Real-time AI Model Inference with Apache Flink - From GenAI to Predictive Analytics

Learn how to leverage Flink for real-time AI model inference in this technical talk by Field CTO Kai Waehner. Explore practical implementations of data streaming platforms for generative AI, predictive analytics, and real-time processing applications. Discover the fundamentals of event-driven architecture and its benefits for model inference, including detailed explanations of streaming, connectivity, processing, and governance. Gain insights into specific use cases such as predictive AI, generative AI applications, retrieval-augmented generation (RAG), and predictive maintenance in manufacturing settings. Access comprehensive resources for implementing these solutions, including documentation, GenAI hub materials, and practical examples of Flink applications in real-world scenarios.