Ryan Lee

i dont think that is sufficient because they can take all your session replay hours without your consent

Why is this closed?

+1

this is already avaliable from the select dropdown 

the chat engine example is kind of busted because chat engine doesnt allow for concurrency. it's chat memory is shared for all connections.

I think so because in their implementation its a shared memory buffer https://github.com/run-llama/llama_index/blob/4e8d3d8cabfea5a2289c01fb9d435a50cdb8c360/llama-index-core/llama_index/core/chat_engine/condense_plus_context.py#L244 it can still work but you'd have to create a new chat engine per room