Objective | Monitoring applications on the cloud provides a stream of irregularly occurring events. These streams often involve events multiple types of events to co-occur. For example, a disk utilisation event, followed by a database query execution event and so on. In this work, we explore the possibilities of using large language models to infer patterns in the stream of events and predict future steam of event. The goal is to identify if there is a possibility of anomalous events in the future to take proactive actions. |