A ChatGPT bot for Kubernetes issues. Ask ChatGPT 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!
Prometheus forwards alerts to the bot using a webhook receiver.
The bot asks ChatGPT 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.
- A Slack workspace (for Teams/Discord support, please open an issue)
- Install Robusta with Helm
- 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: {}
- Add your ChatGPT API key to
generated_values.yaml. Make sure you edit the existingglobalConfigsection, don't add a duplicate section.
globalConfig:
chat_gpt_token: YOUR KEY GOES HERE
-
Do a Helm upgrade to apply the new values:
helm upgrade robusta robusta/robusta --values=generated_values.yaml --set clusterName=<YOUR_CLUSTER_NAME> -
Send your Prometheus alerts to Robusta. Alternatively, just use Robusta's bundled Prometheus stack.
Instead of waiting around for a Prometheus alert, lets cause one.
- 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
- 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.
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!
Share your funniest output and suggest new features on our Slack.
Feel free to use the following image or create your own.
- Natan tests ChatGPT on production Kubernetes alerts
- Natan Yellin and Sid Palas go over the code on YouTube - relevant part starts at 38:54