Implement LiteLLM

[ahuang11]

Call 100+ LLMs using the OpenAI Input/Output Format
Translate inputs to provider's completion, embedding, and image_generation endpoints Consistent output, text responses will always be available at ['choices'][0]['message']['content']

But the primary motivation for me to add LiteLLM was because of https://docs.litellm.ai/docs/batches so we don't have to maintain a large portion of #1290.

But maybe we can just use Instructor...
https://python.useinstructor.com/cli/batch/#create-from-file

[codecov]

Codecov Report

Attention: Patch coverage is 30.12048% with 58 lines in your changes missing coverage. Please review.

Project coverage is 58.31%. Comparing base (2983a93) to head (bf4cb20).
Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
lumen/util.py	17.94%	32 Missing ⚠️
lumen/ai/llm.py	40.90%	26 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1294      +/-   ##
==========================================
- Coverage   58.44%   58.31%   -0.14%     
==========================================
  Files         114      114              
  Lines       18238    18297      +59     
==========================================
+ Hits        10660    10670      +10     
- Misses       7578     7627      +49     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.