Bugfix/broken azure config

[collijk]

Background

We introduced a reliance on setting openai module attributes a couple of months ago to verify model access. This was causing breakages in Azure usage not fixed by #4875 or #4098.

Known Issue: We have default fallbacks when gpt4 is not available (use gpt-3.5-turbo), but azure deployments can modify the names of models and there are no guarantees that a system will have gpt3.5 if it doesn't have gpt4. I think this is mostly a non-issue as someone using azure wants their model to fail on misconfiguration as this is most likely a user error.

Changes

• Pass in credentials when we check for model validity.
• Put azure resolution of --gpt3only and --gpt4only on the same path.

Documentation

Test Plan

CI

Manual testing of ./run.sh with no flags, with --gpt3only flag and with --gpt4only flag on an azure instance.

PR Quality Checklist

• My pull request is atomic and focuses on a single change.
• I have thoroughly tested my changes with multiple different prompts.
• I have considered potential risks and mitigations for my changes.
• I have documented my changes clearly and comprehensively.
• I have not snuck in any "extra" small tweaks changes.
• I have run the following commands against my code to ensure it passes our linters:

  black .
  isort .
  mypy
  autoflake --remove-all-unused-imports --recursive --ignore-init-module-imports --ignore-pass-after-docstring autogpt tests --in-place

[netlify]

✅ Deploy Preview for auto-gpt-docs canceled.

Name	Link
🔨 Latest commit	e590c1e
🔍 Latest deploy log	https://app.netlify.com/sites/auto-gpt-docs/deploys/64a897cd3b21fd0008a17cde

[collijk]

@jayden5744 This should hopefully address your issues.