Skip to content

QUICKSTART.md

Latest commit

 

History

History
121 lines (88 loc) · 2.79 KB

QUICKSTART.md

File metadata and controls

121 lines (88 loc) · 2.79 KB

🚀 Quick Start Guide

Get your Vision-based Personal Memory Assistant running in 5 minutes!

Prerequisites

  • Python 3.8 or higher
  • Webcam (for image capture)
  • OpenAI API key (for natural language processing)

Step 1: Clone and Setup

# Navigate to your project directory
cd MemoryAssistant

# Run the setup script
python setup.py

Step 2: Configure API Key

  1. Edit the .env file:
nano .env
  1. Replace your_openai_api_key_here with your actual OpenAI API key:
OPENAI_API_KEY=sk-your-actual-api-key-here

Step 3: Run the Application

streamlit run app.py

The application will open in your browser at http://localhost:8501

Step 4: Test the System

  1. Manual Capture: Click "📸 Capture Image Now" in the sidebar
  2. Search Memories: Try queries like:
    • "When did I last see my laptop?"
    • "Show me when I was working at my desk"
    • "Find memories from today"

Features

🔍 Search Memories

  • Natural language queries
  • Object-based search
  • Time-based filtering
  • AI-powered responses

📊 Statistics

  • Total memories captured
  • Most common objects
  • Search history
  • Daily activity tracking

📸 Recent Captures

  • Browse all captured images
  • View scene descriptions
  • See detected objects

Configuration

Edit .env file to customize:

# Capture settings
CAPTURE_INTERVAL=300          # Capture every 5 minutes
CAPTURE_ACTIVE_HOURS_START=8  # Start at 8 AM
CAPTURE_ACTIVE_HOURS_END=22   # Stop at 10 PM

# AI settings
OPENAI_MODEL=gpt-3.5-turbo    # Use GPT-3.5 for faster responses
CONFIDENCE_THRESHOLD=0.5      # Object detection confidence

Troubleshooting

Camera Issues

  • Ensure your webcam is connected and accessible
  • Check camera permissions in your OS
  • Try different camera index in .env file

OpenAI API Issues

  • Verify your API key is correct
  • Check your OpenAI account has credits
  • Ensure you're using a supported model

Performance Issues

  • Use yolov8n.pt (nano) model for faster processing
  • Reduce capture frequency in .env
  • Close other applications using the webcam

Example Usage

  1. Start the app: streamlit run app.py
  2. Capture some images: Click "Capture Image Now" a few times
  3. Search for objects: "When did I last see my phone?"
  4. Browse recent captures: Check the "Recent Captures" tab
  5. View statistics: See your memory patterns in the "Statistics" tab

Next Steps

  • Enable auto-capture for continuous monitoring
  • Customize capture intervals based on your needs
  • Add more objects to the detection vocabulary
  • Integrate with cloud storage for backup

Support

  • Check the main README.md for detailed documentation
  • Run python test_setup.py to diagnose issues
  • Review logs in the terminal for error messages

Happy memory hunting! 🧠✨