Build Generative AI Apps for Enterprises with Cloud
summary
Recommends a concrete template: Cloud Run + AlloyDB as the quick-start stack, swapping in GKE or Cloud SQL when needed, and using Vertex AI for embeddings and inference. Claims content workflows drop from weeks to hours by automating attribute and description generation. Uses Retrieval Augmented Generation to intercept queries, run vector search against enterprise data, and append results so models stay grounded without costly fine-tuning. Advises logging outputs to BigQuery for evaluation and iterative improvement.
AI-written summary · about
chapters (6)
- 0:00Meet Harish & Sean
- 0:59Common use cases for gen AI apps
- 2:45Pairing Google databases with cloud runtimes
- 3:49Why use Retrieval Augmented Generation with generative AI apps?
- 5:13Best practices for building gen AI apps
- 6:46Wrap up
related talks
38mBuild Gen AI applications with Google Databases and Cloud Runtimes
48mHow to Make Smart Architecture Decisions when Building Gen AI Apps
02h 35mBringing GenAI to the Modern Enterprise. A production use-case. In Serverless Java!
37mBuilding Generative AI Applications
29mCustomizing genAI applications for your business
15mLatest Generative AI products and solutions on
20mThe secret path to practical generative AI in the enterprise
01h 20mGenerative AI for Businesses