Deploying Generative AI Applications with Cloud Run and LangChain on Google Cloud

Learn how to deploy and manage Generative AI applications on Google Cloud in this 31-minute technical presentation from AppDev Field Day 1. Discover the integration of LangChain framework with Cloud Run, Cloud SQL's pgvector, and Vertex Endpoints to build powerful GenAI applications. Follow along as Google Cloud's Group Product Manager Steren Giannini and Senior Product Manager Lisa Shen demonstrate the Retrieval-Augmented Generation (RAG) model architecture and its implementation. Explore practical examples through a live demonstration of deploying a web application that leverages vector databases to answer queries about Cloud Run features. Master the scalability and cost-optimization features of Cloud Run, including its ability to scale to zero when inactive. Access hands-on experience through the provided codelab to build and deploy your own LangChain application on Cloud Run, while learning best practices for containerized application management without infrastructure overhead.