[Backend] Lazy Model Initialization & Fault-Tolerant Startup (#302)

[j4b3-21]

This PR implements lazy, thread-safe initialization for embedding and LLM models to improve API startup reliability and reduce cold-start latency.

Previously, models were loaded during import, causing slow startup and failures when models were unavailable.
Now, models initialize only on first use and fallback gracefully on failure.A minor fix was done to footer.jelly to match the root name with main.tsx

Changes

•	Added runtime_models.py for lazy model loading
•	Implemented thread-safe cached getters
•	Added graceful fallback when models fail
•	Guarded retrieval paths to prevent crashes
•	Removed heavy initialization at import time
•	Updated footer.jelly root ID from chatbot-root → root to match main.tsx

Testing Done

•	API startup without models → successful
•	First request → lazy initialization works
•	Concurrent requests → single initialization, cached reuse
•	Simulated failure → fallback response returned
•	Verified UI loads correctly after root ID change (screenshots attached)

Files Modified

•	chat_service.py
•	tools.py
•	embedding_model.py
•	llama_cpp_provider.py
•	main.py
•	footer.jelly

New file:
• runtime_models.py

##Related Issue
Closes #302

Submitter checklist

• Make sure you are opening from a topic/feature/bugfix branch (right side) and not your main branch!
• Ensure that the pull request title represents the desired changelog entry
• Please describe what you did
• Link to relevant issues in GitHub or Jira
• Link to relevant pull requests, esp. upstream and downstream changes
• Ensure you have provided tests that demonstrate

[j4b3-21]

To fix the linting issue ,
i would have to run pylint . on the entire chatbot-core right??

edit-
i ran the pylint . command and fixed all the issues

[berviantoleo]

To fix the linting issue ,
i would have to run pylint . on the entire chatbot-core right??

edit-
i ran the pylint . command and fixed all the issues

Yes

[j4b3-21]

To fix the linting issue ,
i would have to run pylint . on the entire chatbot-core right??
edit-
i ran the pylint . command and fixed all the issues

Yes

yes i did that and updated the pr

[berviantoleo]

I don't think we should raise Error

[berviantoleo]

Why you ignore this pylint?

[berviantoleo]

Define this on top of the file as a var.

[berviantoleo]

Define on top