kubectl-ai

Kubectl OpenAI plugin ✨

This project is a kubectl plugin to generate and apply Kubernetes manifests using OpenAI GPT.

My main motivation is to avoid finding and collecting random manifests when dev/testing things.

Usage

Prerequisites

kubectl-ai requires an OpenAI API key or an Azure OpenAI Service API key and endpoint, and a valid Kubernetes configuration.

For both OpenAI and Azure OpenAI, you can use the following environment variables:

export OPENAI_API_KEY=<your OpenAI key>

For Azure OpenAI Service, you can use the following environment variables:

export AZURE_OPENAI_ENDPOINT=<your Azure OpenAI endpoint, like https://my-aoi-endpoint.openai.azure.com>
export OPENAI_DEPLOYMENT_NAME=<your OpenAI deployment/model name. defaults to "text-davinci-003">

If AZURE_OPENAI_ENDPOINT variable is set, then it will use the Azure OpenAI Service. Otherwise, it will use OpenAI API.

Installation

• Download the binary from GitHub releases.

• If you want to use this as a kubectl plugin, then copy kubectl-ai binary to your PATH. If not, you can also use the binary standalone.

Flags and environment variables

• --require-confirmation flag or REQUIRE_CONFIRMATION environment varible can be set to prompt the user for confirmation before applying the manifest. Defaults to true.

• --temperature flag or TEMPERATURE environment variable can be set between 0 and 1. Higher temperature will result in more creative completions. Lower temperature will result in more deterministic completions. Defaults to 0.

Examples

Creating objects with specific values:

$ kubectl ai "create an nginx deployment with 3 replicas"
✨ Attempting to apply the following manifest:
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx-deployment
  labels:
    app: nginx
spec:
  replicas: 3
  selector:
    matchLabels:
      app: nginx
  template:
    metadata:
      labels:
        app: nginx
    spec:
      containers:
      - name: nginx
        image: nginx:1.7.9
        ports:
        - containerPort: 80
EOF
Use the arrow keys to navigate: ↓ ↑ → ←
? Would you like to apply this? [Apply/Don't Apply]:
  ▸ Apply
    Don't Apply

$ kubectl ai "scale nginx-deployment to 5 replicas"
✨ Attempting to apply the following manifest:
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx-deployment
spec:
  replicas: 5
  selector:
    matchLabels:
      app: nginx
  template:
    metadata:
      labels:
        app: nginx
    spec:
      containers:
      - name: nginx
        image: nginx:1.7.9
        ports:
        - containerPort: 80
EOF
Use the arrow keys to navigate: ↓ ↑ → ←
? Would you like to apply this? [Apply/Don't Apply]:
  ▸ Apply
    Don't Apply

Please note that the plugin does not know the current state of the cluster (yet?), so it will always generate the full manifest.

Optional --require-confirmation flag:

$ kubectl ai "create a service with type LoadBalancer with selector as 'app:nginx'" --require-confirmation=false
✨ Attempting to apply the following manifest:
apiVersion: v1
kind: Service
metadata:
  name: nginx-service
spec:
  selector:
    app: nginx
  ports:
  - port: 80
    targetPort: 80
  type: LoadBalancer

Multiple objects:

$ kubectl ai "create a foo namespace then create nginx pod in that namespace"
✨ Attempting to apply the following manifest:
apiVersion: v1
kind: Namespace
metadata:
  name: foo
---
apiVersion: v1
kind: Pod
metadata:
  name: nginx
  namespace: foo
spec:
  containers:
  - name: nginx
    image: nginx:latest
EOF
Use the arrow keys to navigate: ↓ ↑ → ←
? Would you like to apply this? [Apply/Don't Apply]:
  ▸ Apply
    Don't Apply

Acknowledgements and Credits

Thanks to @simongottschlag for their work on Azure OpenAI fork in https://github.com/simongottschlag/azure-openai-gpt-slack-bot which is based on https://github.com/PullRequestInc/go-gpt3