How do I set the default model to a non OpenAI backend?

[nickanderson]

For example, say I am using both Ollama and GPT4All Desktop each with a couple of models available:

(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_0.gguf"
            "orca-mini-3b-gguf2-q4_0.gguf"
            )) ;Available models

(gptel-make-ollama
 "Ollama"                               ;Any name of your choosing
 :host "localhost:11434"                ;Where it's running
 :models '("zephyr:latest" "mistral:latest")            ;Installed models
 :stream t)                             ;Stream responses

How would I specify Ollmama:zephyr:latest or GPT4All:orca-mini-3b-gguf2-q4_0.gguf as the default backend and model?

If I set like this:

(setq-default gptel-model "Ollama:zephyr:latest")

Then gptel-menu shows the selected model as ChatGPT:Ollama:zephyr:latest

If I set like this:

(setq-default gptel-model "zephyr:latest")

Then gptel-menu shows the selected model as ChatGPT:zephyr:latest.

If I use gptel-menu to set the model interactively I can select Ollama and then select zephyr:latest or minstral:latest, at which point gptel-menu shows Ollama:zephyr:latest or Ollama:minstral:latest. But I don't see how to configure it so that the default works.

[nickanderson]

@nickanderson read the docs more thoroughly ...

https://github.com/karthink/gptel/blob/0192fa07f3f8d2d032b71acd1fae12755207dd76/README.org#ollama

Set this as the default value of gptel-backend:

;; OPTIONAL configuration
(setq-default gptel-model "mistral:latest" ;Pick your default model
              gptel-backend (gptel-make-gpt4all "Ollama" :host ...))

So, it appears that this does what I was looking for:

        (setq-default gptel-backend
                      (gptel-make-ollama
                       "Ollama"                               ;Any name of your choosing
                       :host "localhost:11434"                ;Where it's running
                       :models '("zephyr:latest" "mistral:latest")            ;Installed models
                       :stream t)                             ;Stream responses
                      )
        (setq-default gptel-model "zephyr:latest")