The community member has ingested 1k documents and knows that the response to their query is specifically in one of those documents, but it is only ranked 14th in the get_formatted_sources output, which they feel is not a good ranking. They are asking for methods to get the response without relying on large numbers of top-k similarity results. Another community member suggests looking into using a composable index instead of a single vector index, as it may better direct the query to the correct data. They provide a link to more details in a new FAQ.
Another Q! I have 1k docs ingested. I know that the response of my query is in more than 1 doc, but specifically in one document. However when I look for it in get_formatted_sources i see that’s in 14th position (ordered by similarity, that imo works poorly). Except for writing better the query, which other methods may I apply to get that response without put similarity top k with large numbers?
