Skip to content

QUICK_START.md

Latest commit

 

History

History
153 lines (112 loc) · 3.59 KB

QUICK_START.md

File metadata and controls

153 lines (112 loc) · 3.59 KB
Raw

⚡ Quick Start Guide

Get up and running in 5 minutes!

📋 Before You Start

Make sure you have:

  • Python 3.10+ installed
  • Node.js 18+ installed
  • Azure OpenAI API key (with GPT-4o deployment)
  • Deepgram API key

🚀 Installation (One-Time Setup)

Step 1: Backend Setup (2 minutes)

# Navigate to backend folder
cd backend

# Create virtual environment
python -m venv venv

# Activate it
# Windows:
venv\Scripts\activate
# macOS/Linux:
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

Create a .env file in the backend folder:

AZURE_OPENAI_API_KEY=sk-your-azure-key-here
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
AZURE_OPENAI_API_VERSION=2024-02-15-preview
DEEPGRAM_API_KEY=your-deepgram-key-here
HOST=0.0.0.0
PORT=8000
CORS_ORIGINS=http://localhost:3000,http://localhost:5173

Step 2: Frontend Setup (2 minutes)

# Navigate to frontend folder (new terminal)
cd frontend

# Install dependencies
npm install

# Build Electron main process (first time only)
npm run build:electron-dev

▶️ Running the App (Every Time)

Terminal 1 - Backend

cd backend
venv\Scripts\activate  # or source venv/bin/activate on macOS/Linux
python run.py

You should see:

🎯 Interview Copilot Backend Server
Server URL: http://0.0.0.0:8000
✨ Starting server...

Terminal 2 - Frontend

cd frontend
npm run dev

The Electron app will launch automatically!

🎮 Using the App

  1. Click "Start Listening" (or press Ctrl+Shift+L)
  2. Select the interview window/tab to capture
  3. Check "Share system audio" ✅ (VERY IMPORTANT!)
  4. Click Share
  5. Ask a question (or let the interviewer ask)
  6. Watch the AI response appear in real-time! 🎉

For Coding Problems

  1. Press Ctrl+Shift+S (or click "Capture Screen")
  2. Select the screen with the coding problem
  3. Click Share
  4. Get a complete solution with explanation! 💻

🎯 Keyboard Shortcuts

  • Ctrl+Shift+L - Start/Stop listening
  • Ctrl+Shift+S - Capture screen
  • Ctrl+Shift+H - Hide/Show window

❓ Troubleshooting

"No audio track available"

  • You forgot to check "Share system audio" when selecting the screen
  • Click "Stop Listening" and try again, this time check the audio checkbox

"Connection error"

  • Make sure the backend is running (Terminal 1)
  • Check if port 8000 is available

"API Key error"

  • Double-check your .env file
  • Make sure there are no quotes around the values
  • Verify your Azure endpoint URL ends with /

"Deepgram error"

  • Verify your Deepgram API key is correct
  • Check your account has credits

🎉 Success!

When everything is working:

  • ✅ Backend shows: "Deepgram streaming started successfully"
  • ✅ Frontend shows: Green "Connected" indicator
  • ✅ Listening button turns pink when active
  • ✅ Transcripts appear in real-time
  • ✅ AI responses stream smoothly

📚 Next Steps

💡 Pro Tips

  1. Position the overlay where it won't block important content
  2. Adjust opacity using the ◐ button in the title bar
  3. Clear history regularly to keep responses focused
  4. Test before interviews to ensure everything works
  5. Use screen capture for complex coding problems

Ready to ace your interviews! 🚀

For detailed documentation, see SETUP_GUIDE.md