Kani-vision

Latest version: v0.6.3

Safety actively analyzes 685525 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

0.6.3

- 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/.

Links

Releases

Has known vulnerabilities

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.