Working with ChatGPT Functions on Heroku

Summary

Menu Maker is a Node.js web application that turns user-supplied ingredients into a dish name, fine-dining description, ingredient list, and recipe. Its React front end communicates with an Express back end, which adds prompt instructions and sends the request to OpenAI’s Chat Completions API. The application uses ChatGPT’s function calling feature to define an updateDish function with structured JSON fields for the title, description, ingredients, and recipe, so parsed arguments can update React state directly. The GitHub-hosted Node.js monorepo is deployed to Heroku, where an OPENAI_API_KEY config var authenticates requests, an optional CHATGPT_MODEL selects the model, and Heroku runs yarn build and yarn start.

Takeaways

1. 1

   ChatGPT function calling provides a formatted response that code can feed into a custom function; it does not invoke the function itself.

2. 2

   The updateDish schema requires title, description, ingredients, and recipe fields, with ingredients represented as objects containing an ingredient name and amount.

3. 3

   Heroku deployment uses OPENAI_API_KEY as a config var, optionally reads CHATGPT_MODEL, and runs yarn build followed by yarn start; dynos can be scaled to zero when unused.