The wonderful chatgpt-shell package by Xenodium lets you interact with the gpt-3.5 and gpt-4 APIs in emacs via a handy shell built on top of comint-mode. It also integrates well with org-mode.

I find that I tend to re-use a few prompt patterns for specific tasks. Yasnippet provides a great way to create prompt templates made up of some fixed component with placeholders for user input. I can easily insert these prompt templates when working with chatgpt-shell to gain easy access to reusable, task-specific prompts. This post describes how to start using Yasnippet for prompt templates for use with chatgpt-shell.

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.

For the basics of working with the ChatGPT API, check out part 1.

This brief post shows the basics of using the Julia HTTP library to interact with the OpenAI ChatGPT API, which was made public a few days ago. This post will only include the minimum necessary detail for getting started with the API. Future posts will go into a little more detail on how to send message histories and engage more interactively with the API.

The latest release of Denote (by the inimitable Protesilaos Stavrou) introduced support for custom file types in addition to the defaults, Org, Markdown+YAML,