Large language models offer capabilities that overlap with more traditional approaches to natural language processing tasks like translation. Multimodal large language models have an even broader overlap with traditional speech and image models. You can now choose which approach best suits your needs. Here, you will learn about their strengths and weaknesses compared to neural machine translation techniques and receive an overview of the latest advancements in our SOTA Cloud Translation API, combing ease of use with contextual capabilities of generative AI models, to enhance our customers' translations at scale. Experience how new models trained to perform both transcription and translation can go from speech to text in a target language using one large model.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

Generative AI is rapidly growing in business and the popular imagination. Google Cloud was at the forefront of this revolution with the introduction of the Transformer architecture in 2017 and more recently, with the release of Gemini models. This session introduces JAX, a powerful framework and ecosystem for large model development, which we use to develop our Gemini models, and Keras - an easy to use higher level API for deep learning and gen AI.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

AI is all the rage these days, but how can you make practical use of it without spending months of time learning this new technology? This session explains how to build an AI-powered content search tool for your own content in an afternoon, with a useful AI development pattern called retrieval augmented generation (RAG). We will demonstrate an updated version of the Docs Agent project that uses the Gemini API.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

Go beyond traditional DevRel! Learn how to supercharge your developer experience with the combined power of Firebase, Google Cloud, and communication APIs. Discover unconventional strategies, from gamification to controlling devices via messaging apps. Gain actionable insights to fuel community growth.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

U.S. floods cause ~$3B in damage annually. The National Oceanic and Atmospheric Administration predicts changing water levels, giving scientists and managers time to act. However, the massive archive of forecasts is too complex for typical users. Learn how BYU and U of Alabama, with SADA and Google, are using BigQuery, Cloud Run, DataFlow, and API Gateway to make these forecasts accessible for mobile apps, flood-warning systems, and more, addressing crucial concerns like rising river levels or the likelihood of flooding.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

Marsh McLennan runs a complex Apigee Hybrid configuration, with 36 organizations operating in six global data centers. Keeping all of this in sync across production and nonproduction environments is a challenge. While the infrastructure itself is deployed with Terraform, Marsh McLennan wanted to apply the same declarative approach to the entire environment. See how it used Apigee's management APIs to build a state machine to keep the whole system running smoothly, allowing APIs to flow seamlessly from source control through to production.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

Master the modern data stack with 'The Definitive Guide to Data Integration.' This comprehensive book covers the key aspects of data integration, including data sources, storage, transformation, governance, and more. Equip yourself with the knowledge and hands-on skills to manage complex datasets and unlock your data's full potential. What this Book will help me do Understand how to integrate diverse datasets efficiently using modern tools. Develop expertise in designing and implementing robust data integration workflows. Gain insights into real-time data processing and cloud-based data architectures. Learn best practices for data quality, governance, and compliance in integration. Master the use of APIs, workflows, and transformation patterns in practice. Author(s) The authors, None Bonnefoy, None Chaize, Raphaël Mansuy, and Mehdi Tazi, are seasoned experts in data engineering and integration. They bring years of experience in modern data technologies and consulting. Their approachable writing style ensures that readers at various skill levels can grasp complex concepts effectively. Who is it for? This book is ideal for data engineers, architects, analysts, and IT professionals. Whether you're new to data integration or looking to deepen your expertise, this guide caters to individuals seeking to navigate the challenges of the modern data stack.

Whether you’ve been in the developer kitchen for decades or are just taking the plunge to do it yourself, The Complete Developer will show you how to build and implement every component of a modern stack—from scratch. You’ll go from a React-driven frontend to a fully fleshed-out backend with Mongoose, MongoDB, and a complete set of REST and GraphQL APIs, and back again through the whole Next.js stack. The book’s easy-to-follow, step-by-step recipes will teach you how to build a web server with Express.js, create custom API routes, deploy applications via self-contained microservices, and add a reactive, component-based UI. You’ll leverage command line tools and full-stack frameworks to build an application whose no-effort user management rides on GitHub logins. You’ll also learn how to: Work with modern JavaScript syntax, TypeScript, and the Next.js framework Simplify UI development with the React library Extend your application with REST and GraphQL APIs Manage your data with the MongoDB NoSQL database Use OAuth to simplify user management, authentication, and authorization Automate testing with Jest, test-driven development, stubs, mocks, and fakes Whether you’re an experienced software engineer or new to DIY web development, The Complete Developer will teach you to succeed with the modern full stack. After all, control matters. Covers: Docker, Express.js, JavaScript, Jest, MongoDB, Mongoose, Next.js, Node.js, OAuth, React, REST and GraphQL APIs, and TypeScript

Elasticsearch and Kibana added a brand new query language: ES|QL — coming with a new endpoint (_query) and a simpler syntax. It lets you refine your results one step at a time and adds new features like data enrichment and processing right in your query. And you can use it across the Elastic Stack — from the Elasticsearch API to Discover and Alerting in Kibana. But the biggest change is behind the scenes: Using a new compute engine that was built with performance in mind. Join us for a quick overview and a look at syntax and internals.