Speaker

Guillaume Laforge

Guillaume Laforge

Developer Advocate for Google Cloud

Paris, France

Guillaume Laforge is Developer Advocate for Google Cloud Platform, at day, focusing on serverless technologies, and at night, he is a Java Champion and wears his Apache Groovy hat.

Awards

Area of Expertise

  • Information & Communications Technology

Topics

  • Google Cloud
  • Serverless
  • Java
  • groovy

Generative AI in practice: Concrete LLM use cases in Java, with the PaLM API

Large language models (LLMs) are a powerful new technology that can be used for a variety of tasks, including generating text, translating languages, and writing different kinds of creative content. However, LLMs can be difficult to use, especially for developers who are not proficient in Python, the lingua franca for AI. So what about us Java developers? How can we make use of Generative AI?

This presentation will go through how to use LLMs in Java without the need for Python. We will use the PaLM API, provided by Google Cloud’s Vertex AI services, to perform a variety of tasks, such as searching through documentation, generating kids stories, summarizing content, extracting keywords or entities, and more. In our journey through demos, we’ll discover LangChain4J, a wonderful LLM orchestrator for Java developers that simplifies the implementation of advanced LLM use cases.

Implementing Webhooks backends and clients, not so trivial

Webhooks, we know what they are, right? You’ve probably already used some to be notified of Github commits, to react to text messages received via Twilio, or created a fulfillment for a Dialogflow chatbot to answer users. From the Webhook consumer side, it doesn’t seem complicated to code… On the server-side, is it really just a web API to implement? Hmm… maybe not! Actually, we’ll see that it might be not as simple as it first sounds ! After an introduction on the concept of Webhooks, we’ll create our own callbacks to be notified of events. Then, we’ll go on the other side of the mirror, by creating our own Webhook backend. We’ll study how to deal with client subscription queues, manage all kinds of errors, debug the webhook, handle retries to avoid flooding subscribers, or how to secure those hooks. There’s lots to cover!

Choreography vs Orchestration in Serverless Microservices

We went from a single monolith to a set of microservices that are small, lightweight, and easy to implement. Microservices enable reusability, make it easier to change and scale apps on demand. But they also introduce new problems. How do microservices interact with each other toward a common goal? How do you figure out what went wrong when a business process composed of several microservices fails? Should there be a central orchestrator controlling all interactions between services, or should each service work independently in a loosely coupled way, and only interact through shared events? In this talk, we’ll explore the Choreography vs Orchestration question and see demos of some of the tools that can help.

Learn about Workflows patterns and best practices

One step at a time, that’s how to get started with Google Cloud Workflows! However, writing rock-solid workflows can be trickier than it seems. In this presentation, we’ll share patterns and best practices, tips and tricks, to design your business processes like a pro. How to deploy workflows in multiple environments, how to share and reuse common fragments of workflows, how to version and automate the composition and deployment of your workflows, and much more.

Reuse old smartphones to monitor 3D prints, with WebRTC, WebSockets and Serverless

Monitoring my 3D prints in my basement means climbing lots of stairs back and forth! So here’s my story about how I reused an old smartphone to check the status of my prints. I built a small web app that uses WebRTC to exchange video streams between my broadcasting smartphone and viewers, with WebSockets for signaling, and a serverless platform for easily deploying and hosting my containerized app.

The Developer Advocacy Feedback Loop

Not just about one-way evangelism! Developer Advocacy is about the feedback loop! Dev Advocates talk about their products and services to a technical audience. But, as engineers themselves, they are also alpha testers of those solutions. Developer Advocates advocate for their products, right? Wrong! They first and foremost advocate on behalf of the developers. They help shape the products, thanks to this know-how from the field. Beyond this, they actually advocate for their communities. They represent technical practitioners, listen to their feedback, and influence product teams to implement those needs.

In this presentation, we’ll talk about approaches, tools and solutions that a Developer Advocate can use or put in place in order to create that tight feedback loop (like “friction logs”, “customer empathy sessions”, “office hours”, and more)

A product that is shaped by its users makes for a better product, and happier users make for great customers and themselves advocates of your products! So tighten the loop!

Guillaume Laforge

Developer Advocate for Google Cloud

Paris, France