Inspiration
Every year billions of tonnes in food goes to waste, in Canada alone 47% of waste is at the household level and it's estimated that 60% is preventable. Also, people often face the daunting question, "What should I cook?" We aimed to solve both these problems with the creation of ReFridge.
What it does
ReFridge is an AI integrated food manager and recipe recommender that scans users fridges' through their phone cameras, and adds it to the ReFridgerator (Our database). User's can then keep track of the items they have on hand, and have recipes tailored to their database.
How we built it
We used Google gemini for computer vision and LLM prompting to gather data and suggest recipes. Our database was built using MongoDB, backended in NodeJS, and CSS,HTML, and JS for the frontend.
Challenges we ran into
Connecting Gemini to our backend application was far more difficult than initially anticipated. We also lost a day of coding due to a Saturday afternoon midterm. Additionally, our main front end developer had to leave us on Saturday evening.
Accomplishments that we're proud of
In spite of all these setbacks we were still able to create a fully functional project. One of our group members even learned CSS.
What we learned
Don't do a hackathon during midterm season.
What's next for Refridge
Follow us to find out.
Built With
- css3
- express.js
- gemini-api
- html5
- node.js
Log in or sign up for Devpost to join the conversation.