feat: Part 2 - Add custom LLM inference class

[ishaansehgal99]

Reason for Change:
This series of PR will integrate llamaindex RAG service for Kaito.

This PR contains the custom LLM inference class for llamaindex. We need this class because we use custom HTTP endpoint or OpenAI API for handling LLM requests so we need a custom LLM inference class.

https://docs.llamaindex.ai/en/stable/module_guides/models/llms/usage_custom/#example-using-a-custom-llm-model-advanced

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 54.49%. Comparing base (5c30038) to head (78548f3).
Report is 31 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #630      +/-   ##
==========================================
- Coverage   58.18%   54.49%   -3.69%     
==========================================
  Files          30       34       +4     
  Lines        2987     3257     +270     
==========================================
+ Hits         1738     1775      +37     
- Misses       1149     1376     +227     
- Partials      100      106       +6     

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