Production-ready machine learning platform for real-time streaming data processing, model management, and high-performance API serving.
Full documentation is available in the docs/ directory.
- Setup Guide: Get started with installation and local setup.
- Architecture: Understand the system design and components.
- Project Structure: Detailed overview of directories and files.
- API Reference: Detailed API documentation.
- Running the Demo: Step-by-step guide to run the end-to-end demo.
- Multi-cloud streaming: Kafka, AWS Kinesis, and GCP Pub/Sub consumers.
- Feature Store: Low-latency Redis cache with PostgreSQL persistence.
- Model Serving: High-performance FastAPI server with async support.
- MLflow Integration: Automated model versioning and registry.
- Observability: Built-in Prometheus metrics and Grafana dashboards.
# Clone repository
git clone <repository-url>
cd rt-ml-multicloud-platform
# Setup environment
cp ops/envs/.env.example .env
# Run the full end-to-end local demo (starts services, trains models, tests API)
./scripts/demo/demo-local/demo.shMIT License - see LICENSE file for details.
2026-02-20 21:53