The model: gpt-4 does not exist / fixing defaults in llm_utils.py

[Boostrix]

Duplicates

• I have searched the existing issues

Summary 💡

the defaults need to be adapted for people without access to GPT4 - or the corresponding functions won't work.
The default model for people without GPT4 access should be cfg.fast_llm_model and not cfg.smart_llm_model

It would probably make sense to check once during startup what model is available and then set up the default accordingly.
In general, GPT4 should only be a default setting once it is verified to be available.

Examples 🌈

No response

Motivation 🔦

No response

[konraddroeske]

Pull request: #4278