Try upping similarity top k during the

The response quality got worse through that unfortunately. How can the system fetch information from other nodes when similarity_top_k=1 (default). Im using a vectoindex, mode=default and response_mode=default. It seems to definately include other nodes but i cannot see them in the results.

If you're searching a vector index, its likely not retrieving the "correct" node in the first try because your prompt doesn't have a high enough vector similarity to the material you're trying to retrieve

You can either allow gpt_index to search over more nodes (by increasing top_k) or you can make a better prompt

response_mode=tree_summarize will touch more nodes but will be slower and more expensive in terms of LLM calls to execute

thanks, makes sense will try!