No 'gptel-api-key' found in the auth source when using GPT4All

[nickanderson]

I occasionally get a message No 'gptel-api-key' found in the auth source even though I am only using GPT4All.

  (gptel-make-gpt4all
   "GPT4All"                              ;Name of your choosing
   :protocol "http"
   :host "localhost:4891"                 ;Where it's running
   :models '( "mistral-7b-instruct-v0.1.Q4_0.gguf"
              "mistral-7b-openorca.Q4_K_M.gguf"
              )) ;Available models
  ;; (setq gptel-model "mistral-7b-instruct-v0.1.Q4_0.gguf")
  (setq gptel-model "mistral-7b-openorca.Q4_K_M.gguf")
  (setq-default gptel-max-tokens 800)
  (setq gptel-directives   '((default . "You are a Nexus, Nick Anderson's helpful assistant. You have dry humor.")
                            (programming . "You are a large language model and a careful programmer. Provide code and only code as output without any additional text, prompt or note.")
                            (writing . "You are a large language model and a writing assistant. Respond concisely.")
                            (chat . "You are a large language model and a conversation partner. Respond concisely.")))

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.

[karthink]

Are you using gptel in a dedicated buffer (with M-x gptel) or in regular buffers?

[nickanderson]

Regular buffers.

[karthink]

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.)

[nickanderson]

Ok, I'll give that a shot and report back.

Thanks.

[nickanderson]

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.