Here’s some of the projects I’ve been working on.
I’m currently working on a method for automating the generation of high-quality, in-domain text-to-SQL training data for any database. The goal is to enable users to train models on their own data and better enable them answer questions using their databases. Paper and code coming soon.
A data platform that uses analytics augmented generation to write comprehensive reports grounded by your data.
Mim is an information retrieval system used for answering complex questions over large document corpora.
