You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Nice project! Thank you for developing and maintaining it!
Maybe I missed something in the help, but is there a way to cancel an inference? If not, I think this could be really useful, specially when trying models locally (specially the big ones that may run very slowly).
Some suggestions (please feel free to ask me to open a separate issue for the ones you may be implemented):
Option to delete chat
Add a secondary keybinding to send a message, maybe Shift + Enter or Ctrl + Enter. Personally, I would prefer that it worked like some messengers can be configured: Enter to send and Shift/Ctrl+Enter to add a line break (maybe add a preference for this?)
Other options to the app "theme"
Tune some variables per chat, like system prompt, temperature, etc
Export the chat (as a MarkDown file?)
Add image to the chat (for multimodal models)
Thanks again. Regards
The text was updated successfully, but these errors were encountered:
You can press a when highlighting a chat on the home screen to archive it (it will remain in your local database but is hidden from the UI).
I've added alt+enter in the latest version, but support is down to your terminal. Customisable keymaps will be available in the coming months.
I've added support for custom themes in the latest version.
Good idea! Right now you can change the system prompt in ctrl+o menu from the home page, and that will apply for the remainder of the session. It'll be set back to your config file prompt in the next session however.
Good idea!
This may come in the future but it's not a priority for me as I don't really use any multimodal stuff. Happy to accept contributions though!
Hi, there!
Nice project! Thank you for developing and maintaining it!
Maybe I missed something in the help, but is there a way to cancel an inference? If not, I think this could be really useful, specially when trying models locally (specially the big ones that may run very slowly).
Some suggestions (please feel free to ask me to open a separate issue for the ones you may be implemented):
Thanks again. Regards
The text was updated successfully, but these errors were encountered: