feat(code): switch fully to ollama as LLM provider

[frgfm]

This PR introduces the following modifications:

• adds ollama as LLM service provider
• drops usage of OpenAI in the community version
• adds script & results of latency benchmark on ollama models
• adds test cases for the chat route

[codecov]

Codecov Report

Attention: 2 lines in your changes are missing coverage. Please review.

Comparison is base (6bc7921) 82.59% compared to head (4ef800a) 86.09%.

Files	Patch %	Lines
src/app/services/ollama.py	80.00%	2 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #101      +/-   ##
==========================================
+ Coverage   82.59%   86.09%   +3.49%     
==========================================
  Files          29       29              
  Lines         971      906      -65     
==========================================
- Hits          802      780      -22     
+ Misses        169      126      -43     

Flag	Coverage Δ
unittests	86.09% <94.44%> (+3.49%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

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