VectorStoreIndex of chunked documentation pages, how would I implement a "related pages" search where a filename (that is part of the index) is given as input and the filenames that are associated with semantically related chunks in the same index are returned as output? (The index was created with filename_as_id=True.)response = query_engine.query(query_str) print(response.source_nodes[0].node.ref_doc_id)
query_str when it's the whole doc (and all its chunks) that I want to compare to all the other docs (and all their chunks) in the index. Maybe I should just use the title of the doc as the query or a summary of the doc?