-
Notifications
You must be signed in to change notification settings - Fork 18
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
RHOAI-10948 monitoring book restructure (#394)
* RHOAI-10948 monitoring book restructure * RHOAI-10948 monitoring book restructure * peer review * peer review
- Loading branch information
Showing
15 changed files
with
331 additions
and
321 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,28 @@ | ||
:_module-type: ASSEMBLY | ||
|
||
ifdef::context[:parent-context: {context}] | ||
|
||
[id="setting-up-model-monitoring_{context}"] | ||
= Setting up model monitoring | ||
|
||
[role='_abstract'] | ||
|
||
To set up model monitoring for data scientists to use in {productname-short}, a cluster administrator does the following tasks: | ||
|
||
* Configure monitoring for the model serving platform | ||
* Enable the TrustyAI component in the {productname-long} {install-package} | ||
* Install the TrustyAI service on each data science project that contains models that the data scientists want to monitor | ||
|
||
[NOTE] | ||
==== | ||
Model monitoring with TrustyAI is only available on the ModelMesh-based _multi-model serving platform_. Model monitoring with TrustyAI is unavailable on the KServe-based _single-model serving platform_. | ||
==== | ||
|
||
include::modules/configuring-monitoring-for-the-multi-model-serving-platform.adoc[leveloffset=+1] | ||
|
||
include::modules/enabling-trustyai-component.adoc[leveloffset=+1] | ||
|
||
include::modules/installing-trustyai-service.adoc[leveloffset=+1] | ||
|
||
ifdef::parent-context[:context: {parent-context}] | ||
ifndef::parent-context[:!context:] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,51 @@ | ||
:_module-type: PROCEDURE | ||
|
||
[id='enabling-trustyai-component_{context}'] | ||
= Enabling the TrustyAI component | ||
|
||
[role='_abstract'] | ||
To allow your data scientists to use model monitoring, you must enable the TrustyAI component in {productname-short}. | ||
|
||
.Prerequisites | ||
* You have logged in to {openshift-platform} with the `cluster-admin` role. | ||
* You have access to the data science cluster. | ||
* You have installed {productname-long}. | ||
|
||
.Procedure | ||
. In the {openshift-platform} console, click *Operators* -> *Installed Operators*. | ||
ifdef::self-managed,cloud-service[] | ||
. Search for the *Red Hat OpenShift AI* Operator, and then click the Operator name to open the Operator details page. | ||
endif::[] | ||
ifdef::upstream[] | ||
. Search for the *Open Data Hub Operator*, and then click the Operator name to open the Operator details page. | ||
endif::[] | ||
. Click the *Data Science Cluster* tab. | ||
. Click the default instance name (for example, *default-dsc*) to open the instance details page. | ||
. Click the *YAML* tab to show the instance specifications. | ||
. In the `spec:components` section, set the `managementState` field for the `trustyai` component to `Managed`: | ||
+ | ||
---- | ||
trustyai: | ||
managementState: Managed | ||
---- | ||
|
||
. Click *Save*. | ||
|
||
.Verification | ||
Check the status of the *trustyai-service-operator* pod as follows: | ||
|
||
ifdef::self-managed,cloud-service[] | ||
. In the {openshift-platform} console, from the *Project* list, select *redhat-ods-applications*. | ||
endif::[] | ||
ifdef::upstream[] | ||
. In the {openshift-platform} console, from the *Project* list, select *opendatahub*. | ||
endif::[] | ||
|
||
. Click *Workloads* -> *Deployments*. | ||
. Search for the *trustyai-service-operator-contoller-manager* deployment. | ||
Check the status as follows: | ||
.. Click the deployment name to open the deployment details page. | ||
.. Click the *Pods* tab. | ||
.. Check the pod status. | ||
+ | ||
When the status of the *trustyai-service-operator-controller-manager-_<pod-id>_* pod is *Running*, the pod is ready to use. |
This file was deleted.
Oops, something went wrong.
Oops, something went wrong.