Skip to content

Install Helm Chart

Deploy HolmesGPT as a service in your Kubernetes cluster with an HTTP API.

When to use the Helm chart?

Most users should use the CLI or UI/TUI instead. Using the Helm chart is only recommended if you're building a custom integration over an HTTP API.

Prerequisites

  • Kubernetes cluster
  • Helm
  • kubectl configured to access your cluster
  • Supported AI Provider API key.

Installation

  1. Add the Helm repository:

    helm repo add holmesgpt https://robusta-dev.github.io/holmesgpt
    helm repo update
    

  2. Load an API Key to HolmesGPT using Kubernetes Secret:

    kubectl create secret generic holmes-secrets \
      --from-literal=api-key="your-openai-api-key"
    
    kubectl create secret generic holmes-secrets \
      --from-literal=api-key="your-anthropic-api-key"
    
    kubectl create secret generic holmes-secrets \
      --from-literal=api-key="your-azure-api-key" \
      --from-literal=azure-endpoint="https://your-resource.openai.azure.com/" \
      --from-literal=azure-api-version="2024-02-15-preview"
    
  3. Create or modify values.yaml to customize HolmesGPT:

    If you want to change the default configuration (such as AI provider or model), create a values.yaml file:

    # values.yaml
    config:
      aiProvider: "openai"
      model: "gpt-4"
    
    # Reference the secret created above
    secret:
      create: false
      name: "holmes-secrets"
      key: "api-key"
    

  4. Install HolmesGPT:

    helm install holmesgpt holmesgpt/holmes -f values.yaml
    

Usage

After installation, test the service with a simple API call:

# Port forward to access the service locally
kubectl port-forward svc/holmesgpt 8080:80

# Test with a basic question
curl -X POST http://localhost:8080/ask \
  -H "Content-Type: application/json" \
  -d '{"question": "what pods are unhealthy and why?"}'

Upgrading

helm repo update
helm upgrade holmesgpt holmesgpt/holmes -f values.yaml

Uninstalling

helm uninstall holmesgpt

Need Help?