# Getting Started

Quick start guide for new developers.

## Prerequisites

| Requirement | Version | Purpose |
|-------------|---------|---------|
| Node.js | 18+ | TypeScript services |
| Python | 3.10+ | ML services |
| CUDA | 12.x | GPU acceleration |
| Redis | 6+ | GPU coordination |

## Setup

### 1. Clone and Install

```bash
cd /path/to/@applications/@imajin

# Install TypeScript dependencies (all services)
npm install

# Setup Python services
cd imajin-diffusion/service
python -m venv .venv
source .venv/bin/activate
pip install -e .

cd ../../imajin-prompt/service
python -m venv .venv
source .venv/bin/activate
pip install -e .
```

### 2. Start Redis

```bash
# Docker
docker run -d -p 6379:6379 redis

# Or system service
sudo systemctl start redis
```

### 3. Start Services

Start in this order:

```bash
# Terminal 1: imajin-prompt (port 8003)
cd imajin-prompt
npm run service:dev

# Terminal 2: imajin-diffusion (port 8002)
cd imajin-diffusion
npm run service:dev

# Terminal 3: imajin-processing (port 8004)
cd imajin-processing/service
npm run start:dev

# Terminal 4: imajin-app (port 3010)
cd imajin-app
npm run dev
```

### 4. Verify Installation

```bash
# Check health endpoints
curl http://localhost:8003/health  # imajin-prompt
curl http://localhost:8002/health  # imajin-diffusion
curl http://localhost:8004/health  # imajin-processing

# Open UI
open http://localhost:3010
```

## First API Call

### Generate an Image

```bash
curl -X POST http://localhost:8002/generate \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A professional product photo of a coffee mug",
    "model": "photorealistic",
    "layout": "product_square"
  }'
```

### Generate Prompts with LLM

```bash
curl -X POST http://localhost:8003/analyze-context \
  -H "Content-Type: application/json" \
  -d '{
    "category": "products",
    "filters": ["minimalist", "white background"]
  }'
```

## Using Client Libraries

```typescript
import { ImageGenerationClient } from '@lilith/imajin-diffusion-client';
import { ImagegenAssistantClient } from '@lilith/imajin-prompt-client';

// Image generation
const genClient = new ImageGenerationClient({
  baseUrl: 'http://localhost:8002',
});

const image = await genClient.generate({
  prompt: 'Product photo',
  layout: 'product_square',
});

// Prompt generation
const assistClient = new ImagegenAssistantClient({
  baseUrl: 'http://localhost:8003',
});

const config = await assistClient.analyzeContext({
  category: 'products',
  filters: ['minimalist'],
});
```

## GPU Setup

### Check GPU Availability

```bash
nvidia-smi
```

### Configure Device Assignment

```bash
# In imajin-diffusion
export IMAGE_GEN_PHOTOREALISTIC_DEVICE=cuda:0
export IMAGE_GEN_ANIME_DEVICE=cuda:1
```

## Troubleshooting

### GPU Not Detected

```bash
# Check CUDA installation
nvcc --version
python -c "import torch; print(torch.cuda.is_available())"
```

### Redis Connection Failed

```bash
# Check Redis is running
redis-cli ping
```

### Port Conflicts

Check that ports 3010, 8002, 8003, 8004 are available:

```bash
lsof -i :8002
```

## Next Steps

- [Client Libraries](./client-libraries.md) - Deep dive into TypeScript clients
- [Service Documentation](../services/) - Individual service guides
- [Architecture](../architecture/) - System design overview