quickstart.sh

#!/bin/bash

# Quick Start Script for LLM Data Extractor (Ollama-powered)
# This script helps you get started quickly with FREE local models

set -e  # Exit on error

echo "🚀 LLM Data Extractor - Quick Start (Ollama)"
echo "=============================================="
echo ""

# Check if Ollama is installed
if ! command -v ollama &> /dev/null; then
    echo "❌ Ollama is not installed!"
    echo ""
    echo "Please install Ollama first:"
    echo "  macOS/Linux: curl -fsSL https://ollama.ai/install.sh | sh"
    echo "  macOS (Homebrew): brew install ollama"
    echo "  Or visit: https://ollama.ai"
    echo ""
    exit 1
fi

echo "✓ Ollama is installed"
echo ""

# Check if Ollama is running
if ! curl -s http://localhost:11434/api/tags > /dev/null 2>&1; then
    echo "⚠️  Ollama server is not running!"
    echo ""
    echo "Starting Ollama in background..."
    ollama serve > /dev/null 2>&1 &
    sleep 3
    
    if curl -s http://localhost:11434/api/tags > /dev/null 2>&1; then
        echo "✓ Ollama server started"
    else
        echo "❌ Could not start Ollama server"
        echo "Please run 'ollama serve' in a separate terminal and try again"
        exit 1
    fi
else
    echo "✓ Ollama server is running"
fi
echo ""

# Check if llama3.2 model is available
if ! ollama list | grep -q "llama3.2"; then
    echo "⚠️  llama3.2 model not found"
    echo ""
    echo "Pulling llama3.2 model (this may take a few minutes)..."
    ollama pull llama3.2
    echo "✓ Model downloaded"
else
    echo "✓ llama3.2 model is available"
fi
echo ""

# Check Python version
echo "Checking Python version..."
python_version=$(python3 --version 2>&1 | awk '{print $2}')
echo "✓ Found Python $python_version"
echo ""

# Check if virtual environment exists
if [ ! -d "venv" ]; then
    echo "Creating virtual environment..."
    python3 -m venv venv
    echo "✓ Virtual environment created"
else
    echo "✓ Virtual environment already exists"
fi
echo ""

# Activate virtual environment
echo "Activating virtual environment..."
source venv/bin/activate
echo "✓ Virtual environment activated"
echo ""

# Install dependencies
echo "Installing dependencies..."
pip install -q --upgrade pip
pip install -q -r requirements.txt
echo "✓ Dependencies installed"
echo ""

# Check for .env file
if [ ! -f ".env" ]; then
    echo "Creating .env from template..."
    cp .env.example .env
    echo "✓ .env file created (using defaults)"
else
    echo "✓ .env file already exists"
fi
echo ""

# Create output directory
mkdir -p output logs
echo "✓ Created output and logs directories"
echo ""

# Run example
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo "🎯 Running example extraction..."
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo ""

python3 cli.py extract \
    --input sample_inputs/invoice_tech.txt \
    --type invoice \
    --output output/quickstart_invoice.json

echo ""
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo "✅ Setup complete!"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo ""
echo "Next steps:"
echo "  1. Check output/quickstart_invoice.json"
echo "  2. View logs in logs/ directory"
echo "  3. Try other examples:"
echo ""
echo "     python3 cli.py extract --input sample_inputs/email_project.txt --type email"
echo "     python3 cli.py extract --input sample_inputs/support_ticket_urgent.txt --type support_ticket"
echo ""
echo "  4. See all options:"
echo "     python3 cli.py extract --help"
echo "     python3 cli.py list-schemas"
echo ""
echo "  5. Try different models:"
echo "     ollama pull llama3.1"
echo "     python3 cli.py extract --input sample_inputs/invoice_tech.txt --type invoice --model llama3.1"
echo ""
echo "Happy extracting with FREE local models! 🎉"