Great project, not sure if its dead or not.. but with the new vision preview models. I have modified the original codebase to support vision by supplying a --image option. Only works with the gpt-4-vision-preview model, supports both local images and URLs.
Also added an extra dependency that estimates the number of tokens.
Great project, not sure if its dead or not.. but with the new vision preview models. I have modified the original codebase to support vision by supplying a
--image
option. Only works with thegpt-4-vision-preview
model, supports both local images and URLs.Also added an extra dependency that estimates the number of tokens.