Install MDAI

MDAI runs in a Kubernetes cluster. You’ll use Helm charts to bring up the pods in the cluster.

Bring Up the MDAI Cluster

Make sure Docker is running.

Use kind to create a new cluster.
```
kind create cluster --name mdai
```

Use kubectl to install cert-manager.

kubectl apply -f https://github.com/cert-manager/cert-manager/releases/latest/download/cert-manager.yaml
kubectl wait --for=condition=Established crd/certificates.cert-manager.io --timeout=60s
kubectl wait --for=condition=Ready pod -l app.kubernetes.io/instance=cert-manager -n cert-manager --timeout=60s
kubectl wait --for=condition=Available=True deploy -l app.kubernetes.io/instance=cert-manager -n cert-manager --timeout=60s

Note

Wait a few moments for cert-manager to finish installing.

Use helm to install MDAI.

helm upgrade --install \
  --repo https://charts.mydecisive.ai \
  --namespace mdai \
  --create-namespace \
  --cleanup-on-fail \
  --set mdai-operator.manager.env.otelSdkDisabled=true \
  --set mdai-gateway.otelSdkDisabled=true \
  --set mdai-s3-logs-reader.enabled=false \
  --version v0.8.0-rc3 \
  mdai mdai-hub

Verify that the cluster’s pods are running.
```
kubectl get pods -n mdai
```

If the cluster is running, you’ll see output similar to the following.

NAME                                                READY   STATUS    RESTARTS     AGE
alertmanager-kube-prometheus-stack-alertmanager-0   2/2     Running   0            50s
kube-prometheus-stack-operator-6cfdc788d4-ts297     1/1     Running   0            59s
mdai-event-hub-556c8897f5-kpn9g                     1/1     Running   0            59s
mdai-gateway-5df8b6f749-qlm88                       1/1     Running   0            59s
mdai-grafana-84bb594f6c-d6shj                       3/3     Running   0            59s
mdai-kube-state-metrics-6cd9fd8458-rhrmr            1/1     Running   0            59s
mdai-operator-controller-manager-65955fb98b-trn26   1/1     Running   0            59s
mdai-prometheus-node-exporter-zm8k7                 1/1     Running   0            59s
mdai-rabbitmq-0                                     1/1     Running   0            59s
mdai-valkey-primary-0                               1/1     Running   0            59s
opentelemetry-operator-6d8ddbdc4d-5rjcl             1/1     Running   0            59s
prometheus-kube-prometheus-stack-prometheus-0       2/2     Running   0            50s

Clone our examples repo `mdai-labs`

Choose how you’d like to clone

via https

git clone https://github.com/DecisiveAI/mdai-labs.git

via ssh

git clone git@github.com:DecisiveAI/mdai-labs.git

Make the `mdai-labs` repo your working directory

cd mdai-labs

Set Up the MDAI Hub

Apply the configuration to the hub resource.

kubectl apply -f ./mdai/hub/hub_ref.yaml -n mdai

Verify the hub is applied by running

kubectl get customresourcedefinitions mdaihubs.hub.mydecisive.ai

Your output should be similar to the following.

NAME                         CREATED AT
mdaihubs.hub.mydecisive.ai   2025-03-24T20:02:19Z

Success

Now that MDAI is running, we can go on to generate log data.