Getting StartedInstallation

Installation

Apollo RAG supports multiple installation methods depending on your use case and infrastructure.

System Requirements

Minimum Requirements

  • OS: Linux (Ubuntu 20.04+), macOS (12+), or Windows 10/11 with WSL2
  • Python: 3.9 or higher
  • RAM: 8GB minimum, 16GB recommended
  • Storage: 10GB for models and dependencies

GPU Requirements (Optional but Recommended)

For optimal performance with GPU acceleration:

  • NVIDIA GPU: Compute Capability 7.0+ (RTX 2000 series or newer)
  • VRAM: 6GB minimum, 12GB+ recommended
  • CUDA: 11.8 or higher
  • cuDNN: 8.6 or higher

Apollo works on CPU-only systems but GPU acceleration provides 10x faster retrieval and embedding operations.

Installation Methods

Docker Installation (Recommended)

The fastest way to get Apollo running is with Docker Compose:

# Clone the repository
git clone https://github.com/yourusername/apollo-rag.git
cd apollo-rag
 
# Launch with Docker Compose (includes GPU support)
docker compose up -d
 
# Verify the installation
curl http://localhost:8000/health

The Docker setup includes:

  • ✅ FastAPI backend with GPU support
  • ✅ Vector database (FAISS)
  • ✅ Monitoring stack (Prometheus + Grafana)
  • ✅ Redis cache
  • ✅ Pre-configured models

Docker Compose automatically detects NVIDIA GPUs and enables GPU acceleration if available.

pip Installation

Install Apollo as a Python package:

# Create a virtual environment
python -m venv apollo-env
source apollo-env/bin/activate  # On Windows: apollo-env\Scripts\activate
 
# Install Apollo with GPU support
pip install apollo-rag[gpu]
 
# Or CPU-only version
pip install apollo-rag
 
# Verify installation
apollo --version

Optional Dependencies:

# For PDF processing
pip install apollo-rag[pdf]
 
# For advanced monitoring
pip install apollo-rag[monitoring]
 
# Install all extras
pip install apollo-rag[all]

Build from Source

For development or customization:

# Clone the repository
git clone https://github.com/yourusername/apollo-rag.git
cd apollo-rag
 
# Install in development mode
pip install -e ".[dev,gpu]"
 
# Run tests to verify
pytest tests/
 
# Start the development server
python -m apollo.server --dev

Development Dependencies:

# Install pre-commit hooks
pre-commit install
 
# Install all development tools
pip install -e ".[dev,test,docs]"

GPU Setup

CUDA Installation

If you have an NVIDIA GPU, install CUDA for optimal performance.

Ubuntu/Debian

# Add NVIDIA package repositories
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-keyring_1.0-1_all.deb
sudo dpkg -i cuda-keyring_1.0-1_all.deb
sudo apt-get update
 
# Install CUDA Toolkit
sudo apt-get install cuda-toolkit-11-8
 
# Install cuDNN
sudo apt-get install libcudnn8
 
# Verify installation
nvidia-smi
nvcc --version

Windows

nvidia-smi
nvcc --version

macOS

NVIDIA GPUs are not supported on modern macOS. Apollo can run on CPU or you can use Docker with GPU passthrough on a Linux host.

For Metal GPU acceleration (experimental):

pip install apollo-rag[metal]

Verify Installation

After installation, verify everything is working:

# Check Apollo version
apollo --version
 
# Run diagnostics
apollo diagnose
 
# Check GPU availability
python -c "import torch; print(f'CUDA available: {torch.cuda.is_available()}')"
 
# Test with a simple query
curl -X POST http://localhost:8000/query \
  -H "Content-Type: application/json" \
  -d '{"query": "test query"}'

Expected output:

{
  "status": "success",
  "version": "4.1.0",
  "gpu_enabled": true,
  "gpu_count": 1,
  "gpu_name": "NVIDIA RTX 4090"
}

Troubleshooting

GPU Not Detected

If CUDA is installed but Apollo doesn’t detect it:

# Check CUDA environment variables
echo $CUDA_HOME
echo $LD_LIBRARY_PATH
 
# Reinstall PyTorch with CUDA support
pip uninstall torch torchvision
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu118

Permission Errors (Docker)

If you get permission errors with Docker:

# Add your user to the docker group
sudo usermod -aG docker $USER
 
# Log out and back in, then restart Docker
sudo systemctl restart docker

Import Errors

If you encounter import errors:

# Clear pip cache and reinstall
pip cache purge
pip install --force-reinstall apollo-rag[gpu]

Next Steps

Now that Apollo is installed:

Need help? Join our Discord community or check the troubleshooting guide.

Quick StartMaking Your First Query