Skip to content

README.md

Latest commit

 

History

History
59 lines (40 loc) · 1.87 KB

README.md

File metadata and controls

59 lines (40 loc) · 1.87 KB

MOVED TO InMeal

Generative Recipe Images

Generative Recipes is released under the MIT license Generative Recipes is deployed using Docker

A simple REST Microservice abstracting the consumption of a generative model for images of a recipe. This provides stylistic representations of the recipe prompt and implements some prod-ready features.

🤖 Features

This is still a work in progress but currently supports simple recipe and ingredient management.

The main goal of this project is providing an easy to deploy, maintain, and consumable model. The model aims to provide consistently styled results, so that they are themed. These are also stylistic, and not a pure representation of the real recipe.

  • Safe: Filtered prompts and tailoured outputs to avoid extranous uses...
  • Documentation: OpenAPI standard and code-first design.
  • Fast: uses FastAPI for a fast development + build + deploy time.

Getting started

To run the app in development mode,

source ./bin/activate
uvicorn app.main:app --reload

Then checkout the OpenAPI docs, [http://127.0.0.1:8000/docs].

Build the Docker image

To build the service using Docker compose run,

docker compose up

or to build without compose,

docker build -t testImage .
docker run -d --name testContainer -p 80:80 testImage

test it by visiting the ping-pong test URL

👀 Examples

// TODO