Feel like this is very basic, but cant quite get it to work - how can I see exactly the prompt that is actually sent to the LLM - that is, the exact system message and user message wth all the docs filled in, etc. Something is going wrong and I need to debug it and i wan tto start by just verifying the exact string sent to the LLM

Is there anyway to chat directly with dosu bot on GitHub? Or any rag chat over the llamaindex docs generally?

I see something like node.excluded_llm_metadata_keys = ["vector"] will work for that one node... but I wan to this to apply to all nodes coming from OS at all times. and I dotn want to blacklist like this, Id like to whitelist. Something like; forallnodes.included_llm_metadata_keys = None without the loop