Create a LiteLLM layer for handling requests to different inference backends

[debabratamishra]

Currently the application supports Ollama backend only. Instead, the call needs to be routed to LiteLLM which will enable interaction across multiple backends.
Important resources to look at :

• LiteLLM Swagger UI : https://litellm-api.up.railway.app
• Ollama Docs : https://docs.litellm.ai/docs/providers/ollama