Integrate chat models with vision capability?

It would be nice if TaskingAI could integrate vision LLMs. I’m working on a project where having chat models that can also analyze and respond to visual info.

Is the team working on adding vision support, or is it already on the roadmap?

Thanks for the great suggestion. As a fact, the integration of multimodal LLMs is already under development. I cannot provide a exact timeline now, but you can expect to see that feature soon. Please stay tuned.

1 Like