Hi, in our org the LLM api_key expires every hour. We load a bunch of indices in memory and then run queries on them. So for the first hour everything works. But once token expires we get 401. We refresh the api_key through Settings.llm and Settings.embed_model but it does not help - still getting 401 expired token when querying.

To fix this we tried to recreate query engines after the token is refreshed I can see that llm.api_key contains new token, but retriever._embed_model.api_key is old. Which I suspect causing this issue. From what I can see in code .as_query_engine factory method resolves llm but it does not resolve embed_model. Is there a reason for that?

What is the right way to refresh the api_key for existing loaded index / query engine?

Hi, I am working on RAG system to provide insights from the large number of jira tickets. I use llama_index DocumentSummaryIndex for this.
So I store ticket data in a form of resolved_date,key,product,description in document per each date.
Summarization works pretty well for a general questions (e.g. provide common topics of incidents).
But is there a way for RAG to be able to provide insights based on:

• the tickets quantity (e.g. provide number of tickets for a particular topic/category)
• the dates (e.g. what is the month-to-month trend for a particular ticket topic/category)?

Is there a way to achieve this or at least what is the direction I should be looking at?

Hi, got more of a general question. So there are at least 3 ways to work with summary based RAG in llama_index:

• SummaryExtractor
• SummaryIndex
• DocumentSummaryIndex

What is the main difference in using those? Can someone provide some examples of use cases for each?