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

Feat/converse support images #211

Open
wants to merge 9 commits into
base: develop
Choose a base branch
from

Conversation

MiNeves00
Copy link
Contributor

LLMstudio Version X.X.X

What was done in this PR:

  • Added ConverseAPI support for input of images using Openai's contract. Supports single or multiple images.

How it was tested:

  • Integration test added test_send_imgs for converse and openai - tested sync, async, stream and non stream
  • Run core.py which now has code for using images. (example is there on how to run with images)

Additional notes:

  • Prettified print of ChatCompletionLLMstudio to hide the b64 image since it would be huge in the print
    • Ex: 'chat_input': [{'type': 'text', 'text': "What's in this image?"}, {'type': 'image_url', 'image_url': {'url': '<large image base64 data hidden>'}}, {'type': 'image_url', 'image_url': {'url': 'https://awsmp-logos.s3.amazonaws.com/seller-zx4pk43qpmxoa/53d235806f343cec94aac3c577d81c13.png'}}]

@MiNeves00 MiNeves00 self-assigned this Feb 19, 2025
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