How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

groq released the image recognition language for llama 3.2, and you can also choose related 90B and 11B models, but when I upload an image and ask the language model to recognize it, it always fails, I don't know if it's stuck on the base64 issue

Are there known steps to reproduce?

選取groq的llama-3.2-90b-vision-preview 或是 llama-3.2-11b-vision-preview 模型 , 然後上傳一張圖片