The community member is working on generating questions and answers from a large PDF file. They have created a vector index and are using the "tree_summarize" response mode. The community member is wondering if, without initializing a retriever, the system will fetch all the nodes and then apply the "tree_summarize" response mode by default.
In the comments, another community member states that the default behavior for a vector index (without setting anything) is to fetch the top 2 nodes and use the compact mode to answer the query.
So my usecase is that I need to generate questions and answers from a large pdf file. I have created a vector index on top of this document and am using "tree_summarize" as the response mode. But let's say If i don't initialize a retriever, will it by default get all the nodes and then apply the "tree_summarize" response mode?
