fix: use singleton in llama_cpp

[dartpain]

• What kind of change does this PR introduce? (Bug fix, feature, docs update, ...)

• Why was this change needed? (You can also link to an open issue here)

• Other information:

[vercel]

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

Name	Status	Preview	Comments	Updated (UTC)
docs-gpt	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Jun 25, 2024 1:41pm
nextra-docsgpt	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Jun 25, 2024 1:41pm

[codecov]

Codecov Report

Attention: Patch coverage is 38.09524% with 13 lines in your changes missing coverage. Please review.

Project coverage is 21.83%. Comparing base (651eb33) to head (5aa8871).
Report is 7 commits behind head on main.

Files	Patch %	Lines
application/llm/llama_cpp.py	38.09%	13 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1013      +/-   ##
==========================================
+ Coverage   21.69%   21.83%   +0.14%     
==========================================
  Files          80       80              
  Lines        3632     3645      +13     
==========================================
+ Hits          788      796       +8     
- Misses       2844     2849       +5     

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

[starkgate]

@dartpain Looks good, thanks! Much cleaner than my proposal, too. This will be a great improvement for many people.