Google Cloud Platform

Are you tired on learning and building a production RAG systems? With the Grounding support in Gemini, you can easily build a RAG system by enabling the option on the console.

Cloud logging’s log router is a power tool that gives you the flexibility to choose which logs are stored in Cloud Logging, sent to other Google Cloud products like Cloud Storage, or even sent to

Dataflow ML Documentation → goo.gle/4aMiaN9 Github Notebooks → goo.gle/3wRPZi5 Learn how Dataflow and Beam can help you easily craft and manage a streaming pipeline with AI/ML.

In this video Luke Schlangen shows Martin Omander how to run your Next.js web app on Google Cloud Run, without having to configure or manage any servers.

There are two security settings for Cloud Run services: what can trigger the service and what the service can do when it runs.

Imagine you are in a situation where you have documents containing complex graphs or diagrams packed with information and you want to extract this data to answer questions or queries.

Learn how to build a web application that allows users to generate html code from wireframes and prompts that the user enters using Vertex AI Generative AI Models.

The JavaScript ecosystem moves so quickly that it can leave you wondering, can I deploy [JavaScript framework] to Google Cloud Run? Yes.

Learn how to use Gemini Cloud Assist, an AI-powered collaborator in Google Cloud.

Learn about grounding with generative AI and discover how to integrate Gemini, multimodal embeddings, and vector search to build a production-ready RAG system.

Discover the power of connecting LLMs to external knowledge sources and APIs with LangChain's open-source capabilities integrated with Vertex AI.

By profiling Go applications at runtime, the Go compiler can make better optimization decisions in subsequent builds, leading to substantial improvements in CPU performance.

Supercharge your generative AI development workflow with Vertex AI and Flutter.

Learn about the latest tools and updates enabling developers to learn, build, and do more on Google Cloud and Workspace.

Leverage Vertex AI for the complete lifecycle of Google's Gemini Pro.

Build a generative AI application using the Gemini API and Vertex AI, and deploy it rapidly using Cloud Run, so you can focus on what's core to your business and leave the auto-scaling to Google.

Chloe Condon gets ready for Google I/O 2024 at Shoreline. Be sure to subscribe so you don't miss any of the exciting generative AI announcements from this year's conference. #Gemini

We often need to run Cloud Run Jobs with different parameters. For example, a job may need to look for files in different Cloud Storage buckets every time it runs.

All the exciting announcements at Google Cloud Next 2024 in Las Vegas left an excitement in the air. Join us as we wrap up the conference by asking attendees what they learned. What will you build?

Opportunity, innovation, and magical! These are just some of the words that come to mind when we asked Google Cloud Next 2024 attendees what Gen AI means to them.

Custom large language models (LLMs) can be fine-tuned and deployed using Google Kubernetes Engine (GKE) and Cloud Run.

In this exciting demo Luka Fontanilla, Custom Engineer Google Cloud, demonstrates a Google LLM with multiple data sources and rich analysis powered by AI.

The industry’s first cloud risk management solution that fuses cloud security and enterprise security operations—supercharged by Mandiant expertise and Gemini at Google scale.

How can regulated industries benefit from the latest generative AI trend?

Make Google part of your security team with security guardrails such as Cloud Identity by enacting the principle of least privilege intel-driven security operations, and cloud security—supercharged

Try out the Hypergame today!

Join Regional Security Architect, Sandy Wenzel, as she detects, investigates, and responds to modern cloud threats at Google scale with threat intelligence and Gemini.

AI practitioners can use the notebook experience to run TPU clusters on GKE to build a cost efficient AI infrastructure and train large scale generative AI models.

Gen AI can play a key role in transforming maintenance workflows. Manufacturing engineers can use natural language for common inquiries, unlocking generative AI features for anyone.

Follow Cameron Peron and Nishant Kohli and they demonstrate hardware accelerators for generative AI on-premises to deliver predictive analytics in real time.