Discover how Firebase GenKit can revolutionize the way Flutter developers create applications by seamlessly integrating cutting-edge generative AI capabilities. From intelligent chatbots and personalized recommendations to dynamic content generation and workflow automation, GenKit enables you to harness the power of leading AI models such as Claude, ChatGPT, Gemini, Gemma, and more—all tailored to your app's unique needs.

GenKit provides unparalleled flexibility, allowing developers to utilize multiple AI models simultaneously. You can chain models together, using the output of one as the prompt for another, or dynamically switch between models based on your app's requirements. This capability opens up endless possibilities for crafting sophisticated, context-aware features.

This talk will focus on how Flutter developers can work with GenKit locally, testing and debugging AI-driven functionality with ease, and how these features can be seamlessly deployed using Firebase Cloud Functions or Cloud Run, ensuring scalability and reliability in production.

Join the talk to explore practical use cases, step-by-step setup and deployment techniques, and actionable insights into leveraging multiple AI models with GenKit to create smarter, more engaging Flutter applications. Let's build the future of app development, together!

In this talk, we'll dive into the exciting world of Gemma, a groundbreaking family of open AI models by Google. We'll explore how you can leverage Gemma's capabilities to build innovative Mobile and Web projects using Flutter. One of these capabilities is running on your mobile device or browser locally, without an internet connection, without cloud bills and without privacy concerns

Key takeaway:

• Understand the core functionalities and architectures of Gemma, lightweight, state-of-the-art models
• Discover the advantages of using Gemma, including its open-source nature, versatility across tasks, and on-device/browser capabilities
• Discover practical methods for integrating Gemma into your Flutter Mobile and Web applications, unlocking new possibilities for user interaction and functionality
• Explore different approaches to fine-tuning of Gemma model, that let you achieve better results on a wide number of tasks. Once a model has been fine-tuned, you won't need to provide as many examples in the prompt.
• Explore the different types of Gemma (CodeGemma, PaliGemma, etc.), the purposes for which they can be used, how Gemma differs from Gemini, and explore the distinct characteristics of each model, including size, performance, and optimal use cases
• Discover Gemma alternatives that you can use on-device and in the browser
• As a bonus, we'll take a look at Llama, exploring its features and how it compares to Gemma.

PS: Additionally I'll introduce the Flutter plugin that I created and currently maintain for the integration of Gemma into Flutter apps

1. What exciting developments and features can we expect in Flutter over the next year?

2. Reflecting on Flutter’s journey, what have been the most game-changing moments and milestones?

3. Have there been any ambitious ideas or experimental features that didn’t make it to production? What lessons were learned from them?

4. In what scenarios might companies or developers consider technologies other than Flutter, and how do you see Flutter adapting or responding to such scenarios?

5. Could you describe any scenarios or use cases where Flutter might not be the optimal choice, and what would you suggest developers consider in those cases?

6. What advice would you give developers or teams who are just starting their journey with Flutter today?