K8sGPT is a tool for scanning your Kubernetes clusters, diagnosing and triaging issues in simple english. It has SRE experience codified into its analyzers and helps to pull out the most relevant information to enrich it with AI. In the session we will integrate OpenAI with K8sGPT to diagnose our Kubernetes Cluster.
AWS Community Day CPH - Three problems of Terraform
K8sGPTThe AI way to diagnose Kubernetes
1. K8sGPT: The AI
way to diagnose
Kubernetes
Shubham Chaubey
Software Consultant
DevOps Competency
2. Lack of etiquette and manners is a huge turn off.
KnolX Etiquettes
Punctuality
Join the session 5 minutes prior to the session start time. We start on
time and conclude on time!
Feedback
Make sure to submit a constructive feedback for all sessions as it is very
helpful for the presenter.
Silent Mode
Keep your mobile devices in silent mode, feel free to move out of session
in case you need to attend an urgent call.
Avoid Disturbance
Avoid unwanted chit chat during the session.
3. 1. What is K8sGPT?
2. How does it work?
3. How K8sGPT can help us?
4. Available backends for K8sGPT
5. How to use K8sGPT?
Installing the CLI
Installing in-cluster operator
6. Demo
4.
5. What is K8sGPT?
K8sGPT is a tool for scanning your Kubernetes clusters, diagnosing and triaging issues in
simple English.
It aims to simplify the process of identifying and resolving Kubernetes issues by providing
explanations in plain English, leveraging AI to offer insights and suggestions for fixes.
It has SRE experience codified into its analyzers and helps to pull out the most
relevant information to enrich it with AI.
K8sGPT's functionality includes analyzing Kubernetes configurations and reporting back with
suggestions to fix issues. It supports integration with observability tools like Grafana and
Prometheus and offers an extension feature for connecting to other tools through plugins.
6. How does it work?
Extraction
K8sGPT extracts the current
configuration of all the
Kubernetes workload that is
currently deployed in a cluster
Filtration
Based on the SRE
experience codified into its
analyzers, K8sGPT
analyses and filters the
most necessary data
Generation
By passing the filtered data to
an AI backend, K8sGPT brings
you the exact explanation to
resolve any issue in your
Kubernetes cluster
7.
8. Available Backends for K8sGPT
A Backend is a service that provides access to the AI language model. There are many different
backends available for K8sGPT. Currently, a total of 8 backends are available:
OpenAI
Cohere
Amazon Bedrock
Amazon SageMaker
Azure OpenAI
Google Gemini
LocalAI
9.
10. How K8sGPT can help : Use cases
Starting as a newbie with Kubernetes, some basic errors like CrashLoopBackOff,
Service manifest not matching the pod's labels, and etc. can be a real pain. K8sGPT comes in
play here helping everyone with diagnosing the issue and providing possible solution for that in
plain English.
It can assist in pin-pointing and resolving problems related to specific resources and namespaces
For experienced SRE folks or for teams that works with Kubernetes, it
provides great observability and 24x7 monitoring experience.
It also has integration with other open source tools like Prometheus-Grafana stack
and Trivy. More integrations are already in progress.
11.
12. How to use K8sGPT?
Installation options: K8sGPT CLI or In-cluster operator
K8sGPT CLI:
• Run the analyzer on any Kubernetes cluster
• Get AI powered solutions for any issue on any Kubernetes cluster
• All you need is the Kube-config file of the cluster
In-cluster operator:
Keeps running the analyzer on the workload in the background
Publishes the results to Prometheus-Grafana stack
Provides 24x7 visibility of the cluster and the deployed workload
Monitor multiple clusters at once