Inspiration
MixMaster was inspired by the world of mixology and the desire to reduce the prep time it takes to make the best of limited resources. We wanted to create a platform that demonstrates the importance of AI in terms of waste management through a fun application. It not only shares cocktail and mocktail recipes, but also provides personalized recommendations.
How we built it
MixMaster was built using a combination of HTML, CSS, and React for the frontend, while Django and FastAPI handle the backend. The core business logic is written in Pyton, ensuring smooth data management and interaction. Gemini and NLX were integrated to enhance the conversational capabilities, providing personalized drink recommendations for the user.
Challenges we ran into
The challenges we ran into were actually creating an image recognition and deliverance system for the AI. Sometimes it would not recognize whether the drink shown was empty or not, and mislabeled items frequently.
Accomplishments that we're proud of
We were able to create a functioning website system from scratch, with account creation, login, and reset features. Integrating the AI into this application was a great achievement.
What we learned
We learned how to implement Google's AI, Gemini into our own algorithmic program. It is a new experience for all of us to implement AI and as well as using React, Fast API, Flask, and Django, all mixed together to form and create our front-end and back-end.
What's next for MixMaster
MixMaster will incorporate a more seamless human-to-AI interaction in the future. This includes using NLX to develop speech-to-text, and text-to-speech integration so that a person can have a seamless conversation, while creating the drink of their choice.
Log in or sign up for Devpost to join the conversation.