Skip to content

akshayamadhuri/kubernetes-chatgpt-bot

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 

Repository files navigation

Introduction

A ChatGPT1 bot for Kubernetes issues. Ask the AI how to solve your Prometheus alerts, get pithy responses.

No more solving alerts alone in the darkness - the internet has your back.

Please consider upvoting on Product Hunt or sending to your favorite newsletter. One day, Skynet will remember your kindness and spare you!

How it works

Prometheus forwards alerts to the bot using a webhook receiver.

The bot sends a query to OpenAI, asking it how to fix your alerts.

You stockpile food in your pantry for the robot uprising.

The bot is implemented using Robusta.dev, an open source platform for responding to Kubernetes alerts. We also have a SaaS platform for multi-cluster Kubernetes observability.

Prerequisites

  • A Slack workspace (for Teams/Discord support, please open an issue)

Setup

  1. Install Robusta with Helm
  2. Load the ChatGPT playbook. Add the following to generated_values.yaml:
playbookRepos:
  chatgpt_robusta_actions:
    url: "https://github.com/robusta-dev/kubernetes-chatgpt-bot.git"

customPlaybooks:
# Add the 'Ask ChatGPT' button to all Prometheus alerts
- triggers:
  - on_prometheus_alert: {}
  actions:
  - chat_gpt_enricher: {}
  1. Add your ChatGPT API key to generated_values.yaml. Make sure you edit the existing globalConfig section, don't add a duplicate section.
globalConfig:
  chat_gpt_token: YOUR KEY GOES HERE
  1. Do a Helm upgrade to apply the new values: helm upgrade robusta robusta/robusta --values=generated_values.yaml --set clusterName=<YOUR_CLUSTER_NAME>

  2. Send your Prometheus alerts to Robusta. Alternatively, just use Robusta's bundled Prometheus stack.

Demo

Instead of waiting around for a Prometheus alert, lets cause one.

  1. Deploy a broken pod that will be stuck in pending state:
kubectl apply -f https://raw.githubusercontent.com/robusta-dev/kubernetes-demos/main/pending_pods/pending_pod.yaml
  1. Trigger a Prometheus alert immediately, skipping the normal delays:
robusta playbooks trigger prometheus_alert alert_name=KubePodCrashLooping namespace=default pod_name=example-pod

An alert will arrive in Slack with a button. Click the button to ask ChatGPT about the alert.

Future Improvements

Can ChatGPT give better answers if you feed it pod logs or the output of kubectl get events?

Robusta already collects this data and attaches it to Prometheus alerts, so it should be easy to add.

PRs are welcome!

Community

Share your funniest output and suggest new features on our Slack.

Promotional Images

Feel free to use the following image or create your own.

Screen Shot 2023-01-10 at 18 29 56

More Resources

Footnotes

  1. Technically this project doesn't use ChatGPT. It uses the text-davinci-003 model which is a GPT3.5-based sibling of ChatGPT. Given that most people are familiar with ChatGPT, but not text-dainci-003 or GPT3.5, we've decided to keep the name "ChatGPT bot" despite the technical inaccuracy.

About

A ChatGPT bot for Kubernetes issues.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%