Skip to content

Conversation

@chsrimanaswi
Copy link

Description

This PR adds natural language template recommendations to the aio app init command, powered by Azure OpenAI. Instead of browsing through a long list of templates, developers can now describe what they want to build in plain English, and AI will recommend the most suitable template.

Related Issue

https://jira.corp.adobe.com/browse/ACNA-4250

Motivation and Context

  • Developers find it overwhelming to browse through 20+ templates in aio app init

How Has This Been Tested?

Manual, Automated and Functional tests
See https://new.express.adobe.com/id/urn:aaid:sc:VA6C2:b55bcdd9-383a-5ab9-81aa-f4be1aceffef?sceneline=true&taskID=video&q=Start

Screenshots (if appropriate):

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)

Checklist:

  • I have signed the Adobe Open Source CLA.
  • My code follows the code style of this project.
  • My change requires a change to the documentation.
  • I have updated the documentation accordingly.
  • I have read the CONTRIBUTING document.
  • I have added tests to cover my changes.
  • All new and existing tests passed.

Copy link
Contributor

@MichaelGoberling MichaelGoberling left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Lgtm, with one question for the flow

@chsrimanaswi
Copy link
Author

image image


const response = await fetch(url, {
method: 'POST',
headers: {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we have any auth enabled for recommendation API? If not it can lead to DOS attacks very easily.

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We initially wanted everyone to access the AI prompt. We will look into how to achieve the auth part.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@sandeep-paliwal This would be good to discuss - I was thinking maybe we could pass the CLI token and do IMS auth on the backend. That of course would make it so we only allow the recommend flow for the logged in use cases and not noLogin. But maybe that's okay since noLogin is usually non-interactive?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants