Closed nickanderson closed 8 months ago
Are you using gptel in a dedicated buffer (with M-x gptel
) or in regular buffers?
Regular buffers.
Set the default value of gptel-model
instead, with
(setq-default gptel-model "mistral-7b-openorca.Q4_K_M.gguf")
Let me know if the bug persists?
(Additionally, there is an issue with API key entry prompts in dedicated buffers that I'll fix soon. This shouldn't be affecting you.)
Ok, I'll give that a shot and report back.
Thanks.
I have not seen this since using setq-default to set the gptel-model, so I will close this for now and re-open if I see it again.
I occasionally get a message
No 'gptel-api-key' found in the auth source
even though I am only using GPT4All.I see the message when I run
gptel-send
. While it doesn't always do it, once it starts it does not seem to stop until I switch models.