In this hands-on workshop, participants will move beyond theoretical understanding of RAG to learn and build agentic RAG systems ready for production deployment. While most resources focus on basic RAG implementation, this workshop addresses the critical gaps that determine success in production: evaluation driven mindset, optimized retrieval, agent design patterns and end-to-end instrumentation.
Key Takeaways
1 End-to-End Architecture Design: Learn proven system architectures for agentic RAG systems. Understand and incorporate different chunking strategies, retrieval methods, agentic patterns, and evaluation methodologies.
2 Retrieval Optimization Strategies: Explore techniques beyond basic vector search, including query decomposition and routing, re-ranking, metadata filtering, and more.
3 Evaluation Beyond Accuracy: Build comprehensive evaluation frameworks that measure business impact, not just technical metrics, with automated test suites for continuous improvement.
4 Production Readiness: Instrument RAG agents with tracing, logging, and evaluation.
5 Hands-on Implementation: Walk away with working code templates, and examples you can immediately adapt to your organization's needs.
Speaker
Hien Luu
Sr. Engineering Manager @Zoox & Author of MLOps with Ray, Speaker and Conference Committee Chair
Hien Luu is a Sr. Engineering Manager at Zoox, leading the Machine Learning Platform team. He is particularly passionate about building scalable AI/ML infrastructure to power real-world applications. He is the author of MLOps with Ray and the Beginning Apache Spark 3 book. He has given presentations at various conferences such as MLOps World, QCon (SF,NY, London), GHC 2022, Data+AI Summit, XAI 21 Summit, YOW Data!, appy()
