redeploy
 
-Automatically redeploys deployed or partially deployed models upon cluster failure. If all ML nodes inside a cluster crash, the model switches to the `DEPLOYED_FAILED` state, and the model must be deployed manually.
+This setting automatically redeploys deployed or partially deployed models upon cluster failure. If all ML nodes inside a cluster crash, the model switches to the `DEPLOYED_FAILED` state, and the model must be deployed manually.
 
 ### Setting
 
@@ -219,7 +219,7 @@ plugins.ml_commons.model_auto_redeploy.enable: false
 
 ## Set retires for auto redeploy
 
-Sets the limit for the number of times a deployed or partially deployed model will try and redeploy when ML nodes in a cluster fail or new ML nodes join the cluster.
+This setting sets the limit for the number of times a deployed or partially deployed model will try and redeploy when ML nodes in a cluster fail or new ML nodes join the cluster.
 
 ### Setting
 
@@ -234,7 +234,7 @@ plugins.ml_commons.model_auto_redeploy.lifetime_retry_times: 3
 
 ## Set auto redeploy success ratio
 
-Sets the ratio of success for the auto redeployment of a model based on the available ML nodes in the cluster. For example, if ML nodes crash inside a cluster, the auto redeploy protocol adds another node or retires a crashed node. If our ratio is `0.7` and 70% of all ML nodes successfully redeploy the model on auto redeploy activation, the redeployment is a success. If the model redeploys on less the 70% of available ML nodes, the auto redeploy retries until the redeployment succeeds or OpenSearch reaches [the maximum number of retries](#set-retires-for-auto-redeploy).
+This setting sets the ratio of success for the auto-redeployment of a model based on the available ML nodes in a cluster. For example, if ML nodes crash inside a cluster, the auto redeploy protocol adds another node or retires a crashed node. If the ratio is `0.7` and 70% of all ML nodes successfully redeploy the model on auto-redeploy activation, the redeployment is a success. If the model redeploys on fewer than 70% of available ML nodes, the auto-redeploy retries until the redeployment succeeds or OpenSearch reaches [the maximum number of retries](#set-retires-for-auto-redeploy).
 
 ### Setting
 

From bfa20f7ca0eb756c2dffd2bd215d9c1673b74224 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
Date: Wed, 26 Apr 2023 11:47:39 -0500
Subject: [PATCH 13/16] Update _ml-commons-plugin/api.md

Signed-off-by: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
---
 _ml-commons-plugin/api.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index c0a8a16c57..ccb1ac4369 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -243,7 +243,7 @@ POST /_plugins/_ml/models/MGqJhYMBbbh0ushjm8p_/_undeploy
 }
 ```
 
-### Example: Undeploy specific models from specific nodes
+### Example: Undeploying specific models from specific nodes
 
 ```json
 POST /_plugins/_ml/models/_undeploy

From 26b2efce86a0b85a3afecf7cfb4f71922e99a241 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
Date: Wed, 26 Apr 2023 11:48:39 -0500
Subject: [PATCH 14/16] Update _ml-commons-plugin/api.md

Signed-off-by: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
---
 _ml-commons-plugin/api.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index ccb1ac4369..9dd00a6e71 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -231,7 +231,7 @@ POST /_plugins/_ml/models/<model_id>/_undeploy
 POST /_plugins/_ml/models/MGqJhYMBbbh0ushjm8p_/_undeploy
 ```
 
-### Response: Undeploy model from all ML nodes
+### Response: Undeploying a model from all ML nodes
 
 ```json
 {

From bc7cf6deda51afb1493ff1b36283b35925c24769 Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
Date: Wed, 26 Apr 2023 11:48:59 -0500
Subject: [PATCH 15/16] Update _ml-commons-plugin/api.md

Signed-off-by: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
---
 _ml-commons-plugin/api.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index 9dd00a6e71..f211a76c50 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -279,7 +279,7 @@ POST /_plugins/_ml/models/_undeploy
 }
 ```
 
-### Example: Undeploy specific models from all nodes
+### Example: Undeploying specific models from all nodes
 
 ```json
 {

From 8fec9e03407800a51fa696eea2e90499dc581f6e Mon Sep 17 00:00:00 2001
From: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
Date: Mon, 1 May 2023 08:15:10 -0500
Subject: [PATCH 16/16] Update api.md

Signed-off-by: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
---
 _ml-commons-plugin/api.md | 40 +++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/_ml-commons-plugin/api.md b/_ml-commons-plugin/api.md
index f211a76c50..163c726f36 100644
--- a/_ml-commons-plugin/api.md
+++ b/_ml-commons-plugin/api.md
@@ -24,7 +24,7 @@ In order to train tasks through the API, three inputs are required.
 - Model hyper parameters: Adjust these parameters to make the model train better.  
 - Input data: The data input that trains the ML model, or applies the ML models to predictions. You can input data in two ways, query against your index or use data frame.
 
-## Train model
+## Training a model
 
 Training can occur both synchronously and asynchronously.
 
@@ -96,7 +96,7 @@ For asynchronous responses, the API returns the task_id, which can be used to ge
 }
 ```
 
-## Get model information
+## Getting model information
 
 You can retrieve information on your model using the model_id.
 
@@ -115,9 +115,9 @@ The API returns information on the model, the algorithm used, and the content fo
 }
 ```
 
-## Register a model
+## Registering a model
 
-Use the Register operation to register a custom model to a model index. ML Commons splits the model into smaller chunks and saves those chunks in the model's index.
+Use the register operation to register a custom model to a model index. ML Commons splits the model into smaller chunks and saves those chunks in the model's index.
 
 ```json
 POST /_plugins/_ml/models/_register
@@ -181,7 +181,7 @@ To see the status of your model registration, enter the `task_id` in the [task A
 }
 ```
 
-## Deploy model
+## Deploying a model
 
 The deploy model operation reads the model's chunks from the model index and then creates an instance of the model to cache into memory. This operation requires the `model_id`.
 
@@ -189,7 +189,7 @@ The deploy model operation reads the model's chunks from the model index and the
 POST /_plugins/_ml/models/<model_id>/_deploy
 ```
 
-### Example: Deploy to all available ML nodes
+### Example: Deploying to all available ML nodes
 
 In this example request, OpenSearch deploys the model to any available OpenSearch ML node:
 
@@ -197,7 +197,7 @@ In this example request, OpenSearch deploys the model to any available OpenSearc
 POST /_plugins/_ml/models/WWQI44MBbzI2oUKAvNUt/_deploy
 ```
 
-### Example: Deploy to a specific node
+### Example: Deploying to a specific node
 
 If you want to reserve the memory of other ML nodes within your cluster, you can deploy your model to a specific node(s) by specifying the `node_ids` in the request body:
 
@@ -266,7 +266,7 @@ POST /_plugins/_ml/models/_undeploy
 }
 ```
 
-### Response: Undeploy all models from specific nodes
+### Response: Undeploying all models from specific nodes
 
 ```json
 {
@@ -287,7 +287,7 @@ POST /_plugins/_ml/models/_undeploy
 }
 ```
 
-### Response: Undeploy specific models from all nodes
+### Response: Undeploying specific models from all nodes
 
 ```json
 {
@@ -299,7 +299,7 @@ POST /_plugins/_ml/models/_undeploy
 }
 ```
 
-## Search model
+## Searching for a model
 
 Use this command to search models you've already created.
 
@@ -309,7 +309,7 @@ POST /_plugins/_ml/models/_search
 {query}
 ```
 
-### Example: Query all models
+### Example: Querying all models
 
 ```json
 POST /_plugins/_ml/models/_search
@@ -321,7 +321,7 @@ POST /_plugins/_ml/models/_search
 }
 ```
 
-### Example: Query models with algorithm "FIT_RCF"
+### Example: Querying models with algorithm "FIT_RCF"
 
 ```json
 POST /_plugins/_ml/models/_search
@@ -388,7 +388,7 @@ POST /_plugins/_ml/models/_search
   }
 ```
 
-## Delete model
+## Deleting a model
 
 Deletes a model based on the `model_id`.
 
@@ -414,9 +414,9 @@ The API returns the following:
 }
 ```
 
-## Profile
+## Returning model profile information
 
-Returns runtime information on ML tasks and models. This operation can help debug issues with models at runtime.
+The profile operation returns runtime information on ML tasks and models. The profile operation can help debug issues with models at runtime.
 
 
 ```json
@@ -444,7 +444,7 @@ task_ids | string | Returns runtime data for a specific task. You can string tog
 return_all_tasks | boolean | Determines whether or not a request returns all tasks. When set to `false` task profiles are left out of the response.
 return_all_models | boolean | Determines whether or not a profile request returns all models. When set to `false` model profiles are left out of the response.
 
-### Example: Return all tasks and models on a specific node
+### Example: Returning all tasks and models on a specific node
 
 ```json
 GET /_plugins/_ml/profile
@@ -455,7 +455,7 @@ GET /_plugins/_ml/profile
 }
 ```
 
-### Response: Return all tasks and models on a specific node
+### Response: Returning all tasks and models on a specific node
 
 ```json
 {
@@ -790,7 +790,7 @@ POST /_plugins/_ml/_train_predict/kmeans
 }
 ```
 
-## Get task information
+## Getting task information
 
 You can retrieve information about a task using the task_id.
 
@@ -814,7 +814,7 @@ The response includes information about the task.
 }
 ```
 
-## Search task
+## Searching for a task
 
 Search tasks based on parameters indicated in the request body.
 
@@ -905,7 +905,7 @@ GET /_plugins/_ml/tasks/_search
 }
 ```
 
-## Delete task
+## Deleting a task
 
 Delete a task based on the task_id.