Updating the interface behaviour

[ahhany]

I am using research papers as my documents dataset, and usually it is a must to have more than 30 files to answer one question like comprehensive analysis for example.
Now, if the number is high in vectorstore.asRetriever(40) the interface shows "Request failed with status code 400" , also the interface can't handle large text like 1000 words for example.
Is there a way to change the interface to be similar to the chatgpt writing the response as it gets. and how can I get a detailed response from my files if the response should be an analysis not just a simple question?