Fine Tunning gpt4o model with Prompt Engineering and RAG

Hi,

I want to fine tune gpt4o model with custom dataset in such way that model has to be also integrated with Retrieval Augmented Generation Mechanism. So how can i fine tune model with prompt engineering techniqueon on model gpt4o in such a way that fine tuned model can be integrated with RAG system as well during the inference. can you please answer in detail?