Generative AI in Production
Traditional MLOps is a set of practices to productionize traditional ML systems for enterprise applications. Generative AI raises new challenges in managing and productionizing applications at scale. The field of generative AI operations seeks to address these new challenges. In this course, you learn about the challenges that arise when deploying and productionizing generative AI-powered applications. You learn how to secure your generative AI-powered applications. Finally, you will discuss best practices for logging and monitoring your generative AI-powered applications in production.
7 hours
VirtualUnderstand the challenges in productionizing applications using generative AIManage experimentation and evaluation for LLM-powered applicationProductionize LLM-powered applicationsSecure generative AI applicationsImplement logging and monitoring for LLM-powered applications
Introduction to Generative AI in ProductionUnderstand generative AI operationsCompare traditional MLOps and GenAIOpsAnalyze the components of an LLM systemDefine and compare RAG and ReActGenerative AI Application DeploymentEvaluate application deployment optionsDeploy, package, and version applicationsProductionizing Generative AIMaintain and update LLM modelsTest and evaluate generative AI-powered applicationsDeploy CI/CD pipelines for generative AI applicationsSecuring Generative AI ApplicationsIdentify security challenges for generative AI applicationsUnderstand prompt security issuesApply sensitive data protection and DLP APIImplement Model ArmorObservability for Production LLM SystemsDescribe Google Cloud Observability capabilitiesExplain the purpose of Cloud MonitoringExplain the purpose of Cloud LoggingExplain the purpose of Cloud Trace
Developers, DevOps engineers and machine learning engineers who wish to operationalize GenAI-based applications
Upcoming Sessions
Contact us for upcoming dates
There are currently no upcoming sessions scheduled for this course.
Request Information
