Today was another packed day here in Sweden, but I’m learning things and hopefully proving helpful to the folks here. I still made time for reading, and you’ll find some good ones below.
[blog] An advanced LlamaIndex RAG implementation on Google Cloud. There’s no shortage of agent frameworks for building AI apps. This post goes deep into using LlamaIndex.
[blog] How to Boost Performance and Reduce Costs with Stateful Feature Backfill in Apache Beam. The Intuit engineering team wrote up a summary of how they load historical data to provide state for realtime processing pipelines.
[blog] Protocol Buffer as data type in Spanner. Protobufs are used to serialize structured data, and now the Spanner database supports storing and retrieving them.
[article] How Saboteurs Threaten Innovation–and What to Do About It. Good stuff from Steve Blank about recognizing the challenges you’ll face as a founder or innovator.
[article] AI adoption drives ‘unmanageable’ spike in cloud costs. Sounds like a mix of better financial planning and smart deployment strategies are needed here.
[blog] Reduce unexpected costs with the new AI-powered Cost Anomaly Detection. This is such a useful capability! Get some help spotting unusual spend before it goes out of control.
[blog] 🌤️ IDX and Cloud Workstations: two Google tools empowering Cloud Development. I’ve played around with IDX, and need to give it another go. Hosted dev environments haven’t had their big moment yet, but it may be coming.
[article] Anyscale: New Optimized Runtime for Ray, Kubernetes Operator. We offer Ray in Vertex AI and GKE. It’s definitely growing in popularity!
[blog] Vertex AI Model Garden: All of your favorite LLMs in one place. Hyperscale clouds offer a few ways to consume LLMs. Nikita does a good job here of showing one way to deploy an LLM for inference.
Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below:
Richard Seroter's Architecture Musings 
Leave a comment