Organize all the llm stuff into a subpackage

[collijk]

Background

Our interaction with LLMs is sprawling across the repo right now and we have many requests to do things like add new llm backends. I strongly recommend we consolidate and organize the existing code before adding new features. I have much of this work done, and this is the first PR to start us on the path. This PR only moves files. This helps preserve git history from all of our diligent contributors and maintainers and will make later diffs interpretable.

Changes

• Moves all LLM related modules into an llm subpackage.

Documentation

N/A

Test Plan

All tests update to point at new module import paths.

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

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Ignored Deployment

Name	Status	Preview	Comments	Updated (UTC)
docs	⬜️ Ignored (Inspect)			Apr 28, 2023 6:31pm

[codecov]

Codecov Report

Patch coverage: 80.00% and no project coverage change.

Comparison is base (ee4043a) 56.46% compared to head (b8dcc03) 56.46%.

Additional details and impacted files

@@           Coverage Diff           @@
##           master    #3436   +/-   ##
=======================================
  Coverage   56.46%   56.46%           
=======================================
  Files          65       66    +1     
  Lines        3018     3018           
  Branches      507      507           
=======================================
  Hits         1704     1704           
  Misses       1175     1175           
  Partials      139      139           

Impacted Files	Coverage Δ
autogpt/commands/analyze_code.py	0.00% <0.00%> (ø)
autogpt/commands/improve_code.py	0.00% <0.00%> (ø)
autogpt/commands/write_tests.py	0.00% <0.00%> (ø)
autogpt/llm/modelsinfo.py	100.00% <ø> (ø)
autogpt/llm/token_counter.py	94.11% <ø> (ø)
autogpt/logs.py	80.29% <ø> (-0.29%)	⬇️
autogpt/memory/milvus.py	3.38% <0.00%> (ø)
autogpt/memory/weaviate.py	1.63% <0.00%> (ø)
autogpt/llm/chat.py	65.51% <85.71%> (ø)
autogpt/agent/agent.py	45.00% <100.00%> (-0.40%)	⬇️
... and 11 more

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