Skip to main content

Getting Started

This guide will help you set up and run the AI Ingredient Scanner on your machine.

Prerequisites​

RequirementVersion
Python3.11+
Node.js18+ (for mobile app)
Google Cloud API keyGemini
Qdrant Cloud accountFree tier available

Backend Setup​

1. Clone Repository​

git clone https://github.com/udaytamma/AiIngredientScanner.git
cd AiIngredientScanner

2. Create Virtual Environment​

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

3. Install Dependencies​

pip install -r requirements.txt

4. Configure Environment​

Create a .env file in the project root:

# Required
GOOGLE_API_KEY=your_gemini_api_key
QDRANT_URL=your_qdrant_cloud_url
QDRANT_API_KEY=your_qdrant_api_key

# Optional
REDIS_URL=your_redis_connection_string
LANGCHAIN_API_KEY=your_langsmith_api_key
Getting API Keys

5. Verify Connections​

python test_connections.py

6. Run the Application​

Option A: Streamlit Web Interface

streamlit run app.py

Option B: REST API (for mobile app)

uvicorn api:app --host 0.0.0.0 --port 8000

Mobile App Setup​

See the Mobile App Setup Guide for detailed instructions.

Quick Start​

cd mobile
npm install

# Update API URL in src/services/api.ts
# Replace with your machine's IP address

npx expo start
# Scan QR code with Expo Go app

First Analysis​

  1. Open the Streamlit interface at http://localhost:8501
  2. Enter a product name (optional)
  3. Paste an ingredient list
  4. Configure your profile (allergies, skin type)
  5. Click Analyze
  6. View your personalized safety report!

Project Structure​

AiIngredientScanner/
├── app.py                  # Streamlit web interface
├── api.py                  # FastAPI REST endpoints
├── graph.py                # LangGraph workflow
├── agents/                 # AI agents
│   ├── research.py         # Ingredient research
│   ├── analysis.py         # Report generation
│   ├── critic.py           # Quality validation
│   └── supervisor.py       # Workflow routing
├── tools/                  # Utility tools
├── prompts/                # LLM prompts
├── config/                 # Configuration
├── mobile/                 # React Native app
└── tests/                  # Test suite

Next Steps​

Troubleshooting​

Common Issues​

"Cannot connect to Qdrant"

  • Verify your QDRANT_URL and QDRANT_API_KEY are correct
  • Check your network connection

"API key not valid"

  • Ensure GOOGLE_API_KEY is set correctly
  • Check if the key has Gemini API access enabled

"Module not found"

  • Activate your virtual environment
  • Run pip install -r requirements.txt again