Github Models Support

[gs-101]

Github Models

Try, test, and deploy from a wide range of model types, sizes, and specializations.

I signed up to the beta to get an API key to use with this package.
I know their endpoint is "https://models.inference.ai.azure.com", but I'm not sure about the host (see setting up Azure).
Sorry if this isn't possible, but my brain lit up when I read VS Code and thought I could use with this.

In the curl example, a request is sent to "https://models.inference.ai.azure.com/chat/completions":

curl -X POST "https://models.inference.ai.azure.com/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $GITHUB_TOKEN" \
    -d '{
        "messages": [
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
                "content": "What is the capital of France?"
            },
            {
                "role": "assistant",
                "content": "The capital of France is Paris."
            },
            {
                "role": "user",
                "content": "What about Spain?"
            }
        ],
        "model": "gpt-4o"
    }'

[gs-101]

UPDATE: I got it! It was as simple as setting the host to "models.inference.ai.azure.com", and the endpoint to "/chat/completions/"!

(gptel-make-openai "Github Models"
  :host "models.inference.ai.azure.com"
  :endpoint "/chat/completions"
  :stream t
  :key "$GITHUB_TOKEN"
  :models '("gpt-4o"))

I'll open up a PR as soon as possible!