Skip to content

Commit 1fe995c

Browse files
committed
incorp feedback
1 parent 16113c7 commit 1fe995c

File tree

1 file changed

+4
-4
lines changed

1 file changed

+4
-4
lines changed

articles/aks/ai-toolchain-operator.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,7 @@ This article shows you how to enable the AI toolchain operator add-on and deploy
1717
## Before you begin
1818

1919
* This article assumes a basic understanding of Kubernetes concepts. For more information, see [Kubernetes core concepts for AKS](./concepts-clusters-workloads.md).
20-
* For ***all hosted model inference files*** and recommended infrastructure setup, see the [KAITO GitHub repository](https://github.com/Azure/kaito).
20+
* For ***all hosted model inference images*** and recommended infrastructure setup, see the [KAITO GitHub repository](https://github.com/Azure/kaito).
2121

2222
## Prerequisites
2323

@@ -88,9 +88,9 @@ This article shows you how to enable the AI toolchain operator add-on and deploy
8888
```azurecli-interactive
8989
az aks create --location ${AZURE_LOCATION} --resource-group ${AZURE_RESOURCE_GROUP} --name ${CLUSTER_NAME} --enable-managed-identity --enable-oidc-issuer --enable-ai-toolchain-operator
9090
```
91-
91+
9292
> [!NOTE]
93-
> AKS creates a managed identity once you enable the AI toolchain operator add-on. The managed identity is used to access the AI toolchain operator workspace CRD. The AI toolchain operator workspace CRD is used to create and manage AI toolchain operator workspaces.
93+
> AKS creates a managed identity once you enable the AI toolchain operator add-on. The managed identity is used to create GPU node pools in the managed AKS cluster. Proper permissions need to be set for it manually following the steps introduced in the following sections.
9494
>
9595
> AI toolchain operator enablement requires the enablement of OIDC issuer.
9696
@@ -176,7 +176,7 @@ This article shows you how to enable the AI toolchain operator add-on and deploy
176176
4. Run the Falcon 7B model with a sample input of your choice using the following `curl` command:
177177
178178
```azurecli-interactive
179-
curl -X POST "http://${SERVICE_IP}:80/chat" -H "accept: application/json" -H "Content-Type: application/json" -d '{"prompt":"YOUR_PROMPT_HERE"}'
179+
kubectl run -it --rm --restart=Never curl --image=curlimages/curl -- curl -X POST http://$CLUSTERIP/chat -H "accept: application/json" -H "Content-Type: application/json" -d "{"prompt":"YOUR QUESTION HERE"}"
180180
```
181181
182182
## Clean up resources

0 commit comments

Comments
 (0)