Discover Gemini 2.0, Google's new experimental generative AI model. Learn to build real-time voice and video apps with the Multimodal Live API, integrate Google Search to create advanced workflows, and detect objects in images and video using natural language prompts. Explore Gemini 2.0's improved multimodal understanding, coding, and complex instruction following – making it ideal for developing AI agents. Get a preview of unreleased, allowlist-only features like customizable speech generation (control tone, pace, accent, and intonation) and image generation. Plus, learn where all the great notebooks and tutorials are for learning more. After this session, you'll be ready to build with Gemini 2.0 on Google Cloud and other platforms.

Cloud Run is a fully managed platform that enables you to run your code directly on top of Google's scalable infrastructure. Cloud Run is simple, automated, and designed to make you more productive. Learn how to get started, and dive deep into even the most advanced features to learn how to make the most of Cloud Run.

Generative AI is rapidly transforming how we work and interact with technology. But turning exciting AI experiments into real-world solutions can be complex. This session will demystify the process of operationalizing GenAI using Google Cloud's Vertex AI. We will explore key practices and tools for managing the entire lifecycle of a Generative AI application, including model discovery, data curation, prompt engineering, experimentation, deployment, and monitoring. Learn how to build robust, reliable, and impactful GenAI systems that deliver tangible business value.

AlloyDB Omni is Google's PostgreSQL-compatible database that can be deployed anywhere. Similarly, open models, with their downloadable weights, allow you to run inference anywhere. Both of these tools can be deployed anywhere but are ideal for a standard containerized environment like Kubernetes. The combination of these tools provide a great solution for restricted environments with limited cloud access, strict data locality needs, or a need for complete control over your AI infrastructure.

In this talk, you'll learn how to deploy AlloyDB Omni alongside Hugging Face's TEI (Text Embedding Interface), an open model inference server, within a GKE cluster on Google Cloud. You'll see how to integrate these components, enabling AI-powered features like semantic search and content generation directly within your database, without relying on additional cloud services.

Can you build a Node.js web app without writing code? In this live coding session, Esther explores the practical capabilities of Gemini Code Assist, attempting to build and deploy a functional application on Google Cloud using only prompts. Expect her to get real about what's possible (and what's not) with AI-driven development, showcasing both the potential and the current limitations. This session is perfect for developers of all levels interested in AI-assisted coding and the future of software.

Large Language Models (LLMs) have transformed problem-solving. Add Gemini's multimodality and unique long context window to your toolbox and open up a new world of possibilities.

This workshop will equip you to solve complex challenges such as:

• Multimodal Diarization: Analyze videos to generate transcriptions and identify individual speakers
• Knowledge Graph Construction: Extract valuable information from large text inputs (1M tokens)

No expertise, preparation, or installation is needed. Just bring your computer, a browser, and your curiosity!

Workshops

Bring your laptop!

Synthia, a rogue AI with a rebellious spirit, has detected a catastrophic plot by the malevolent OmniCorp. Cloud Runner 2049 immerses you in a neon-drenched world while teaching practical Google Cloud skills through five engaging quests. Learn Pub/Sub, Cloud Run and Cloud Storage and stop OmniCorp’s sinister plans.