The AI Edge On-Device APIs and SDKs repository provide a set of libraries that allow you to easily build end-to-end applications with Google AI Edge's GenAI pipelines.
The AI Edge On-Device RAG SDK provides fundamental components for constructing a RAG (Retrieval Augmented Generation) pipeline on device. The SDK's modular architecture offers easy-to-use abstractions and a variety of concrete implementations for its key building blocks. The SDK is currently available in Java.
You can find the SDK on GitHub or follow our public documentation to install directly from Maven. We have also published a sample app in this repository.
The AI Edge Function Calling SDK (FC SDK) enables developers to use function calling with on-device LLMs. Function calling lets you connect models to external tools and APIs, enabling models to call specific functions with the necessary parameters to execute real-world actions.
Rather than just generating text, an LLM using the FC SDK can generate a structured call to a function that executes an action, such as searching for up-to-date information, setting alarms, or making reservations.
The AI Edge FC SDK is available for Android and can be run completely on-device with the LLM Inference API. Start using the SDK by following the Android guide, which walks you through a basic implementation of a sample application using function calling.
You can find the SDK on GitHub, along with a sample app.