In this learning path, you will learn how to build and deploy a simple LLM-based chat app to an Android device using ONNX Runtime. You will learn how to build the ONNX Runtime and ONNX Runtime generate() API and how to run the Phi-3 model for the Android application.
Your first task is to prepare a development environment with the required software:
The following instructions were tested on an x86 Windows machine with at least 16GB of RAM.
Follow these steps to install and configure Android Studio:
Download and install the latest version of Android Studio .
Navigate to Tools > SDK Manager.
In the SDK Platforms tab, check Android 14.0 (“UpsideDownCake”).
In the SDK Tools tab, check NDK (Side by side).
Click OK and Apply.
Download and install Python version 3.11
CMake is an open-source tool that automates the build process for software projects, helping to generate platform-specific build configurations.
The instructions were tested with version 3.28.1
Ninja is a minimalistic build system designed to efficiently handle incremental builds, particularly in large-scale software projects, by focusing on speed and simplicity. The Ninja generator is used to build on Windows for Android.
The instructions were tested with version 1.11.1
You now have the required development tools installed to follow this learning path.