L3-Sentence_window_retrieval: what re-ranked model in case of "text-embedding-ada-002"?

Short Course Q&A Building and Evaluating Advanced RAG Applications
1

In the L3-Sentence_window_retrieval, it’s used the ranking model “BAAI/bge-reranker-base” to evaluate the embedded model “bge-small-en-v1.5”.
For some reasons, I have to use GPT 3.5 Turbo and “text-embedding-ada-002”.

Then, what re-ranked model do you suggest to use to evaluate a chatbot based on OpenAI “text-embedding-ada-002” embedded model?
What is happen in terms of efficiency, if I still use BAAI/bge-reranker-base?

Thank you!
Cosma