Currently, I see that TaskingAI has already supported vision models, such as GPT4-v and similar, but I haven’t figured out how to use them. Does anyone know?
Hi Riley,
TaskingAI has indeed integrated multimodal large models like GPT4-v. However, our image upload and reception functionality is currently under rapid development. We expect to implement such features in the next version, please stay tuned.
Hello, TaskingAI has now integrated these vision models and supports image upload functionality. However, the native image reception feature for the models is still under development and is expected to be released within 2 weeks.
Currently, there is a more powerful feature that can temporarily meet this need: users can set tools in the assistant and select a vision plugin, such as Gemini. In this way, all models can gain image comprehension capabilities comparable to Gemini.
1 Like