Practical MLflow for Generative AI on Databricks: Build High-Quality AI Agents from Prompt Design to Production($66.99Value)

Description

Bridge the gap between cutting edge research and the practical operationalization of generative AI. This handy guide demystifies the complexities of managing GenAI applications using leading open source platform MLflow on Databricks. What sets this book apart is its focus on the requirements of managing and deploying GenAI applications. ML and AI specialists from Databricks, authors Nuwan Ganganath, Julie Nguyen, and Chang Shi Lim take you through each stage of the development of an agentic chatbot, sharing best practices, innovative techniques, and common challenges along the way. By combining deep technical insights with interactive exercises and actionable real-world code examples, they ensure that you're equipped to implement robust GenAI applications in modern enterprise environments. Understand MLflow fundamentals, including core components and the tool's application to GenAI on the Databricks platform - Build, track, and manage GenAI applications using MLflow, from prompts to the overall agentic chain - Optimize and evaluate GenAI applications through a combination of automated LLM-assisted judges and human-in-the-loop review - Deploy production-ready GenAI applications, leveraging Databricks' scalable infrastructure and monitoring capability Nuwan Ganganath, PhD is an AI/ML Solutions Architect at Databricks specializing in MLOps and LLMOps using MLflow. With over a decade of experience, he helps organizations design, deploy, and manage scalable ML and LLM solutions on the Databricks platform. Julie Nguyen is a Machine Learning and GenAI Specialist at Databricks. She has deep expertise in MLflow and a strong track record of helping enterprise teams bring production-ready AI models to Chang Shi is a Specialist Solutions Architect at Databricks with expertise in MLflow and MLOps. He has led the design and delivery of AI/ML solutions―including LLM-powered systems―across the Asia-Pacific region, and regularly educates teams on best practices in scalable ML deployment.