AllergyIQ

Inspiration

AllergyIQ was born from a collective recognition of the complex challenges individuals face when navigating dietary restrictions that intersect health requirements and cultural practices. The team identified a critical need for a comprehensive solution that helps people manage their unique dietary needs without compromising health or cultural identity.

What it does

AllergyIQ is an AI-driven dietary detection companion that:

• Scans ingredients through text, URLs, or photos
• Instantly identifies potential allergens and dietary restrictions
• Provides comprehensive analysis across multiple dimensions:
  • Medical Requirements
  • Cultural Preferences
  • Nutritional Balance

Users can check their meals against health conditions (like diabetes) and cultural guidelines (such as Halal) with a single scan, ensuring safer and more informed food choices.

How We Built It

The project was developed using a robust tech stack:

• Frontend: React, Vite, TypeScript
• Backend: MongoDB
• Cloud Infrastructure: Google Cloud
• AI Integration: Google's Gemini API

The team implemented a custom response formatter to standardize API outputs and ensure seamless integration with the MongoDB database. The development process involved overcoming complex technical challenges, particularly in AI and database integration.

Challenges We Encountered

The most significant challenge was MongoDB-Gemini API Integration. The development team faced:

• Inconsistent JSON structures from Gemini's ingredient analysis
• Missing required fields in allergen classification responses
• Nested arrays incompatible with the MongoDB schema

To address these issues, the team:

• Developed a custom response formatter
• Implemented robust error handling
• Created flexible data parsing mechanisms
• Ensured consistent data validation across API responses

Accomplishments

The team is proud of:

• Successfully integrating AI technology with complex dietary analysis
• Creating a solution that respects both health and cultural dietary needs
• Developing a robust, flexible system that handles diverse input methods
• Overcoming significant technical integration challenges
• Building a tool that can potentially improve users' health outcomes and dietary choices

Key Learning Outcomes

Through the project, the team gained insights into:

• Advanced API integration techniques
• Complex data parsing and validation
• Importance of flexible system architecture
• Balancing technical complexity with user-friendly design
• Collaborative problem-solving in distributed team environments

Future of AllergyIQ

The team plans to:

• Expand cultural and dietary restriction databases
• Improve AI accuracy and response parsing
• Develop more comprehensive nutritional analysis
• Create personalized dietary recommendation features
• Enhance user interface and experience
• Explore potential partnerships with nutritionists and health organizations

Built With

• google-gemini
• google-vision-api
• mongodb
• node.js
• react
• typescript