The Google Generative AI SDK for Dart allows developers to use state-of-the-art Large Language Models (LLMs) to build language applications.
This repository contains a few sample apps. To try them out, follow these steps:
- Change directory to the samples package.
- Export a
$GOOGLE_API_KEY
environment variable with an API key with access to the Gemini generative models, or run the below commands with an environment containing this variable. - Run any sample from the
bin
directory (e.g.,dart bin/simple_text.dart
).
Add a dependency on this repository to the path pkgs/google_generative_ai
.
Once the API is stable the package will be available from pub.
We welcome pre-publish feedback through GitHub issues.
dependencies:
google_generative_ai:
git:
url: git@github.com:google/generative-ai-dart.git
path: pkgs/google_generative_ai
ref: main
final model = GenerativeModel(model: 'gemini-pro', apiKey: apiKey);
final prompt = 'Write a story about a magic backpack.';
final content = [Content.text(prompt)];
final response = await model.generateContent(content);
print(response.text);
Find complete documentation for the Google AI SDKs and the Gemini model in the Google documentation: https://ai.google.dev/docs
Package | Description | Version |
---|---|---|
google_generative_ai | The Google Generative AI SDK for Dart - allows access to state-of-the-art LLMs. | |
samples/dart | Dart samples for package:google_generative_ai . |
|
samples/flutter_app | Flutter sample for package:google_generative_ai . |
See Contributing for more information on contributing to the Generative AI SDK for Dart.
The contents of this repository are licensed under the Apache License, version 2.0.