The tool I made works with local data -- it analyzes your Google search history from a file on your disk. You can filter it by specifying a topic, which is then matched semantically against the search queries in your history using the word vectors. Given the sensitive nature of this data, I felt it important not to send these topic queries (nor any of the raw search history queries) to a remote server. I can also imagine using the word vectors to do a topic clustering of the search history.
How does that improve privacy in this case? The sort of queries that can be made against a word vector model, and only a word vector model, are pretty trivial.
