My name is Dan. I am a data scientist at bit.io, which offers the fastest way to get a cloud PostgreSQL database. In my role, I use bit.io databases to manage the data in various data science research projects. I've analyzed data and written about topics such as methane emissions , Bayesian statistics , labor turnover , the size of the House of Representatives , and much more. Read more…
Since this start of this year, I've been working on and writing about AI tools for working with Postgres databases. Most of this work has involved finding different ways to integrate ChatGPT (and previously Codex) with other tools and workflows. I wanted to collect and share some of that writing here, as it's related to a lot of the other things I write about on my personal blog.
One of the things that makes working with the ChatGPT API a little different from working with, e.g., the davinci-text-003 model api is the need to maintain the history of a given chat session. A Julia Struct containing the chat history, coupled with a function that acts on that Struct, provides a good way to work with the ChatGPT API.