Eurowings, a subsidiary of Lufthansa Group, implemented semantic search powered by Databricks Vector Search and Model Serving on eurowings.com to overcome technical barriers preventing users from finding relevant information quickly. The company migrated to a new platform, Minerva, built on Databricks, creating a unified data lake using a medallion architecture. This transformation drove a 109% lift in search relevance, reduced latency by over 60%, and improved search recall from 50% to more than 75%. Search latency dropped from 6 seconds to under 2 seconds. The previous environment faced challenges with siloed data across disparate systems, and technical barriers in vector storage slowed development.