Hi team, I had a quick question about the default LLM being used with gptindex. As per
As per https://gpt-index.readthedocs.io/en/latest/how_to/custom_llms.html, I understand it is da-vinci-003.
but is it still da-vinci vector indices and not the ada-002?

Hi, was hoping to get some direction about ComposableGraph concept as per https://gpt-index.readthedocs.io/en/latest/how_to/composability.html

In this example, a list index is constructed from 3 tree indices. the top level index (list index here) is fed into the ComposableGraph wrapper. my questions are:
a) query_configs is a list of configs. is this ordered in any manner (top-down manner or bottom-up)?
b) the example is using "index_struct_type": "tree" and "index_struct_type": "keyword_table".. should it not be a "list" instead of "keyword_table"?
c) can you share what is "recursive" in this?

and thank you for the awesome library! really appreciate all your efforts.