Skip to content

Commit f46533d

Browse files
author
tejhan-diallo
committed
New KAITO documentation updates
1 parent 20cbd2d commit f46533d

13 files changed

+57
-28
lines changed

docs/book/src/README.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,8 @@ Azure Kubernetes Service (AKS) Extension for Visual Studio Code helps enable AKS
2424
* [Run Image Cleaner Eraser Tool](./features/image-cleaner-eraser-tool.md)
2525
* [Run Retina Capture](./features/retina-capture.md)
2626
* [Run Automated Deployments Commands](./features/draft-integration.md)
27-
* [Install & Deploy KAITO Models](./features/kaito-integration.md)
27+
* [Install and Deploy KAITO Models](./features/kaito-install-deploy.md)
28+
* [Manage and Test KAITO Deployments](./features/kaito-manage-test.md)
2829

2930
## Development and Release
3031

docs/book/src/SUMMARY.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,8 @@
2626
- [Run Retina Capture](./features/retina-capture.md)
2727
- [Run Draft Command](./features/draft-integration.md)
2828
- [AKS plugins for GitHub Copilot for Azure](./features/aks-plugins-github-copilot.md)
29-
- [Install & Deploy KAITO Models](./features/kaito-integration.md)
29+
- [Install and Deploy KAITO Models](./features/kaito-install-deploy.md)
30+
- [Manage and Test KAITO Deployments](./features/kaito-manage-test.md)
3031

3132
- [Release](./release.md)
3233
- [Releasing Information](./release/releasing.md)
Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
1+
# Install and Deploy KAITO models
2+
3+
The KAITO integration enables seamless installation of KAITO onto your clusters, empowering you to deploy AI models, manage workflows, and test deployments with ease and precision.
4+
5+
### Install KAITO
6+
7+
Right click on your desired AKS cluster and select **Deploy an LLM with KAITO** and then click on **Install KAITO** to open up the KAITO installation page.
8+
9+
![Installation Page](../resources/kaito-installation-page.png)
10+
11+
Once on the page, click **Install KAITO** and the KAITO installation process will begin. Once KAITO has been successfully installed, you will be prompted with a "Generate Workspace" button that will redirect you to the model deployment page.
12+
13+
![Successfull Installation](../resources/kaito-installation-success.png)
14+
15+
### Deploy a model
16+
17+
Right click on an AKS cluster that has KAITO successfully installed and select **Deploy an LLM with KAITO** and then click on **Create KAITO Workspace** to open the KAITO model deployment page.
18+
19+
![Deployment Page](../resources/kaito-deploy-page.png)
20+
21+
Once on this page, you can click any of the models to open up the side panel, which will present you with the option to either **Deploy Default workspace CRD** or **Customize Workspace CRD**.
22+
23+
Click **Deploy Default workspace CRD** to deploy the model. It will track the progress of the model and notify you once the model has been successfully deployed. It will also notify you if the model was already previously unsucessfully onto your cluster. Upon successful deployment, you will be prompted with a "View Deployed Models" button that will redirect you to the deployment management page.
24+
25+
![Phi-2 Model Being Deployed](../resources/kaito-deployment-example-in-progress.png)
26+
![Phi-2 Model Successfully Deployed](../resources/kaito-deployment-example-success.png)
27+
28+
Click **Customize Workspace CRD** to open up a CRD file pre-populated with the infromation necessary to deploy the model. You can alter this file to your desires and save it locally.

docs/book/src/features/kaito-integration.md

Lines changed: 0 additions & 26 deletions
This file was deleted.
Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
1+
# Manage and Test KAITO Deployments
2+
3+
Actively monitor the the status of all KAITO deployments on the cluster, retrieve logs, test the inference servers, and delete/redeploy models.
4+
5+
### Manage KAITO Deployments
6+
7+
Right click on your desired AKS cluster and select **Deploy an LLM with KAITO** and then click on **Manage KAITO Models**.
8+
9+
![Manage Page](../resources/kaito-manage-page.png)
10+
11+
Once on this page, you will see all existing KAITO deployments on the cluster, alongside their status (ongoing, successful, or failed).
12+
13+
For your selected deployment, click **Get Logs** to access the latest logs from the KAITO workspace pods. This action will generate a new text file containing the most recent 500 lines of logs.
14+
15+
To delete a model, select **Delete Workspace** (or **Cancel** for ongoing deployments). For failed deployments, choose **Re-deploy Default CRD** to remove the current deployment and restart the model deployment process from scratch.
16+
17+
### Test a Model
18+
19+
On your desired model, select **Test** to access the model testing page.
20+
21+
![Test Page](../resources/kaito-test-page.png)
22+
23+
Once on the testing page, you can modify the parameters and enter a prompt for submsission. Click **Reset Params** to reset all configurable parameters to their default values. Click **Submit Prompt** to submit your query.
24+
25+
![Query Response](../resources/kaito-test-response.png)
39.7 KB
Loading
3.78 KB
Loading
-268 KB
Binary file not shown.
192 KB
Loading
15.5 KB
Loading

0 commit comments

Comments
 (0)