Building an AI Cooking Helper with Django

Set up the core Django project and a dedicated recipes app, then model the domain your API will rely on (recipes, ingredients, and ratings). You’ll configure settings (SQLite, CORS, static files), register models in the admin, and add a couple of CLI scripts to seed data and safely wipe/reset tables for local development.

Implement the first set of read-focused API endpoints for your recipe database. You’ll add consistent JSON serialization, pagination, and robust validation/error handling, then expand into recipe discovery features like filtering by ingredients, returning steps as an array, and selecting random or top-rated recipes.

Add an LLM layer to generate and extract structured recipes. You’ll create a lightweight prompt templating system, integrate OpenAI calls behind a small wrapper, and expose an endpoint that generates recipes from ingredients. You’ll also build a CLI workflow to extract a clean recipe from messy HTML and store it into your Django database.