New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Semantic similarity search for design elements #95

Open

kklemon opened this issue Jul 1, 2024 · 0 comments

Labels

ai functionality backlog

Collaborator

kklemon commented Jul 1, 2024

This kind of feature was already discussed during the kick-off and also recently presented by Figma as part of their first AI features.

Given our experience with the Penpot data structures and maturity of the Penai code base, such a feature should be relatively easy to implement.

A few open questions that still need to be discussed would be:

On what level should the similarity search be performed? Components? Groups? Single shapes? Arbitrary levels of the hierarchy?
Should the context, e.g. the surrounding page of a design element be included?
How to implement the similarity search? Vector search? How to compute the vectors then? Pairwise ranking? What about compute complexity?
How to display the results?

opcode81 added backlog ai functionality labels

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