Review Ollama on GKE Learning Path

Author: jasonrandrews

content/learning-paths/servers-and-cloud-computing/multiarch_ollama_on_gke/0-spin_up_gke_cluster.md

@@ -61,31 +61,25 @@ Wait until the cluster shows a green checkmark next to the `ollama-on-multiarch`
 
 Ensure you have `kubectl` and `gcloud` installed. 
 
-You can verify by running each command, for example, enter `gcloud`, and run:
+You can verify each command by printing the version.
+
+Verify `gcloud` by running:
 
 ```bash
-gcloud
-```
-This should return:
-```output
-ERROR: (gcloud) Command name argument expected.
-... 
+gcloud -v
 ```
-Then enter `kubectl` and run it, which should return:
 
-```output
-kubectl controls the Kubernetes cluster manager.
+If `gcloud` is installed the version information is printed. 
 
- Find more information at: https://kubernetes.io/docs/reference/kubectl/
-...
-```
-Otherwise, it might return a message like this:
+Verify `kubectl` by running:
 
-```output
-command not found
+```bash
+kubectl version -o json --client
 ```
 
-If you see this, follow the prerequisite instructions on the first page to install the missing utilities.
+If `kubectl` is installed the version information is printed. 
+
+If you don't see the version information printed refer to the [gcloud](/install-guides/gcloud) and [kubectl](/install-guides/kubectl/) install guides.
 
 Now you can set up your newly-created K8s cluster credentials using the gcloud utility.  
 
@@ -103,7 +97,8 @@ If you get the message:
 ```output
 CRITICAL: ACTION REQUIRED: gke-gcloud-auth-plugin, which is needed for continued use of kubectl, was not found or is not executable. Install gke-gcloud-auth-plugin for use with kubectl by following https://cloud.google.com/kubernetes-engine/docs/how-to/cluster-access-for-kubectl#install_plugin
 ```
-This command will resolve it:
+
+You can resolve the issue by running: 
 
 ```bash
 gcloud components install gke-gcloud-auth-plugin

content/learning-paths/servers-and-cloud-computing/multiarch_ollama_on_gke/3-perf-tests.md

@@ -11,7 +11,7 @@ With your hybrid cluster running Ollama, you can now explore the advantages of r
 
 You may wish to access Ollama without regard to architecture.
 
-To send a request to either based on availability, run:
+To send a request to either architecture, based on availability, run:
 
 ```bash
 ./model_util.sh multiarch hello
@@ -41,7 +41,7 @@ With both architectures responding, you can now load an LLM to compare performan
 The llama3.2 model is used in this demonstration. [Ollama supports multiple different models](https://ollama-operator.ayaka.io/pages/en/guide/supported-models); you can modify the `model_util.sh` script to test others.
 {{% /notice %}}
 
-Ollama hosts and runs models, but first you need to load model before performing inference.  
+Ollama hosts and runs models, but you need to load a model before performing inference.  
 
 To do this, run:
 
@@ -101,7 +101,7 @@ In this example, the output shows more than a 15% performance increase of arm64
 
 ## Evaluating Price and Performance
 
-This Learning Path compared GKE amd64-based c4 against arm64-based c4a instances, both similarly specified for vCPU and memory. Typically, arm64 instances provide better cost efficiency. Check your cloud provider's pricing to confirm potential cost-performance advantages for your workloads.
+This Learning Path compared GKE amd64-based c4 against arm64-based c4a instances, both similarly specified for vCPU and memory. Typically, arm64 instances provide better cost efficiency. Check your cloud provider's pricing to confirm potential price performance advantages for your workloads.
 
 ## Summary
 
@@ -113,5 +113,5 @@ In this Learning Path, you learned how to:
 
 You can use these insights to evaluate Arm's potential advantages for your workloads.
 
-Make sure to shutdown the test cluster and delete all resources after use. 
+Make sure to shutdown the test cluster and delete all resources.
 

content/learning-paths/servers-and-cloud-computing/multiarch_ollama_on_gke/_index.md

@@ -1,13 +1,9 @@
 ---
-title: Migrate an amd64 cluster to a hybrid arm64 and amd64 cluster using a multi-arch container image on GKE using Ollama
-
-draft: true
-cascade:
-    draft: true
+title: Add Arm nodes to your GKE cluster using a multi-architecture Ollama container image 
 
 minutes_to_complete: 30
 
-who_is_this_for: This Learning Path is for developers interested in migrating a homogeneous (amd64 K8s) cluster to a hybrid (arm64 and amd64) cluster using a multi-architecture container image on GKE. This Learning Path demonstrates the migration using Ollama. 
+who_is_this_for: This Learning Path is for developers interested in migrating a homogeneous (amd64 K8s) cluster to a hybrid (arm64 and amd64) cluster on Google Kubernetes Engine (GKE) using a multi-architecture container image. This Learning Path demonstrates the migration using Ollama. 
 
 
 learning_objectives:
@@ -17,7 +13,7 @@ learning_objectives:
 
 prerequisites:
     - A [Google Cloud account](https://console.cloud.google.com/).
-    - A local machine with [Google Cloud CLI](/install-guides/gcloud) and [kubectl](/install-guides/kubectl/) installed.
+    - A local machine with [Google Cloud CLI](/install-guides/gcloud/) and [kubectl](/install-guides/kubectl/) installed.
     - The [GKE Cloud Plugin](https://cloud.google.com/kubernetes-engine/docs/how-to/cluster-access-for-kubectl#gcloud) installed.