🔨 Scaffold for refactor

[ashwinvaidya17]

📝 Description

• llava runs locally through ollama
  

✨ Changes

Select what type of change your PR is:

• 🐞 Bug fix (non-breaking change which fixes an issue)
• 🔨 Refactor (non-breaking change which refactors the code base)
• 🚀 New feature (non-breaking change which adds functionality)
• 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
• 📚 Documentation update
• 🔒 Security update

✅ Checklist

Before you submit your pull request, please make sure you have completed the following steps:

• 📋 I have summarized my changes in the CHANGELOG and followed the guidelines for my type of change (skip for minor changes, documentation updates, and test enhancements).
• 📚 I have made the necessary updates to the documentation (if applicable).
• 🧪 I have written tests that support my changes and prove that my fix is effective or my feature works (if applicable).

For more information about code review checklists, see the Code Review Checklist.

[samet-akcay]

only two comments. Looking clean

[samet-akcay]

quite minor, but it would be good if backend could be str as well

[ashwinvaidya17]

I was thinking of an alternative where instead of the llm provider, the users can select the model, and based on it the model will select the right provider.

[samet-akcay]

VlmAd maybe, as Vlm might sound quite generic?