- Fixes an issue in `chat_in_terminal_vision` that caused filepaths to include the leading `!` errantly, leading to image files not being found
0.6.2
- (OpenAI) Fixes an issue where ImageParts could fail to be sent to the API
0.6.1
kani-vision is now released, extending the kani framework with vision-language model (VLM) support!
kani-vision comes with out of the box support for GPT-4V and LLaVA v1.5. For more information, check out the documentation at https://kani-vision.readthedocs.io/en/latest/.