Caution
The Google AI SDK for Swift is recommended for prototyping only. If you plan to enable billing, we strongly recommend that you use a backend SDK to access the Google AI Gemini API. You risk potentially exposing your API key to malicious actors if you embed your API key directly in your Swift app or fetch it remotely at runtime.
The Google AI SDK for Swift enables developers to use Google's state-of-the-art generative AI models (like Gemini) to build AI-powered features and applications. This SDK supports use cases like:
- Generate text from text-only input
- Generate text from text-and-images input (multimodal)
- Build multi-turn conversations (chat)
For example, with just a few lines of code, you can access Gemini's multimodal capabilities to generate text from text-and-image input:
let model = GenerativeModel(name: "gemini-1.5-flash-latest", apiKey: "YOUR_API_KEY")
let cookieImage = UIImage(...)
let prompt = "Do these look store-bought or homemade?"
let response = try await model.generateContent(prompt, cookieImage)This repository contains a sample app demonstrating how the SDK can access and utilize the Gemini model for various use cases.
To try out the sample app, follow these steps:
-
Check out this repository.
git clone https://github.com/google/generative-ai-swift -
Obtain an API key to use with the Google AI SDKs.
-
Open and build the sample app in the
Examplesfolder of this repo. -
Run the app once to ensure the build script generates an empty
GenerativeAI-Info.plistfile -
Paste your API key into the
API_KEYproperty in theGenerativeAI-Info.plistfile. -
Run the app.
Add generative-ai-swift to your Xcode project
using Swift Package Manager.
For detailed instructions, you can find a quickstart for the Google AI SDK for Swift in the Google documentation.
This quickstart describes how to add your API key and the Swift package to your app, initialize the model, and then call the API to access the model. It also describes some additional use cases and features, like streaming, counting tokens, and controlling responses.
To enable additional logging in the Xcode console, including a cURL command and raw stream
response for each model request, add -GoogleGenerativeAIDebugLogEnabled as
Arguments Passed On Launch in the Xcode scheme.
A command line tool is available to experiment with Gemini model requests via Xcode or the command line:
open Examples/GenerativeAICLI/Package.swift- Run in Xcode and examine the console to see the options.
- Edit the scheme's
Arguments Passed On Launchwith the desired options.
Find complete documentation for the Google AI SDKs and the Gemini model in the Google documentation: https://ai.google.dev/docs
See Contributing for more information on contributing to the Google AI SDK for Swift.
Important
The PaLM API is deprecated for use with Google AI services and tools (but not for Vertex AI). Learn more about this deprecation, its timeline, and how to migrate to use Gemini in the PaLM API deprecation guide.
If you're using the PaLM SDK for Swift, review the information below to continue using the deprecated PaLM SDK until you've migrated to the new version that allows you to use Gemini.
-
To continue using PaLM models, make sure your app depends on version
0.3.0up to the next minor version (0.4.0) ofgenerative-ai-swift. -
When you're ready to use Gemini models, migrate your code to the Gemini API and update your app's
generative-ai-swiftdependency to version0.4.0or higher.
To see the PaLM documentation and code, go to the
palm branch.