From 6a80b474de8a913102936f01ac6c5ce7d4282764 Mon Sep 17 00:00:00 2001 From: Jess Kuras Date: Wed, 23 Sep 2026 20:29:56 +0000 Subject: [PATCH 1/2] docs: update legacy Vertex AI for Firebase references to Firebase AI Logic --- sites/docs/src/content/ai/ai-toolkit/index.md | 29 ++++++++++--------- .../docs/src/content/ai/genui/get-started.md | 5 ++-- .../blog/whats-new-in-flutter-3-44/index.md | 2 +- sites/www/lib/src/pages/ai_page.dart | 8 ++--- 4 files changed, 24 insertions(+), 20 deletions(-) diff --git a/sites/docs/src/content/ai/ai-toolkit/index.md b/sites/docs/src/content/ai/ai-toolkit/index.md index dc0e494603..42be9e5a9a 100644 --- a/sites/docs/src/content/ai/ai-toolkit/index.md +++ b/sites/docs/src/content/ai/ai-toolkit/index.md @@ -65,8 +65,8 @@ dependencies:
  • Configuration -The AI Toolkit supports both the Gemini endpoint (for prototyping) and the -Vertex endpoint (for production). Both require a Firebase project and the +The AI Toolkit supports both the Gemini Developer API (for prototyping) and +Firebase AI Logic production endpoints. Both require a Firebase project and the `firebase_core` package to be initialized, as described in the [Get started with the Gemini API using the Firebase AI Logic SDKs][firebase_ai] docs. @@ -134,7 +134,8 @@ The `FirebaseProvider` class exposes the Firebase AI Logic SDK to the options][options] from which to choose), but you do not provide an API key. All of that is handled as part of the Firebase project. -For production workloads, it's easy to swap in the Firebase Logic AI endpoint: +For production workloads, it's easy to swap in the Firebase AI Logic production +endpoint: ```dart class ChatPage extends StatelessWidget { @@ -145,7 +146,7 @@ class ChatPage extends StatelessWidget { appBar: AppBar(title: const Text(App.title)), body: LlmChatView( provider: FirebaseProvider( - // Use the Vertex AI endpoint + // Use the production endpoint model: FirebaseAI.vertexAI().generativeModel( model: 'gemini-2.5-flash', ), @@ -160,7 +161,7 @@ For a complete example, check out the [gemini.dart] and [vertex.dart][] examples. [options]: - https://firebase.google.com/docs/vertex-ai/gemini-models#available-model-names + https://firebase.google.com/docs/ai-logic/models [gemini.dart]: https://github.com/flutter/ai/blob/main/example/lib/gemini/gemini.dart [vertex.dart]: @@ -215,17 +216,19 @@ attachments, ensure that your app has the necessary permissions: **firebase_options.dart** -To use the [Vertex AI example app][vertex-ex], place your Firebase configuration -details into the `example/lib/firebase_options.dart` file. You can do this with -the `flutterfire CLI` tool as described in the [Add Firebase to your Flutter -app][add-fb] docs **from within the `example` directory**. +To use the [Firebase AI Logic example app][vertex-ex], +place your Firebase configuration details into the +`example/lib/firebase_options.dart` file. +You can do this with the `flutterfire CLI` tool as described in the +[Add Firebase to your Flutter app][add-fb] docs +**from within the `example` directory**. :::note Security considerations for `firebase_options.dart` -If your Flutter app calls Gemini or Vertex AI directly from the client, do not -commit `firebase_options.dart` to a public repository. Anyone could reuse your -app configuration to send requests to your AI endpoint, consuming quota and -potentially causing billing costs. +If your Flutter app calls Gemini APIs directly from the client, +do not commit `firebase_options.dart` to a public repository. +Anyone could reuse your app configuration to send requests to your AI endpoint, +consuming quota and potentially causing billing costs. While this guide shows direct client-side calls for simplicity, for production apps, you should route AI requests through a backend service (for example [Cloud diff --git a/sites/docs/src/content/ai/genui/get-started.md b/sites/docs/src/content/ai/genui/get-started.md index f62adf20fa..c3fdc67728 100644 --- a/sites/docs/src/content/ai/genui/get-started.md +++ b/sites/docs/src/content/ai/genui/get-started.md @@ -57,7 +57,8 @@ Available providers include the following: -To connect to Gemini using the Vertex AI for Firebase SDK, follow these instructions: +To connect to Gemini using the Firebase AI Logic SDK, +follow these instructions: 1. [Create a new Firebase project][] using the Firebase Console. @@ -90,7 +91,7 @@ To connect to Gemini using the Vertex AI for Firebase SDK, follow these instruct } ``` - 6. Create an instance of the Vertex AI for Firebase generative model and wrap it + 6. Create an instance of the Firebase AI Logic generative model and wrap it with your `SurfaceController` and `A2uiTransportAdapter`: ```dart diff --git a/sites/www/content/blog/whats-new-in-flutter-3-44/index.md b/sites/www/content/blog/whats-new-in-flutter-3-44/index.md index 8b0f60ad5a..eedc8f3dd8 100644 --- a/sites/www/content/blog/whats-new-in-flutter-3-44/index.md +++ b/sites/www/content/blog/whats-new-in-flutter-3-44/index.md @@ -205,7 +205,7 @@ In closing, Li-Te challenged us to go beyond walls of text and chatbots, and ins ### Googlebook and peripheral support -Flutter is already equipped to handle the new Googlebook laptop, powered by Gemini. Because Flutter targets Android’s large-screen guidelines, apps handle external hardware inputs naturally. Trackpad scrolling, mouse hover states, right-click menus, and keyboard shortcuts work by default. Because Flutter has mature desktop support across macOS, Windows, and Linux, Flutter apps will feel native and responsive on a Googlebook rather than looking like stretched mobile ports. Existing mobile apps will feel at home on a Googlebook without requiring an extensive rewrite. +Flutter is already equipped to handle the new Googlebook laptop, built with Gemini. Because Flutter targets Android’s large-screen guidelines, apps handle external hardware inputs naturally. Trackpad scrolling, mouse hover states, right-click menus, and keyboard shortcuts work by default. Because Flutter has mature desktop support across macOS, Windows, and Linux, Flutter apps will feel native and responsive on a Googlebook rather than looking like stretched mobile ports. Existing mobile apps will feel at home on a Googlebook without requiring an extensive rewrite. **Learn more**: [Introducing Googlebook, designed for Gemini intelligence](https://blog.google/products-and-platforms/platforms/android/meet-googlebook/) diff --git a/sites/www/lib/src/pages/ai_page.dart b/sites/www/lib/src/pages/ai_page.dart index 0ff2b1de18..e47f8162c5 100644 --- a/sites/www/lib/src/pages/ai_page.dart +++ b/sites/www/lib/src/pages/ai_page.dart @@ -97,7 +97,7 @@ class AiPage extends StatelessComponent { div(classes: 'media', [ img( src: context.asset('images/build-with-ai/vertex-tab.png'), - alt: 'Vertex AI Logo', + alt: 'Firebase AI Logic Logo', ), ]), const div(classes: 'text', [ @@ -112,7 +112,7 @@ class AiPage extends StatelessComponent { ]), a( classes: 'btn', - href: 'https://firebase.google.com/docs/vertex-ai/get-started?platform=flutter', + href: 'https://firebase.google.com/docs/ai-logic/get-started?platform=flutter', target: Target.blank, [.text('Get started')], ), @@ -183,9 +183,9 @@ class AiPage extends StatelessComponent { ), ), FeatureGridItem( - title: 'Build generative AI agents with Vertex AI Agent Builder and Flutter', + title: 'Build generative AI agents with Google Cloud and Flutter', description: - 'Supercharge your generative AI development workflow with Vertex AI and Flutter. ' + 'Supercharge your generative AI development workflow with Gemini Enterprise and Flutter. ' 'Seamlessly integrate with your existing tools and leverage our pre-built components and architectures to accelerate prototyping and deploy production-grade gen AI agents in your apps.', url: 'https://io.google/2024/explore/6f1a4481-7b82-45c9-83eb-caa6e2391152/', icon: context.asset( From b470f8787459dbbef1357a4c9493954786c027d6 Mon Sep 17 00:00:00 2001 From: Jess K <49662805+jesskuras@users.noreply.github.com> Date: Wed, 23 Sep 2026 13:50:11 -0700 Subject: [PATCH 2/2] Update sites/docs/src/content/ai/ai-toolkit/index.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> --- sites/docs/src/content/ai/ai-toolkit/index.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sites/docs/src/content/ai/ai-toolkit/index.md b/sites/docs/src/content/ai/ai-toolkit/index.md index 42be9e5a9a..20dcd4c50b 100644 --- a/sites/docs/src/content/ai/ai-toolkit/index.md +++ b/sites/docs/src/content/ai/ai-toolkit/index.md @@ -65,8 +65,8 @@ dependencies:
  • Configuration -The AI Toolkit supports both the Gemini Developer API (for prototyping) and -Firebase AI Logic production endpoints. Both require a Firebase project and the +The AI Toolkit supports both the Gemini Developer API (for prototyping) and the +Firebase AI Logic production endpoint. Both require a Firebase project and the `firebase_core` package to be initialized, as described in the [Get started with the Gemini API using the Firebase AI Logic SDKs][firebase_ai] docs.