NudgeBite

NudgeBite is a lightweight, context-aware smart nutrition assistant web application that helps users make better food decisions through contextual logic and behavioral nudges.

Features

• Smart Recommendations: Suggests food based on your goal (Weight Loss, Muscle Gain, Balanced Health) and hunger level.
• Context Awareness: Automatically detects the time of day and recommends appropriate meals (Breakfast, Lunch, Dinner, Snack).
• Behavioral Nudges: Each recommendation comes with a smart, actionable nudge to improve your eating habits.
• Smart Swaps: Analyzes available ingredients (e.g., rice, eggs) to recommend optimal healthy pairings.
• Habit Tracking: Tracks your recent choices and provides insights on your eating patterns.
• Premium UI: Features a vibrant, modern glassmorphism design with a responsive layout.

How Recommendation Logic Works

The recommendation engine uses a 0-100 "Health Score" system.

1. Filtering: Foods are first filtered by the time of day (e.g., Breakfast items in the morning).
2. Scoring:
   • Goal based: Low-calorie foods score higher for "Weight Loss", high-protein foods score higher for "Muscle Gain".
   • Hunger based: If hunger is high, lighter meals are penalized to ensure the user gets a filling recommendation.
   • Swaps: If the user inputs an ingredient like "rice", meals containing rice or pairings (like Dal) receive a massive score boost.
3. Nudging: Nudge messages are appended dynamically based on the food's nutritional profile and the user's goal.
4. Sorting: The top 4 highest scoring foods are displayed to the user.

Project Structure

• app.py: Flask backend, dummy dataset, and recommendation logic.
• templates/index.html: Main HTML layout.
• static/css/style.css: Modern CSS styling.
• static/js/app.js: Frontend logic for fetching API and DOM updates.
• Dockerfile: Containerization setup for deployment.

Setup Instructions

Run Locally (Python)

1. Ensure Python 3.9+ is installed.
2. Install dependencies:

   pip install -r requirements.txt

3. Run the Flask server:

   python app.py

4. Access the app at http://localhost:8080 (or http://127.0.0.1:8080).

Run Locally (Docker)

1. Build the Docker image:

   docker build -t nudgebite .

2. Run the container:

   docker run -p 8080:8080 nudgebite

Deploy to Google Cloud Run

1. Authenticate with Google Cloud:

   gcloud auth login
   gcloud config set project [YOUR_PROJECT_ID]

2. Build and deploy using gcloud run deploy:

   gcloud run deploy nudgebite --source . --region us-central1 --allow-unauthenticated

   Or using a pre-built image:

   gcloud builds submit --tag gcr.io/[YOUR_PROJECT_ID]/nudgebite
   gcloud run deploy nudgebite --image gcr.io/[YOUR_PROJECT_ID]/nudgebite --region us-central1 --allow-unauthenticated

How to Modify the Dataset

The dataset is an in-memory Python list located at the top of app.py. To add new foods, simply append a new dictionary to the FOODS list:

{
    "id": 15, 
    "name": "New Food", 
    "calories": 300, 
    "protein": 15, 
    "category": "Lunch", 
    "description": "Short description."
}

Restart the server for the changes to take effect.