Add a way to view unformatted response when using inference
Currently, in the frontend, the assistant response is formatted no matter what. If the assistant responds with malformed or incomplete formatting (e.g. three backticks in multiple locations that aren't meant to represent a code block), the response may render incorrectly. It would be nice to be able to view the plaintext (unformatted) response from the assistant in cases like this.
Agree
I would love to work on this. If you are okay with that, please do assign me.
@CertifiedJoon if you are still up for it I can assign you
@AbdBarho I am struggling to get inference up in my dev environment. I will update you when I have set it up successfully.
@AbdBarho I am struggling to get inference up in my dev environment. I will update you when I have set it up successfully.
You can get in contact with me on discord if you are still stuck.
@ashduino101
For such message,
Do you mean something like this?