Ok, I'm double dipping. Another problem I'm trying to solve is: I've got a database of several hundred interesting conversation questions that I've collected over the years. Essentially just strings, though I've attempted to categorize them, rank them, and add other metadata. I'd like to figure out a way to sort them or dedupe them based on semantic similarity, but I'm not sure how to determine semantic similarity without painstakingly going through and manually looking for similar questions. Any suggestions on how to solve this would be welcome.