Make llm model an argument

[edcohen08]

Background

Targets #942, removes the hardcoded setting for chat completion to use the fast llm model and adds a chat model env variable you can use for specifying which model for chat completion, defaulting to the fast_llm_model setting

This is just the first step towards allowing users to configure what commands use which model but at least not they can run autogpt on gpt4

Changes

Allows user to set which model they want to use for chat completion

Documentation

Test Plan

I don't actually have gpt-4 access but the test suite runs

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

[github-actions[bot]]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[github-actions[bot]]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[codecov[bot]]

Codecov Report

Patch coverage: 55.55% and project coverage change: -7.39 :warning:

Comparison is base (2b5852f) 45.09% compared to head (ec481f1) 37.71%.

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #2621      +/-   ##
==========================================
- Coverage   45.09%   37.71%   -7.39%     
==========================================
  Files          60       60              
  Lines        2856     2861       +5     
  Branches      472      472              
==========================================
- Hits         1288     1079     -209     
- Misses       1463     1720     +257     
+ Partials      105       62      -43     

Impacted Files	Coverage Δ
autogpt/agent/agent.py	12.74% <ø> (-28.44%)	:arrow_down:
autogpt/chat.py	24.63% <ø> (-45.37%)	:arrow_down:
autogpt/configurator.py	0.00% <0.00%> (ø)
autogpt/app.py	29.59% <100.00%> (-17.35%)	:arrow_down:
autogpt/config/config.py	74.66% <100.00%> (-0.68%)	:arrow_down:

... and 12 files with indirect coverage changes

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.

[github-actions[bot]]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[p-i-]

This is a mass message from the AutoGPT core team. Our apologies for the ongoing delay in processing PRs. This is because we are re-architecting the AutoGPT core!

For more details (and for infor on joining our Discord), please refer to: https://github.com/Significant-Gravitas/Auto-GPT/wiki/Architecting

[Boostrix]

Related #4229

[Pwuts]

Is this PR still relevant, now that OpenAI has announced deprecation/deprioritization of their traditional Completion models, in favor of ChatCompletion? https://openai.com/blog/gpt-4-api-general-availability#:~:text=As%20part%20of%20our%20increased%20investment,new%20models%20using%20the%20Completions%20API.