Helm Chart
Deploy Spice.ai Enterprise on Kubernetes with the official Helm chart.
The Spice.ai Enterprise Helm chart deploys the Spice runtime as a Kubernetes Deployment or StatefulSet with a ConfigMap-mounted Spicepod configuration.
Install
The chart is published to the AWS Marketplace ECR registry for the enterprise and enterprise-models image variants, with the image pre-configured. The -sysalloc image has no chart of its own: set image.tag to run it. Subscribe to the Enterprise listing first (see AWS Marketplace), then authenticate Helm against the registry:
aws ecr get-login-password --region us-east-1 \
| helm registry login --username AWS --password-stdin 709825985650.dkr.ecr.us-east-1.amazonaws.comThe login is valid for 12 hours; re-run it when the token expires.
helm install spiceai \
oci://709825985650.dkr.ecr.us-east-1.amazonaws.com/spice-ai/spiceai-enterprise-byol \
--version 2.4.1-enterprise-models-helm \
--set spicepod.name=my-appValues Reference
| Parameter | Description | Default |
|---|---|---|
image.repository | Container image repository | 709825985650.dkr.ecr.us-east-1.amazonaws.com/spice-ai/spiceai-enterprise-byol |
image.tag | Container image tag | The chart variant's image tag, such as 2.4.1-enterprise-models |
imagePullSecrets | Image pull secrets for the pod | None |
replicaCount | Number of replicas | 1 |
strategy | Update strategy for the Deployment | None (Kubernetes default) |
updateStrategy | Update strategy for the StatefulSet | None (Kubernetes default) |
command | Container command that starts spiced | spiced with HTTP on 8090, metrics on 9090, and Arrow Flight on 50051 |
livenessProbe | Liveness probe for the runtime container | HTTP GET /health on port 8090 |
readinessProbe | Readiness probe for the runtime container | HTTP GET /v1/ready on port 8090 |
startupProbe | Startup probe for the runtime container | HTTP GET /health on port 8090 |
serviceAccount.create | Create a ServiceAccount | false |
serviceAccount.name | ServiceAccount name | None |
serviceAccount.annotations | Annotations for the ServiceAccount | {} |
service.type | Kubernetes Service type | None (Kubernetes default, ClusterIP) |
service.additionalAnnotations | Annotations for the Service | {} |
service.loadBalancerSourceRanges | Source IP ranges allowed to reach a LoadBalancer Service | None |
service.ports | Service ports, which replace the default list | 8090 (http), 9090 (metrics), 50051 (flight) |
service.selector | Service selector, which replaces the default selector | The chart's labels, additionalLabels, and app: <release name> |
stateful.enabled | Use a StatefulSet with PVC | false |
stateful.storageClass | StorageClass for StatefulSet PVC | standard |
stateful.size | PVC size | 1Gi |
stateful.mountPath | Mount path in container | /data |
monitoring.podMonitor.enabled | Create a PodMonitor for Prometheus | false |
monitoring.podMonitor.additionalLabels | Labels for the PodMonitor | {} |
additionalLabels | Labels added to all resources | {} |
nameOverride | Name used in place of the chart name in resource names and in the app.kubernetes.io/name and app.kubernetes.io/part-of labels | The chart name |
fullnameOverride | Name of the Deployment or StatefulSet and the Service, the ConfigMap prefix, and the default name of a created ServiceAccount, truncated to 63 characters | <release name>-<name>, or the release name when it contains the name |
namespaceOverride | Namespace for the workload, the Service, the ConfigMap, and the ServiceAccount. The PodMonitor stays in the release namespace | The release namespace |
selectorOverride | Labels that replace app.kubernetes.io/name and app.kubernetes.io/instance in the pod selector and in the labels of every resource. The chart adds app: <release name> to the selector | None |
additionalEnv | Extra environment variables | [] |
resources | CPU/memory requests and limits | {} |
nodeSelector | Node selector for the pod | None |
tolerations | Tolerations for the pod | None |
affinity | Affinity rules for the pod | None |
volumes | Additional volumes | [] |
volumeMounts | Additional volume mounts | [] |
spicepod | Spicepod configuration (inlined into ConfigMap) | name: app, version: v1, kind: Spicepod, and no datasets |
Spicepod Configuration
The Spicepod spec is inlined directly in the Helm values and mounted as a ConfigMap:
spicepod:
name: my-app
version: v1
kind: Spicepod
datasets:
- from: s3://my-bucket/data/
name: my_data
params:
file_format: parquet
acceleration:
enabled: true
engine: cayenneStatefulSet with Persistent Storage
Enable a StatefulSet with a PersistentVolumeClaim for durable storage:
stateful:
enabled: true
storageClass: gp3
size: 50Gi
mountPath: /dataUpdate Strategy
Both keys are unset by default, so Kubernetes applies its own default strategy. Which one the chart reads depends on stateful.enabled.
With stateful.enabled: false the chart renders a Deployment and reads strategy:
strategy:
type: RecreateWith stateful.enabled: true the chart renders a StatefulSet and reads updateStrategy:
updateStrategy:
type: RollingUpdateThe key that does not match stateful.enabled is ignored, so setting strategy on a StatefulSet deployment has no effect. Each value is passed through to the workload spec unchanged, so any field the Kubernetes strategy type accepts (for example rollingUpdate.maxUnavailable or rollingUpdate.partition) can be set alongside type.
Health Probes
The chart sets a liveness, readiness, and startup probe on the runtime container. Each probe uses these defaults:
livenessProbe:
httpGet:
path: /health
port: 8090
timeoutSeconds: 1
periodSeconds: 10
failureThreshold: 3The readiness probe calls /v1/ready instead of /health. Helm merges your values with these defaults, so you can override one field. For example, give a large dataset more time to load before the kubelet restarts the container:
startupProbe:
failureThreshold: 60When a probe sets exec, tcpSocket, or grpc, the chart removes the default httpGet handler from that probe.
Container Command
By default, the container runs this command:
command:
- /usr/local/bin/spiced
- --http
- 0.0.0.0:8090
- --metrics
- 0.0.0.0:9090
- --flight
- 0.0.0.0:50051Set command to replace the full list, for example to add a spiced flag. Include every flag you need, because the chart does not merge your list with the default. The container ports stay 8090 (HTTP), 9090 (metrics), and 50051 (Flight), and the default probes call port 8090. Keep each address on its port.
Service Exposure
The Service exposes ports 8090 (http), 9090 (metrics), and 50051 (flight). To expose the runtime through a cloud load balancer and allow only some source ranges:
service:
type: LoadBalancer
loadBalancerSourceRanges:
- 10.0.0.0/8Pod Scheduling and Image Pull Secrets
nodeSelector, tolerations, affinity, and imagePullSecrets are passed to the pod spec unchanged:
nodeSelector:
node-pool: spice
tolerations:
- key: dedicated
operator: Equal
value: spice
effect: NoSchedule
imagePullSecrets:
- name: my-registry-secretResource Limits
resources:
requests:
cpu: 200m
memory: 1Gi
limits:
cpu: "2"
memory: 4GiPrometheus Monitoring
monitoring:
podMonitor:
enabled: true
additionalLabels:
release: prometheusServiceAccount for Cloud IAM
AWS IRSA (EKS)
serviceAccount:
create: true
name: spiceai
annotations:
eks.amazonaws.com/role-arn: arn:aws:iam::123456789012:role/my-spice-roleSee AWS IRSA for full setup instructions.
GKE Workload Identity
serviceAccount:
create: true
annotations:
iam.gke.io/gcp-service-account: my-gcp-sa@my-project.iam.gserviceaccount.comAzure Workload Identity (AKS)
serviceAccount:
create: true
annotations:
azure.workload.identity/client-id: <AZURE_CLIENT_ID>