also i found out that managing document updates is so hard in production, i have a client that very often they have new documents, and as for now it has been manual but later i want to make it in automatic fasion, still not sure what is the best way and best vector database to use to handle upadting old documents with new ones

Hi guys, i am using CondensePlusContextChatEngine should i initialise memory to be able to ask consecutive questions? I noticed in my previous versions i was not using any memory but i was able to ask consecutive questions, (however, only in my application and not my jupyternotebook)

i am asking this as i noticed in the case that i am using some of the more advance transformations the reponses are more halucinated, and my guess is as i am feding them to the reposne generation part as well!

its my question too! also if we add summary of document to each node, then how does it affect the retrieval and generation of reponse?

i am using langfuse and i am trying this example https://langfuse.com/docs/integrations/llama-index/example-python-instrumentation-module#custom-trace-properties, but still i dont see anything in my langfuse! i noticed currently its for us and eu regions and i am at Australia, do u guys think thats why?

Hi guys, if i have a recursive folder with indexes saved on them and use this line with parrent folder path, will i expect to see all the indexes merged in one right? # load multiple indices
indices = load_indices_from_storage(storage_context) # loads all indices
indices = load_indices_from_storage(
storage_context, index_ids=[index_id1, ...]
) # loads specific indices @Logan M

Hi guys, not sure what is wrong, when i am trying this CondensePlusContextChatEngine when the user asks the second question it stays in a loop for every, so only user can ask one question. I dont have this problem, when i use index.as_chat_engine any reason what might be the problem? @Logan M

Hi guys has anyone know how can we use advanced RAG with chat_engine? as I noticed i can do lots of advanced RAG with query engine, but not chat_engine. Or equivalently how easy is that to convert an advanced query engine to a chat engine?