In the cluster where Alauda AI is to be used, the following two operators need to be deployed:
Alauda AI Operator is the main engine that powers Alauda AI products. It focuses on two core functions: model management and inference services, and provides a flexible framework that can be easily expanded.
Alauda AI Model Serving Operator provides serverless model inference.
During the deployment process of the Alauda AI, the Alauda AI Model Serving Operator will be automatically deployed, without requiring manual operation or configuration changes.
You can download 'Alauda AI' and 'Alauda AI Model Serving' from the Marketplace on the Customer Portal website. Follow these steps:
aml-operator.xxx.tgz
and kserveless-operator.xxx.tgz
packages.We need to upload both Alauda AI
and Alauda AI Model Serving
to the cluster where Alauda AI is to be used.
First, we need to download the violet
tool if not present on the machine.
Log into the Web Console and switch to the Administrator view:
violet
tool.chmod +x ${PATH_TO_THE_VIOLET_TOOL}
to make the tool executable.Save the following script in uploading-ai-cluster-packages.sh
first, then read the comments below to update environment variables for configuration in that script.
${PLATFORM_ADDRESS}
is your ACP platform address.${PLATFORM_ADMIN_USER}
is the username of the ACP platform admin.${PLATFORM_ADMIN_PASSWORD}
is the password of the ACP platform admin.${CLUSTER}
is the name of the cluster to install the Alauda AI components into.${AI_CLUSTER_OPERATOR_NAME}
is the path to the Alauda AI Cluster Operator package tarball.${KSERVELESS_OPERATOR_PKG_NAME}
is the path to the KServeless Operator package tarball.${REGISTRY_ADDRESS}
is the address of the external registry.${REGISTRY_USERNAME}
is the username of the external registry.${REGISTRY_PASSWORD}
is the password of the external registry.After configuration, execute the script file using bash ./uploading-ai-cluster-packages.sh
to upload both Alauda AI
and Alauda AI Model Serving
operator.
In Administrator view:
Click Marketplace / OperatorHub.
At the top of the console, from the Cluster dropdown list, select the destination cluster where you want to install Alauda AI.
Select Alauda AI, then click Install.
Install Alauda AI window will popup.
Then in the Install Alauda AI window.
Leave Channel unchanged.
Check whether the Version matches the Alauda AI version you want to install.
Leave Installation Location unchanged, it should be aml-operator
by default.
Select Manual for Upgrade Strategy.
Click Install.
Confirm that the Alauda AI tile shows one of the following states:
Installing
: installation is in progress; wait for this to change to Installed
.Installed
: installation is complete.Once Alauda AI Operator is installed, you can create an Alauda AI instance.
In Administrator view:
Click Marketplace / OperatorHub.
At the top of the console, from the Cluster dropdown list, select the destination cluster where you want to install the Alauda AI Operator.
Select Alauda AI, then Click.
In the Alauda AI page, click All Instances from the tab.
Click Create.
Select Instance Type window will pop up.
Locate the AmlCluster tile in Select Instance Type window, then click Create.
Create AmlCluster form will show up.
Keep default
unchanged for Name.
Select Deploy Flavor from dropdown:
single-node
for non HA deployments.ha-cluster
for HA cluster deployments (Recommended for production).Select Managed for Knative Serving Mode.
Select Managed for KServe Mode.
Input a valid domain for Domain field.
This domain is used by ingress gateway for exposing model serving services. Most likely, you will want to use a wildcard name, like *.example.com.
You can specify the following certificate types by updating the Domain Certificate Type field:
Provided
SelfSigned
ACPDefaultIngress
By default, the configuration uses SelfSigned
certificate type for securing ingress traffic to your cluster, the certificate is
stored in the knative-serving-cert
secret that is specified in the Domain Certificate Secret field.
To use certificate provided by your own, store the certificate secret in the istio-system
namespace, then update the value of the
Domain Certificate Secret field, and change the value of the Domain Certificate Secret field to Provided
.
Under Gitlab section:
cpaas-system
for Admin Token Secret Namespace.aml-gitlab-admin-token
for Admin Token Secret Name.Under MySQL section:
3306
).aml
).About MySQL user privileges
CREATE DATABASE
privileges to create the database.Review above configurations and then click Create.
Check the status field from the AmlCluster
resource which named default
:
Should returns Ready
:
Now, the core capabilities of Alauda AI have been successfully deployed. If you want to quickly experience the product, please refer to the Quick Start.
If you want to replace GitLab Service after installation, follow these steps:
Reconfigure GitLab Service
Refer to the Pre-installation Configuration and re-execute its steps.
Update Alauda AI Instance
Modify GitLab Configuration
In the Update default form:
cpaas-system
aml-gitlab-admin-token
Restart Components
Restart the aml-controller
deployment in the kubeflow
namespace.
Refresh Platform Data
In Alauda AI management view, re-manage all namespaces.
Original models won't migrate automatically Continue using these models: