Skip to content
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.

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

Add support for LLaVa #17

Draft
wants to merge 6 commits into
base: main
Choose a base branch
from
Draft

Add support for LLaVa #17

wants to merge 6 commits into from

Conversation

dsibilio
Copy link
Collaborator

@dsibilio dsibilio commented Sep 16, 2024

Adding a describe_image tool to describe/analyze/explain/extrapolate context and text from images using https://llava-vl.github.io/.

This feature was worked on as part of the Hyland Alfresco TechQuest Hackathon 2024.

NOTE: it would be nice to experiment with streamed responses before merging a feature like this, as it feels pretty clunky otherwise. However, while with very minimal tinkering it was possible to achieve streaming responses, the quality of the responses themselves seemed to deteriorate so that requires some investigation as some parameters should most likely played with until good responses can be obtained even then.

@dsibilio
Copy link
Collaborator Author

cc: @gionn @tpage-alfresco @damianujma, just so you're aware of the feature we worked on together with @vprovaggi during the Hyland Alfresco TechQuest 2024 Hackathon, and in case you wanted to play around with it.

We do not plan to merge it at this time.

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.

1 participant