AlloyDB Omni and EmbeddingGemma with Gemma 4 on Kubernetes

Codelab: https://codelabs.developers.google.co... In this codelab, you will learn how to deploy AlloyDB Omni on Google Kubernetes Engine (GKE) and use it with open models like EmbeddingGemma and Gemma 4 for embeddings and predictions. Running both the database and models in the same cluster reduces network latency and avoids third-party service dependencies. It also helps satisfy compliance and data residency requirements since your data never leaves your environment. Result Submission: https://goo.gle/result-validation Speaker: Gleb Otochkin Cloud Databases Advocate Google   / glebotochkin