Abstract: This case study examines the deployment of a scalable Light Retrieval-Augmented Generation (RAG) system designed for processing and querying Albanian legal data. The system leverages lightweight retrieval methods combined with generative AI to deliver accurate, context-aware responses from a comprehensive corpus of Albanian laws and legal documents. Deployed using Kubernetes, the architecture ensures high availability, scalability, and efficient resource management, making it well-suited for legal professionals and institutions seeking fast and reliable access to complex legal information. https://conf.linuxappsummit.org/event/7/sessions/14/ Talk should be available on Youtube stream at 11:00am EAT and can be watched afterwards: https://www.youtube.com/@linuxappsummit2688/streams Benson