An AI-Powered Kitchen and Health Management Platform
Intelligent recipe generation, comprehensive meal tracking, and personalized nutrition analysis powered by advanced Retrieval-Augmented Generation technology.
Modern households face significant challenges in daily meal preparation and nutrition management:
- Meal Planning Inefficiency — Difficulty in creating recipes from available ingredients
- Resource Waste — Food spoilage due to inadequate planning and utilization
- Nutritional Awareness Gap — Limited access to affordable, personalized dietary guidance
Chuk implements Retrieval-Augmented Generation (RAG) architecture to address these challenges through:
- Intelligent Recipe Generation — Dynamic recipe creation based on available ingredients
- Natural Language Processing — Intuitive meal logging without complex data entry
- Personalized Health Analytics — Multi-tier nutritional analysis with actionable insights
The platform delivers accurate, culturally-aware recipe recommendations paired with comprehensive nutrition tracking and analysis.
- AI-Powered Recipe Generation — Contextual recipe creation from user-specified ingredients
- Multi-Cuisine Database — Comprehensive collection spanning global and regional cuisines, including authentic Nepali dishes
- Category-Based Navigation — Structured browsing by meal type, cuisine, and dietary requirements
- Natural Language Meal Logging — Conversational input system for effortless data entry
- Multi-Tier Analysis Engine — weekly, and monthly nutritional insights
- Personalized Recommendations — Goal-oriented guidance based on individual health profiles
- Localized Recipe Recognition — Specialized support for traditional and regional cuisines
- Dietary Restriction Compliance — Automatic filtering for vegetarian, vegan, and allergen-free options
- Profile-Driven Customization — Adaptive recommendations based on age, weight, activity level, and health objectives
Backend Framework: Django 5.2 with Django REST Framework
AI Integration: Google Gemini 2.5 Flash API
Data Persistence: SQLite (Development) | PostgreSQL (Production)
Frontend: Django Template Engine, Tailwind CSS, Chart.js
Caching Layer: Django Cache Framework
API Architecture: RESTful design with comprehensive endpoint coverage
Retrieval-Based Grounding Personalization (RAG) — A proprietary approach that queries the recipe database prior to AI generation, ensuring contextually accurate and culturally appropriate recipe recommendations while minimizing hallucination risks inherent in pure language model outputs.
- Python 3.12 or higher
- pip package manager
- Virtual environment (recommended)
- Git version control
# Clone the repository
git clone https://github.com/yourusername/chuk.git
cd chuk
# Create and activate virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Execute database migrations
python manage.py migrate
# Create administrative user (optional)
python manage.py createsuperuser
# Launch development server
python manage.py runserverCreate a .env file in the project root directory with the following variables:
SECRET_KEY=your-secret-key-here
GEMINI_API_KEY=your-gemini-api-key
DEBUG=True
ALLOWED_HOSTS=localhost,127.0.0.1- Main Application: http://localhost:8000
- Administrative Interface: http://localhost:8000/admin
# Input: Comma-separated ingredient list
# Example: "chicken, tomato, garlic"
# Output: Contextually appropriate recipe with preparation instructions# Input: Natural language meal description
# Example: "2 boiled eggs, 1 toast, coffee"
# Output: Comprehensive nutritional analysis with macronutrient breakdown# Available filters:
# - Category (Breakfast, Lunch, Dinner, Snacks, Desserts, Beverages)
# - Cuisine type (Global, Regional, Nepali-specific)
# - Dietary preferences (Vegetarian, Vegan, Gluten-free)POST /api/generate/ # Recipe generation from ingredients
GET /api/chat/history/ # Retrieve conversation history
POST /api/tracker/meals/ # Create meal entry
GET /api/tracker/meals/weekly/ # Retrieve weekly meal data
POST /api/tracker/daily-analyses/ # Generate daily nutritional analysis
POST /api/tracker/weekly-analyses/ # Generate weekly nutritional analysis
POST /api/tracker/monthly-analyses/ # Generate monthly nutritional analysisFor comprehensive API documentation, refer to the API Reference Guide.
chuk/
├── core/ # Primary application module
│ ├── models.py # Database schema definitions
│ ├── views.py # Recipe generator view controllers
│ ├── tracker_views.py # Nutrition tracker API endpoints
│ ├── gemini.py # AI service integration layer
│ └── recipe_retrieval.py # RAG implementation and search logic
├── data/ # Static data resources
│ ├── recipes_dataset.json # Global recipe collection
│ └── recipes_nepali.json # Regional Nepali recipe database
├── templates/ # HTML template files
├── static/ # Static assets (CSS, JavaScript, images)
├── requirements.txt # Python dependencies
└── manage.py # Django management interface
We welcome contributions from the developer community. To contribute:
- Fork the repository
- Create a feature branch (
git checkout -b feature/enhancement-name) - Commit your changes (
git commit -m 'Add specific enhancement') - Push to the branch (
git push origin feature/enhancement-name) - Submit a Pull Request for review
Please ensure all contributions adhere to the project's coding standards and include appropriate documentation.
- Mobile Platform Development — Native iOS and Android applications
- Voice Integration — Hands-free cooking assistance and voice-activated meal logging
- Computer Vision — Image-based meal recognition and nutritional analysis
- Social Features — Recipe sharing and community engagement capabilities
- IoT Integration — Smart kitchen appliance connectivity and automation
These features are subject to change based on user feedback and technical feasibility assessments.
This project is licensed under the MIT License. See the LICENSE file for complete terms and conditions.
This project acknowledges the following contributions and resources:
- Recipe Data Sources — Open-source culinary databases and community-contributed content
- AI Technology — Google Gemini 2.5 Flash API for natural language processing
- Beta Testing Program — Early adopters who provided critical feedback during development
Development Team: TechForGood Innovators
Email: team@chuk.dev
Repository: GitHub
For bug reports, feature requests, or technical inquiries, please use the GitHub Issues system.
Chuk is an open-source project committed to improving nutrition accessibility and reducing food waste through intelligent technology.