Feat/litellm

[tqtensor]

What does this PR do?

This PR integrates LiteLLM to provide a unified interface for multiple Vision LLM providers. It simplifies configuration and expands model support while maintaining compatibility with existing implementations.

Key changes:

• Added support for LiteLLM proxy models, treating them as OpenAI models internally

• Replaced provider-specific configs (openai_config, gemini_config, ollama_config) with a universal provider_config parameter

• Fixed async/sync handling for better performance with concurrent processing

• Simplified worker calculation to focus on CPU cores

• Updated documentation with examples for the new unified API

• Addresses issue (#XXX)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Ran make lint and make format to handle lint / formatting issues.
• Ran make test to run relevant tests scripts.
• Read the contributor guidelines.
• Wrote necessary unit or integration tests.