Multimodal Agent that analyze product ingredients and provide health and nutrition insights

Table of contents

• Overview
• Architecture
• Features
• Dependencies
• Project Structure
• Installation
• Usage
• Contributing

Overview

IngreCheck is an Multimodal agentic AI application that helps you decode the ingredients in the products you use daily. Whether you're uploading an image, snapping a quick photo, or selecting from sample images, this app provides deep insights into what’s inside your products, empowering you to make healthier choices.

The application integrates two powerful tools:

• IngreCompare: A tool for side-by-side ingredient comparison between two products.
• NutriCare Assistant: A conversational health and nutrition assistant offering evidence-based information, wellness recommendations, and fitness advice.

Together, these features make IngreCheck a comprehensive solution for ingredient analysis, product comparison, and personalized health guidance.

Architecture

Features

IngreCheck Features

Feature	Description
Ingredient Analysis	Analysis of product ingredients, highlighting healthy or harmful components.
Image Upload & Camera Support	Upload images or capture product photos directly for analysis.
Sample Image Selection	Preloaded product images for quick testing and analysis.
(IngreCompare) Comparison Mode	Side-by-side comparison of two product ingredient lists.
Interactive Table Output	Ingredient information and comparison results are displayed in a tabular format.
Agentic AI Approach	Dynamic and personalized ingredient evaluation powered by AI models.
User-Friendly Interface	Engages users with a user-friendly interface for better understanding.

NutriCare Assistant Features

Feature	Description
Health Information Search	Finds accurate health and wellness information.
Interactive Chat Interface	Provides conversational health and nutrition advice, making the assistant feel personal and approachable.
Evidence-Based Insights	Uses advanced AI models to pull accurate, evidence-based nutrition and wellness information.
Dynamic Response Output	Uses structured data, display responses in easy-to-read tables for better understanding.
Empathetic Tone	Ensures a friendly and engaging user experience.
Real-Time Health Assistance	Delivers personalized health guidance instantly.

Dependencies

• python-dotenv: Library for managing environment variables from a .env file
• streamlit: Web framework for building interactive applications
• phidata: Data science tools and frameworks for efficient processing and analysis
• pillow: Image processing library for handling and manipulating images
• google-generativeai: Integration for using Google's generative AI models
• googlesearch-python: Library for performing Google searches programmatically
• pycountry: Library for working with country-related data (essential for googlesearch)

Project Structure

IngreCheck_App
├── IngreCheck.py               # Main application file
├── prompts.py                  # Contains AI prompts and configurations
├── pages/                      # Pages folder for additional app features
│   └── NutriCare_Assistant.py  # NutriCare Assistant feature implementation
├── sample_images/              # Folder containing sample product images for testing
├── assets/                     # Assets folder for frontend elements
│   ├── logo.png                # App logo
│   ├── favicon.png             # App favicon
│   └── [other assets]          # Additional frontend elements
├── .streamlit/                 # Streamlit configuration folder
│   └── config.toml             # Streamlit configuration file
├── requirements.txt            # Dependencies and libraries for the project
└── README.md                   # Project documentation

Installation

1. Clone the repository:

   git clone https://github.com/Adityathere/IngreCheck

2. Navigate to the project directory:

   cd IngreCheck

3. Create and activate a virtual environment:

   python3 -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

4. Install dependencies:

   pip install -r requirements.txt

5. Acquire API keys through makersuite.google.com and console.groq.com and put them in the .env file:

   GOOGLE_API_KEY="ENTER YOUR API"
   GROQ_API_KEY="ENTER YOUR API"

6. Run the application:

   streamlit run IngreCheck/IngreCheck.py

Usage

1. Launch the application in your browser.
2. Choose one of the following options to upload a product image:
   • Upload an image file.
   • Take a photo using your device's camera.
   • Select from sample images.
3. View the analysis report generated by the AI model, including insights into the product's ingredients.

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star⭐! Thanks again!

1. Fork the Project
2. Create your Feature Branch git checkout -b feature-name
3. Commit your Changes git commit -m 'Add new feature
4. Push to the Branch git push origin feature-name
5. Open a Pull Request