docs: add clean extensible architecture design

Created comprehensive architecture document for RunPod deployment:

**Key Design Principles:**
- No Docker (direct Python for RunPod compatibility)
- Extensible (add models in 3 simple steps)
- Maintainable (clear structure, base classes)
- Simple (one command startup)

**Structure:**
- core/ - Base service class + service manager
- model-orchestrator/ - Request routing
- models/ - Service implementations (vllm, flux, musicgen)
- scripts/ - Install, start, stop, template prep
- docs/ - Adding models, deployment, templates

**Adding New Models:**
1. Create server.py inheriting BaseService
2. Add entry to models.yaml
3. Add requirements.txt

That's it! Orchestrator handles lifecycle automatically.

Next: Implement base_service.py and refactor existing services.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
2025-11-21 15:16:51 +01:00
parent 31be1932e7
commit 03a430894d

212
ARCHITECTURE.md Normal file
View File

@@ -0,0 +1,212 @@
# RunPod Multi-Modal AI Architecture
**Clean, extensible Python-based architecture for RunPod GPU instances**
## Design Principles
1. **No Docker** - Direct Python execution for RunPod compatibility
2. **Extensible** - Adding new models requires minimal code
3. **Maintainable** - Clear structure and separation of concerns
4. **Simple** - One command to start, easy to debug
## Directory Structure
```
runpod/
├── core/ # Core infrastructure
│ ├── base_service.py # Abstract base class for all services
│ ├── service_manager.py # Process lifecycle management
│ └── requirements.txt # Core dependencies
├── model-orchestrator/ # Request orchestration
│ ├── orchestrator.py # Main orchestrator (process-based)
│ ├── models.yaml # Model registry (simple config)
│ └── requirements.txt # Orchestrator dependencies
├── models/ # Model service implementations
│ ├── vllm/ # Text generation
│ │ ├── server.py # vLLM service (inherits base_service)
│ │ └── requirements.txt # vLLM dependencies
│ │
│ ├── flux/ # Image generation
│ │ ├── server.py # Flux service
│ │ └── requirements.txt # Flux dependencies
│ │
│ └── musicgen/ # Music generation
│ ├── server.py # MusicGen service
│ └── requirements.txt # AudioCraft dependencies
├── scripts/ # Deployment & management
│ ├── install.sh # Install all dependencies
│ ├── download-models.sh # Pre-download models
│ ├── start-all.sh # Start orchestrator + services
│ ├── stop-all.sh # Stop all services
│ └── prepare-template.sh # RunPod template preparation
├── systemd/ # Optional systemd services
│ ├── ai-orchestrator.service
│ └── install-services.sh
└── docs/ # Documentation
├── ADDING_MODELS.md # Guide for adding new models
├── DEPLOYMENT.md # Deployment guide
└── RUNPOD_TEMPLATE.md # Template creation guide
```
## Component Responsibilities
### Core (`core/`)
- **base_service.py**: Abstract base class for all model services
- Health check endpoint
- Graceful shutdown
- Logging configuration
- Common utilities
- **service_manager.py**: Process lifecycle management
- Start/stop services
- Health monitoring
- Auto-restart on failure
- Resource cleanup
### Orchestrator (`model-orchestrator/`)
- **orchestrator.py**: Routes requests to appropriate model
- Reads `models.yaml` configuration
- Manages model switching
- Proxies requests to services
- OpenAI-compatible API
- **models.yaml**: Simple model registry
```yaml
models:
model-name:
type: text|image|audio
service_script: path/to/server.py
port: 8001
startup_time: 120
endpoint: /v1/chat/completions
```
### Models (`models/`)
Each model directory contains:
- **server.py**: Service implementation (inherits `BaseService`)
- **requirements.txt**: Model-specific dependencies
Services are standalone - can run independently for testing.
### Scripts (`scripts/`)
- **install.sh**: Install Python packages for all services
- **download-models.sh**: Pre-download models to `/workspace`
- **start-all.sh**: Start orchestrator (which manages model services)
- **stop-all.sh**: Graceful shutdown of all services
- **prepare-template.sh**: RunPod template preparation
## Adding a New Model (3 steps)
### 1. Create Model Service
```python
# models/mymodel/server.py
from core.base_service import BaseService
class MyModelService(BaseService):
def __init__(self):
super().__init__(
name="mymodel",
port=8004
)
async def initialize(self):
"""Load model"""
self.model = load_my_model()
def create_app(self):
"""Define FastAPI routes"""
@self.app.post("/v1/mymodel/generate")
async def generate(request: MyRequest):
return self.model.generate(request.prompt)
if __name__ == "__main__":
service = MyModelService()
service.run()
```
### 2. Add to Registry
```yaml
# model-orchestrator/models.yaml
models:
mymodel:
type: custom
service_script: models/mymodel/server.py
port: 8004
startup_time: 60
endpoint: /v1/mymodel/generate
```
### 3. Add Dependencies
```
# models/mymodel/requirements.txt
transformers==4.36.0
torch==2.1.0
```
That's it! The orchestrator handles everything else.
## Request Flow
```
Client Request
Orchestrator (port 9000)
↓ (determines model from endpoint)
Model Service (port 8001-800X)
Response
```
## Startup Flow
1. Run `scripts/start-all.sh`
2. Orchestrator starts on port 9000
3. Orchestrator reads `models.yaml`
4. On first request:
- Orchestrator starts appropriate model service
- Waits for health check
- Proxies request
5. On subsequent requests:
- If same model: direct proxy
- If different model: stop current, start new
## Benefits
- **Simple**: No Docker complexity, just Python
- **Fast**: No container overhead, direct execution
- **Debuggable**: Standard Python processes, easy to inspect
- **Extensible**: Add models by creating one file + YAML entry
- **Maintainable**: Clear structure, base classes, DRY principles
- **Portable**: Works anywhere Python runs (local, RunPod, other cloud)
## Development Workflow
```bash
# Local development
python3 models/vllm/server.py # Test service directly
python3 model-orchestrator/orchestrator.py # Test orchestrator
# RunPod deployment
./scripts/install.sh # Install dependencies
./scripts/download-models.sh # Pre-download models
./scripts/start-all.sh # Start everything
# Create template
./scripts/prepare-template.sh # Prepare for template save
```
## Future Enhancements
- Load balancing across multiple GPUs
- Model pooling (keep multiple models loaded)
- Batch request queueing
- Metrics and monitoring
- Auto-scaling based on demand