The production version is hosted here at goodreads-recommender.vercel.app
This project uses the OpenAI GPT-3 API (specifically, text-davinci-003) and Vercel Edge functions with streaming. It generates 5 book recommendations based on the form and user input, sends it to the GPT-3 API via a Vercel Edge function, then streams the response back to the application. The code was forked from this repo for cinema recommendations. All book data is collected from the Google Books public API.
An additional feature was added for extra personalization. A user can import their goodreads reading data after exporting it from goodreads. The recommended will then display the list of books the user is reading, has read, or wants to read. The user can then select up to 10 books that will be sent to GPT in order to further personalize the recommendations.
Credit for idea: Divide-By-0 from https://github.com/Divide-By-0/ideas-for-projects-people-would-use.
After cloning the repo, go to OpenAI to make an account and put your API key in a file called .env.
For example:
OPENAI_API_KEY=...
Then, run the application in the command line and it will be available at http://localhost:5173.
npm run dev