Project

AutoCoder

Challenging

22 completions

~ 15 hours

4.2

This project will help you gain hands-on experience with GitHub Actions, the GitHub API, Bash scripting, and integrating third-party services like OpenAI's ChatGPT. You will also learn about workflow automation, security considerations, and the power of integrating AI in DevOps practices.

Provided by

JetBrains Academy

About

Dive into the cutting-edge intersection of DevOps and AI with AutoCoder. This project guides you to build a reusable GitHub Action that leverages Generative AI to auto-generate code. You will create workflows, interact with OpenAI using scripts, enforce security standards, and eventually convert your project to a reusable GitHub Action to share with others or show off in your portfolio.

Graduate project

This project covers the core topics of the DevOps Engineer with AI: CI/CD Pipelines & Docker Skills course, making it sufficiently challenging to be a proud addition to your portfolio.

At least one graduate project is required to complete the course.

What you'll learn

Once you choose a project, we'll provide you with a study plan that includes all the necessary topics from your course to get it built. Here’s what awaits you:

Let's start with the GitHub repository. Set up a new public GitHub repository in your GitHub account which you will use to store the configuration files for GitHub Actions as well as the script to interact with ChatGPT.

Develop a basic workflow file to recap the basics. The action runs on push events and prints “Hello, world!”

Use GitHub Actions to interact with the versatile GitHub API, a tool capable of managing the full spectrum of repository data. In this stage, you'll focus on using it to read existing issues and comments.

Fine-tune the issues before ChatGPT processes them. Curate the content to ensure it's concise and relevant, which will assist ChatGPT in generating quality code. Additionally, tag Issues with a specific label so that only issues containing it are sent to ChatGPT.

Integrate OpenAI's ChatGPT into the workflow using a Bash script to generate code based on the contents of the issue. Upload the generated files as an artifact and echo the files in the workflow logs.

Create a pull request with the generated code for review. The branch should be named with the convention autocoder-branch-issueNumber and the pull request should be created against the main branch. Commit the files first in your workflow and use an external action to create the pull request.

Add the action.yml metadata file to define the inputs and outputs for the workflow.

Reviews

Roland Onderka

2 months ago

4.3

Very intersting project. Learned many new topics and a whole lot about GitHub actions.

Brendan Tomlinson

5 months ago

5.0

I learned that it's really easy to get lost in config hell if you start this project and don't finish it, then come back a year later and try to finish it from where you left off.

Klekovkina Alena

6 months ago

4.7

This project taught me how to create reusable GitHub Actions and integrate AI tools into developer workflows. I learned to: structure composite actions with action.yml; handle GitHub's API for issues and pull requests; manage secrets and permissions securely.The project was really challenging for m ...

4.2

Learners who completed this project within the DevOps Engineer with AI: CI/CD Pipelines & Docker Skills course rated it as follows:

Usefulness

4.6

Fun

4.2

Clarity

3.8