This blog post demonstrates how to build an RAG-enabled GenAI model using Confluent, Flink, and MongoDB. It outlines the need for integrating data from different sources and destinations in real-time, leveraging NoSQL database technology for agile development, reduced operational costs, and scalable operations. The authors discuss the benefits of using Confluent Cloud, Confluent for Kubernetes, and Apache Kafka to build a streaming data pipeline that facilitates real-time data transfer between an on-premises relational database and a document-oriented NoSQL database like MarkLogic. They provide step-by-step instructions on deploying a self-managed Oracle CDC connector and a MarkLogic Sink connector using Confluent for Kubernetes, leveraging the Control Center UI or CLI to configure the connectors. The post also highlights the importance of security, scalability, and ease of use in building end-to-end data pipelines consisting of both relational and NoSQL databases.