Examples# Multi-modal AI pipeline Get the code Development Production No infrastructure headaches LLM training and inference Get the code Set up Data ingestion Fine-tuning Batch inference Online serving Production Audio batch inference Setup Get the code Streaming data ingestion Audio preprocessing GPU inference with Whisper LLM-based quality filter Persist the curated subset Distributed XGBoost pipeline Get the code Time-series forecasting Get the code Setup Acknowledgements Scalable video processing Get the code Distributed RAG pipeline Get the code Notebooks Deploy MCP servers Why Ray Serve for MCP Anyscale service benefits Prerequisites Development Production No infrastructure headaches Get the code Build a tool-using agent Get the code Architecture overview Dependencies and compute resource requirements Implementation: Building the services Deploy the services Test the agent Next steps Build a multi-agent system with the A2A protocol 1. Architecture 2. Project structure 3. Get started with local deployment Get the code 4. Deploy to production on Anyscale 5. Deep dive: Understand each component 6. Next steps 7. Additional resources