With cloud-native AI, we typically hear a lot about the models, but what about our data? Efficient ingestion and retrieval of enterprise knowledge is the backbone of intelligent applications, yet developers still struggle with messy, unstructured formats, governance concerns, and runaway costs from inference. Join us for this hands-on workshop showing how Kubernetes-native tooling can help build scalable Retrieval-Augmented Generation (RAG) applications.

What you’ll learn (and practice):
- Structure Unstructured Data: Use open-source projects like Docling to transform PDFs, proprietary formats, and unstructured text into query-ready knowledge for your apps.
- Deploy and Scale RAG: See how RAG improves generative responses without heavy fine-tuning, using projects such as Kafka, Knative, and Kubeflow Pipelines for data ingestion and processing.

We'll finish by building a Kubernetes-native AI-powered ticketing system retriever, with complete data sovereignty and scalability!