DRIFT (Dynamic Reasoning in Inference with Flexible Traversal) search is a novel technique introduced by Microsoft that combines global and local search by using hypothetical document embedding to generate a document based on the query that is then embedded and used to retrieve similar community reports, followed by generation of an initial answer and follow-up questions, then local search on each follow-up question with relevance scoring to create a pseudo-refinement loop.

factualpending

Speaker

Adam Lucik

Evidence Quote

“drift search is a pretty cool combination of both Global and local search it is going to include Community Information within the search process when a user actually implements a query it is going to go through hypothetical document embedding to generate a hypothetical document based on that query that hypothetical document instead of the query is going to be the one that's actually embedded to run the first stage of retrieval then from all of these retrieved Community reports what we do is we generate an initial answer to the query along with follow-up questions then for each of the follow-up questions we switch over to our local search”

Source

Knowledge Graph or Vector Database… Which is Better?— Adam Lucek
Created: 8/11/2026, 7:35:39 AM

Your notes

Loading notes...