RHOAI-10948 monitoring book restructure (#394)

* RHOAI-10948 monitoring book restructure

* RHOAI-10948 monitoring book restructure

* peer review

* peer review

assemblies/configuring-bias-metrics-for-a-model.adoc → assemblies/monitoring-model-bias.adoc

@@ -7,8 +7,8 @@ ifdef::context[:parent-context: {context}]
 
 :context: bias-monitoring
 
-[id="configuring-bias-metrics-for-a-model_{context}"]
-= Configuring bias metrics for a model
+[id="monitoring-model-bias_{context}"]
+= Monitoring model bias
 :upstream:
 //:preview:
 
@@ -20,13 +20,15 @@ As a data scientist, you might want to monitor your machine learning models for
 
 {productname-long} provides a set of metrics that help you to monitor your models for bias. You can use the {productname-short} interface to choose an available metric and then configure model-specific details such as a protected attribute, the privileged and unprivileged groups, the outcome you want to monitor, and a threshold for bias. You then see a chart of the calculated values for a specified number of model inferences.
 
-The sections that follow describe how to configure your models for bias monitoring.
-
 include::modules/creating-a-bias-metric.adoc[leveloffset=+1]
 
-include::modules/duplicating-a-bias-metric.adoc[leveloffset=+1]
+include::modules/duplicating-a-bias-metric.adoc[leveloffset=+2]
 
 include::modules/deleting-a-bias-metric.adoc[leveloffset=+1]
 
+include::modules/viewing-bias-metrics.adoc[leveloffset=+1]
+
+include::modules/supported-bias-metrics.adoc[leveloffset=+1]
+
 ifdef::parent-context[:context: {parent-context}]
 ifndef::parent-context[:!context:]

assemblies/setting-up-model-monitoring.adoc

@@ -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:]

modules/authenticating-trustyai-service.adoc

@@ -13,27 +13,17 @@ endif::[]
 ifdef::cloud-service[]
 * You installed the OpenShift command line interface (`oc`) as described in link:https://docs.openshift.com/dedicated/cli_reference/openshift_cli/getting-started-cli.html[Getting started with the CLI] (OpenShift Dedicated) or link:https://docs.openshift.com/rosa/cli_reference/openshift_cli/getting-started-cli.html[Getting started with the CLI] (Red Hat OpenShift Service on AWS)
 endif::[]
-* Your OpenShift cluster administrator has installed {productname-short}, added you as a user to the OpenShift cluster, and enabled the TrustyAI service for the data science project where the models are deployed.
+* Your OpenShift cluster administrator has installed {productname-short}, added you as a user to the OpenShift cluster, and installed the TrustyAI service for the data science project where the models are deployed.
 
 .Procedure
 
-ifdef::upstream,self-managed[]
 . In a terminal window, log in to {openshift-platform} where {productname-short} is deployed.
-endif::[]
-ifdef::cloud-service[]
-. In a terminal window, log in to OpenShift where {productname-short} is deployed.
-endif::[]
 +
 ----
 oc login
 ----
 
-ifdef::upstream,self-managed[]
-. Enter the following command to get the user token on {openshift-platform}.
-endif::[]
-ifdef::cloud-service[]
-. Enter the following command to get the user token on OpenShift.
-endif::[]
+. Enter the following command to set a user token variable on {openshift-platform}:
 +
 ----
 TOKEN=$(oc whoami -t)

modules/creating-a-bias-metric-using-cli.adoc

@@ -19,17 +19,15 @@ endif::[]
 
 * You are familiar with the specific data set schema and understand the names and meanings of the inputs and outputs.
 
-* Your OpenShift cluster administrator has installed {productname-short} and enabled the TrustyAI service for the data science project where the models are deployed.
+* Your OpenShift cluster administrator has configured monitoring for the model serving platform, enabled the TrustyAI component in the {productname-long} {install-package}, and installed the TrustyAI service for the data science project where the models are deployed.
 
 * You installed the OpenShift command line interface (`oc`) as described in link:https://docs.openshift.com/container-platform/{ocp-latest-version}/cli_reference/openshift_cli/getting-started-cli.html[Get Started with the CLI].
 
 ifndef::upstream[]
 * You have a user token for authentication as described in link:{rhoaidocshome}{default-format-url}/monitoring_data_science_models/authenticating-trustyai-service_monitor[Authenticating the TrustyAI service].
-* You have sent training data to your models as described in link:{rhoaidocshome}{default-format-url}/monitoring_data_science_models/sending-training-data-to-a-model_monitor[Sending training data to a model].
 endif::[]
 ifdef::upstream[]
 * You have a user token for authentication as described in link:{odhdocshome}/monitoring-data-science-models/#authenticating-trustyai-service_monitor[Authenticating the TrustyAI service].
-* You have sent training data to your models as described in link:{odhdocshome}/monitoring-data-science-models/#sending-training-data-to-a-model_monitor[Sending training data to a model].
 endif::[]
 
 .Procedure

modules/creating-a-bias-metric-using-dashboard.adoc

@@ -16,19 +16,17 @@ endif::[]
 
 * You are familiar with the specific data set schema and understand the names and meanings of the inputs and outputs.
 
-* Your OpenShift cluster administrator has installed {productname-short} and enabled the TrustyAI service for the data science project where the models are deployed.
-
-* You have logged in to {productname-long}.
+* Your OpenShift cluster administrator has configured monitoring for the model serving platform, enabled the TrustyAI component in the {productname-long} {install-package}, and installed the TrustyAI service for the data science project where the models are deployed.
 
 ifndef::upstream[]
 * You have a user token for authentication as described in link:{rhoaidocshome}{default-format-url}/monitoring_data_science_models/authenticating-trustyai-service_monitor[Authenticating the TrustyAI service].
-* You have sent training data to your models as described in link:{rhoaidocshome}{default-format-url}/monitoring_data_science_models/sending-training-data-to-a-model_monitor[Sending training data to a model].
 endif::[]
 ifdef::upstream[]
 * You have a user token for authentication as described in link:{odhdocshome}/monitoring-data-science-models/#authenticating-trustyai-service_monitor[Authenticating the TrustyAI service].
-* You have sent training data to your models as described in link:{odhdocshome}/monitoring-data-science-models/#sending-training-data-to-a-model_monitor[Sending training data to a model].
 endif::[]
 
+* You have logged in to {productname-long}.
+
 .Procedure
 . Optional: To set the `TRUSTY_ROUTE` variable, follow these steps. 
 .. In a terminal window, log in to the OpenShift cluster where {productname-short} is deployed.

modules/enabling-trustyai-component.adoc

@@ -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.