PluginBench
Skill
Official
Pass
Audit score 90

firebase-ai-logic

firebase/agent-skills

Integrate Gemini API into web apps with Firebase AI Logic—multimodal inference, structured output, and client-side AI without a backend.

What is firebase-ai-logic?

Firebase AI Logic enables developers to add generative AI to web applications using the Gemini API directly from client-side SDKs. It supports text and multimodal inputs (images, audio, video, PDFs), chat sessions, streaming responses, and structured JSON output. Use this skill to set up Firebase AI integration, configure security with App Check, and implement AI features without managing a dedicated backend.

  • Call Gemini models directly from web apps using client-side SDKs
  • Process multimodal inputs: text, images, audio, video, and PDFs
  • Maintain multi-turn conversations with automatic chat history
  • Stream responses for real-time user feedback (typing effect)
  • Generate structured JSON output with enforced schemas
  • Run hybrid on-device and cloud inference with Gemini Nano

How to install firebase-ai-logic

npx skills add https://github.com/firebase/agent-skills --skill firebase-ai-logic
Prerequisites
  • Node.js 16 or later and npm installed
  • Firebase project with at least one app associated
  • Gemini Developer API enabled (automatic via init) or Vertex AI Gemini API for enterprise scale
  • App Check configured with reCAPTCHA Enterprise for production security
Claude Code
Cursor
Windsurf
Cline

How to use firebase-ai-logic

  1. 1.Install the Firebase CLI: npm install -g firebase@latest
  2. 2.List your Firebase projects: npx -y firebase-tools@latest projects:list
  3. 3.Verify an app exists: npx -y firebase-tools@latest apps:list
  4. 4.Initialize AI Logic: npx -y firebase-tools@latest init and select AI Logic
  5. 5.Import the Firebase SDK in your web app code
  6. 6.Call generateContent() or generateContentStream() with text or multimodal inputs
  7. 7.For chat: use startChat() to maintain conversation history
  8. 8.For structured output: define a JSON schema and pass it to the model

Use cases

Good for
  • Build image captioning or object detection features by analyzing user-uploaded images
  • Create chatbots that maintain conversation history across multiple turns
  • Implement real-time AI assistants with streaming text responses
  • Enforce structured data extraction (e.g., JSON forms) from user input
  • Protect API quota and prevent unauthorized access using App Check
Who it's for
  • Web developers building AI-powered applications
  • Mobile and web app teams using Firebase
  • Developers prototyping with the free Gemini Developer API tier
  • Production applications requiring enterprise-grade Vertex AI Gemini API

firebase-ai-logic FAQ

Which Gemini API should I use?

Use the Gemini Developer API by default—it has a free tier for prototyping and pay-as-you-go pricing. Only switch to Vertex AI Gemini API if your application requires enterprise-grade production readiness and scale.

Can I use Firebase AI Logic on mobile (Android/iOS)?

Yes, Firebase AI Logic supports Android (Kotlin/Java), iOS (Swift), Flutter (Dart), and Web (JavaScript). If your platform is unsupported, refer to the Firebase documentation at https://firebase.google.com/docs/ai-logic/get-started.

How do I handle large files (>20 MB)?

Store files larger than 20 MB in Cloud Storage for Firebase and pass their URLs to the Gemini API instead of sending them as inline data to avoid HTTP 413 errors.

Is App Check required?

Yes. App Check is a critical safety requirement to prevent unauthorized clients from using your API quota and accessing backend resources. Set it up with reCAPTCHA Enterprise before production.

Can I update the model version without redeploying my app?

Yes. Use Firebase Remote Config to store and dynamically update model names (e.g., gemini-flash-latest) without deploying new client code.

Full instructions (SKILL.md)

Source of truth, from firebase/agent-skills.


name: firebase-ai-logic description: Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security. version: 1.0.0

Firebase AI Logic Basics

Overview

Firebase AI Logic is a product of Firebase that allows developers to add gen AI to their mobile and web apps using client-side SDKs. You can call Gemini models directly from your app without managing a dedicated backend. Firebase AI Logic, which was previously known as "Vertex AI for Firebase", represents the evolution of Google's AI integration platform for mobile and web developers.

It supports the two Gemini API providers:

  • Gemini Developer API: It has a free tier ideal for prototyping, and pay-as-you-go for production
  • Vertex AI Gemini API: Ideal for scale with enterprise-grade production readiness, requires Blaze plan

Use the Gemini Developer API as a default, and only Vertex AI Gemini API if the application requires it.

Setup & Initialization

Prerequisites

  • Before starting, ensure you have Node.js 16+ and npm installed. Install them if they aren’t already available.
  • Identify the platform the user is interested in building on prior to starting: Android, iOS, Flutter or Web.
  • If their platform is unsupported, Direct the user to Firebase Docs to learn how to set up AI Logic for their application (share this link with the user https://firebase.google.com/docs/ai-logic/get-started)

Installation

The library is part of the standard Firebase Web SDK.

npm install -g firebase@latest

If you're in a firebase directory (with a firebase.json) the currently selected project will be marked with "current" using this command:

npx -y firebase-tools@latest projects:list

Ensure there's at least one app associated with the current project

npx -y firebase-tools@latest apps:list

Initialize AI logic SDK with the init command

npx -y firebase-tools@latest init # Choose AI logic

This will automatically enable the Gemini Developer API in the Firebase console.

More info in Firebase AI Logic Getting Started

Core Capabilities

Text-Only Generation

Multimodal (Text + Images/Audio/Video/PDF input)

Firebase AI Logic allows Gemini models to analyze image files directly from your app. This enables features like creating captions, answering questions about images, detecting objects, and categorizing images. Beyond images, Gemini can analyze other media types like audio, video, and PDFs by passing them as inline data with their MIME type. For files larger than 20 megabytes (which can cause HTTP 413 errors as inline data), store them in Cloud Storage for Firebase and pass their URLs to the Gemini Developer API.

Chat Session (Multi-turn)

Maintain history automatically using startChat.

Streaming Responses

To improve the user experience by showing partial results as they arrive (like a typing effect), use generateContentStream instead of generateContent for faster display of results.

Generate Images with Nano Banana

  • Start with Gemini for most use cases, and choose Imagen for specialized tasks where image quality and specific styles are critical. (Example: gemini-2.5-flash-image)
  • Requires an upgraded Blaze pay-as-you-go billing plan.

Search Grounding with the built in googleSearch tool

Supported Platforms and Frameworks

Supported Platforms and Frameworks include Kotlin and Java for Android, Swift for iOS, JavaScript for web apps, Dart for Flutter, and C Sharp for Unity.

Advanced Features

Structured Output (JSON)

Enforce a specific JSON schema for the response.

On-Device AI (Hybrid)

Hybrid on-device inference for web apps, where the Firebase Javascript SDK automatically checks for Gemini Nano's availability (after installation) and switches between on-device or cloud-hosted prompt execution. This requires specific steps to enable model usage in the Chrome browser, more info in the hybrid-on-device-inference documentation.

Security & Production

App Check

[!WARNING] Critical Safety Requirement: In order to use AI Logic safely, you MUST set up App Check on your app. This prevents unauthorized clients from using your API quota and accessing your backend resources.

See App Check with reCAPTCHA Enterprise for setup instructions.

Remote Config

Consider that you do not need to hardcode model names (e.g., gemini-flash-lite-latest). Use Firebase Remote Config to update model versions dynamically without deploying new client code. See Changing model names remotely

Initialization Code References

Language, Framework, PlatformGemini API providerContext URL
Web Modular APIGemini Developer API (Developer API)firebase://docs/ai-logic/get-started

Always use the most recent version of Gemini (gemini-flash-latest) unless another model is requested by the docs or the user. DO NOT USE gemini-1.5-flash

References

Web SDK code examples and usage patterns