uezo / ChatdollKit

ChatdollKit enables you to make your 3D model into a chatbot
Apache License 2.0
682 stars 73 forks source link

Unable to use vision feature #310

Open yodaiaia opened 1 week ago

yodaiaia commented 1 week ago

手順に従ってセットアップを完了しましたが、Vision機能が使えませんでした。エラーは発生しないのですが「画像の取得に失敗しました」という返答が返ってきます。この問題を解決するにはどうすればよいでしょうか?

uezo commented 1 week ago

Hi @yodaiaia ,

I followed the instructions and completed the setup, but I couldn't use the Vision feature. No errors occur, but I get a response saying "Failed to retrieve image." How can I resolve this issue?

If you are using ChatGPT, it is likely to be in this section. Please refer to it and try debugging, including setting breakpoints to check if images are being obtained from the camera. https://github.com/uezo/ChatdollKit/blob/master/Scripts/LLM/ChatGPT/ChatGPTService.cs#L366