Inspiration
The inspiration for NutriJuzz came from the growing need for people to understand their nutritional intake. We wanted to create a simple app that leverages AI to provide instant, customize, precise nutritional information, and making it accessible to everyone.
What it does
NutriJuzz is an app that counts the nutrition content of your food. By simply inputting the foods you eat, NutriJuzz provides detailed nutritional information, including calories, macronutrients, vitamins, and minerals.
How we built it
We build Nutrijuzz using combination of Snowflake Arctic (latest open-source LLM from Snowflake) and Streamlit. We combined these technology to create NutriJuzz. Our development process include:
- AI-Integration: Snowflake Arctic is a new technology, hence we need to learn about it first.
- User-Interface Design: We design simple and still has the functionality for NutriJuzz. This simple design will help user count their nutrition instantly.
Challenges we ran into
Building NutriJuzz was not without its challenges. Some of the key obstacles we faced included:
- Limited Time: We know about this hackaton information 2 days before deadline. At this range of time we still have little knowledge about Streamlit and Snowflake Arctic. So we speed up our learning about create app utilizing LLM and Streamlit.
- New Knowledge: Snowflake Arctic and Streamlit is new technology for us, so we need to putting in extra effort for building it, But We Can!!
Accomplishments that we're proud of
We built the first AI powered app using Streamlit and Snowflake Arctic.
What we learned
- I learn how to use LLM from replicate.
- How to create a good UI design with streamlit.
- Utilizing Snowflake Arctic
- Hope I could also learn how to tune the LLM, but for this I need extra miles.
What's next for NutriJuzz
- Advanced Features: Introduce new features such as meal planning, integration with fitness trackers, and more detailed nutrient analysis.
- Online Store: Actually at very first of this Idea is I build online shop about juice. User could choose whatever fruit or veggie from the web, they will count the nutrition and then will order that menu customized by themselves.
Built With
- arctic
- python
- streamlit
Log in or sign up for Devpost to join the conversation.