Skip to main content
TealTiger provides official Helm charts for deploying on any Kubernetes cluster. The charts include production-ready defaults, auto-scaling, monitoring, and security configurations.

​
Quick Start

# Add the TealTiger Helm repository
helm repo add tealtiger https://charts.tealtiger.ai
helm repo update

# Install TealTiger
helm install tealtiger tealtiger/tealtiger \
  --namespace tealtiger \
  --create-namespace \
  --set secrets.openaiApiKey=sk-xxx

# Verify
kubectl get pods -n tealtiger

​
Available Charts

ChartDescriptionUse Case
tealtiger/tealtigerFull TealTiger deploymentProduction, staging
tealtiger/tealtiger-engineTealEngine onlyLightweight policy engine
tealtiger/tealtiger-monitorMonitoring stackPrometheus + Grafana dashboards

​
Installation

​
Prerequisites

  • Kubernetes 1.25+
  • Helm 3.10+
  • kubectl configured for your cluster

​
Basic Install

helm install tealtiger tealtiger/tealtiger \
  --namespace tealtiger \
  --create-namespace

​
Production Install

helm install tealtiger tealtiger/tealtiger \
  --namespace tealtiger \
  --create-namespace \
  --values values-production.yaml

​
Using Existing Secrets

# Create secret first
kubectl create secret generic tealtiger-secrets \
  --namespace tealtiger \
  --from-literal=openai-api-key=sk-xxx \
  --from-literal=anthropic-api-key=sk-ant-xxx

# Install referencing the secret
helm install tealtiger tealtiger/tealtiger \
  --namespace tealtiger \
  --set existingSecret=tealtiger-secrets

​
Configuration

​
values.yaml Reference

# values-production.yaml

replicaCount: 3

image:
  repository: ghcr.io/tealtiger/python-sdk
  tag: "1.1.0"
  pullPolicy: IfNotPresent

service:
  type: ClusterIP
  port: 8080

ingress:
  enabled: true
  className: nginx
  annotations:
    cert-manager.io/cluster-issuer: letsencrypt-prod
  hosts:
    - host: api.example.com
      paths:
        - path: /
          pathType: Prefix
  tls:
    - secretName: tealtiger-tls
      hosts:
        - api.example.com

resources:
  requests:
    cpu: 250m
    memory: 256Mi
  limits:
    cpu: "1"
    memory: 512Mi

autoscaling:
  enabled: true
  minReplicas: 3
  maxReplicas: 20
  targetCPUUtilization: 70
  targetMemoryUtilization: 80

# TealTiger configuration
tealtiger:
  environment: production
  logLevel: INFO

  engine:
    enabled: true
    policyMode: ENFORCE

  guard:
    enabled: true
    piiDetection: true
    promptInjection: true
    contentModeration: true

  monitor:
    enabled: true
    costTracking: true
    budgetAlerts: true

  circuit:
    enabled: true
    failureThreshold: 5
    resetTimeout: 30

  audit:
    enabled: true
    redaction: true
    retention: 90

# Secrets (use existingSecret for production)
secrets:
  existingSecret: ""
  openaiApiKey: ""
  anthropicApiKey: ""
  geminiApiKey: ""
  cohereApiKey: ""
  mistralApiKey: ""

# Monitoring
monitoring:
  serviceMonitor:
    enabled: true
    interval: 30s
  grafanaDashboard:
    enabled: true

# Pod disruption budget
podDisruptionBudget:
  enabled: true
  minAvailable: 2

# Node affinity
nodeSelector: {}
tolerations: []
affinity: {}

​
Platform-Specific Guides

​
Amazon EKS

# Create EKS cluster (if needed)
eksctl create cluster --name tealtiger --region us-east-1

# Install AWS Load Balancer Controller
helm install aws-load-balancer-controller \
  eks/aws-load-balancer-controller \
  --namespace kube-system

# Install TealTiger
helm install tealtiger tealtiger/tealtiger \
  --namespace tealtiger \
  --create-namespace \
  --set ingress.className=alb \
  --set ingress.annotations."alb\.ingress\.kubernetes\.io/scheme"=internet-facing

​
Google GKE

# Create GKE cluster (if needed)
gcloud container clusters create tealtiger \
  --region us-central1 \
  --num-nodes 3

# Install TealTiger
helm install tealtiger tealtiger/tealtiger \
  --namespace tealtiger \
  --create-namespace \
  --set ingress.className=gce

​
Azure AKS

# Create AKS cluster (if needed)
az aks create --resource-group tealtiger-rg \
  --name tealtiger-cluster \
  --node-count 3

# Install TealTiger
helm install tealtiger tealtiger/tealtiger \
  --namespace tealtiger \
  --create-namespace \
  --set ingress.className=azure-application-gateway

​
Upgrading

# Update repo
helm repo update

# Check available versions
helm search repo tealtiger --versions

# Upgrade
helm upgrade tealtiger tealtiger/tealtiger \
  --namespace tealtiger \
  --values values-production.yaml

# Rollback if needed
helm rollback tealtiger 1 --namespace tealtiger

​
Monitoring Stack

Install the optional monitoring chart for Prometheus metrics and Grafana dashboards. 
helm install tealtiger-monitor tealtiger/tealtiger-monitor \
  --namespace tealtiger \
  --set prometheus.enabled=true \
  --set grafana.enabled=true \
  --set grafana.adminPassword=changeme

​
Pre-built Dashboards

The monitoring chart includes Grafana dashboards for:
  • Request rate and latency (P50, P95, P99)
  • Error rates by guardrail type
  • Cost tracking per provider and model
  • Token usage and budget consumption
  • Circuit breaker status
  • Audit event volume

​
Uninstall

helm uninstall tealtiger --namespace tealtiger
kubectl delete namespace tealtiger

​
Next Steps

Terraform

Provision clusters with Terraform

Pulumi

Deploy with Pulumi

Monitoring

Set up monitoring and alerting

Security

Security best practices for Kubernetes