Mood Mixer

drink recommendation for matcha latte

Inspiration

In the winters, we want warm drinks. In the summers, we want cool drinks. But with this program, we don't even need to think about what drink to make next!

What it does

We built the front-end with HTML, CSS, and JavaScript, supported by a robust back-end powered by a Spring Boot Java server. Natural language processing is handled by the Google GenAI API, which works in tandem with the extensive recipe collection from TheCocktailDB.

How we built it

The front-end website uses basic html/css/js, while the backend is handled with a spring-boot Java server. The natural language processing was handled via google genAI API, while the drink database is from TheCocktailDB.

Challenges we ran into

One of our biggest hurdles was prompt engineering—fine-tuning our requests to get consistent, accurate responses from the Gemini API. We also tackled the classic challenges of parsing data from multiple API calls and establishing a seamless connection between our front-end and back-end services.

Accomplishments that we're proud of

We're proud of the fact that it actually works! We successfully created a smooth data pipeline that flows from the user's input on the front-end, through our back-end logic, and back to the user with a perfect recommendation.

What we learned

Integration is one of the hardest parts of software development. We learned that while you might be able to "vibe-code" a million tiktok clones, the real challenge comes from making multiple complex systems talk to each other. Navigating the headaches of server integrations taught us invaluable lessons about building robust, real-world software.