# Build and Run Android chat app

## In this learning path

- [Introduction](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/)
- [Create a development environment](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/1-dev-env-setup/)
- [ExecuTorch Setup](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/2-executorch-setup/)
- [Understanding Llama models](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/3-understanding-llama-models/)
- [Prepare Llama models for ExecuTorch](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/4-prepare-llama-models/)
- [Run Benchmark on Android phone](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/5-run-benchmark-on-android/)
- [Build and Run Android chat app](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/6-build-android-chat-app/)
- [Next Steps](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/_next-steps/)

In this section, you will use a Android demo application to demonstrate local inference with ExecuTorch.

## Build the Android Archive (AAR)

1. Open a terminal window and navigate to the root directory of the `executorch` repository.
2. If you haven’t already, set the following environment variables:
   ```bash
   export ANDROID_NDK=$ANDROID_HOME/ndk/29.0.14206865/
   export ANDROID_ABI=arm64-v8a
   export ANDROID_SDK=$ANDROID_HOME
   ```
   > **Note:** `<path_to_android_ndk>` is the root for the NDK, which is usually under `~/Library/Android/sdk/ndk/XX.Y.ZZZZZ` for macOS, and contains NOTICE and README.md. Make sure you can confirm `<path_to_android_ndk>/build/cmake/android.toolchain.cmake` is available for CMake to cross-compile.

3. Run the following command to set up the required JNI library:
   ```bash
   sh scripts/build_android_library.sh
   ```

## Getting models

Make sure the exported model and tokenizer are copied to the Android phone:

### Option 1: using adb

1. Check if the files are available on the phone:
   ```bash
   adb shell "ls -la /data/local/tmp/llama/"
   ```
2. If not, copy them:
   ```bash
   adb shell mkdir -p /data/local/tmp/llama
   adb push <model.pte> /data/local/tmp/llama/
   adb push <tokenizer.bin> /data/local/tmp/llama/
   ```

### Option 2: Using Android Studio

1. Use Android Studio’s device explorer to look for the model files.

![Device Explorer](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/device-explorer.webp)
*Figure 1. Android Studio Device Explorer*

2. Upload the files.

If the files are not on the device, use the device explorer to copy them.

![Files Upload](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/device-explorer-upload.webp)
*Figure 2. Android Studio upload files using Device Explorer*

## Build the Android Package Kit

Before starting, you need to obtain the example app by cloning `executorch-examples`:
```bash
git clone https://github.com/meta-pytorch/executorch-examples.git
```

### Option 1: Using Android Studio

This is the recommended option.

1. Open Android Studio and select **Open an existing Android Studio project** and navigate to open `executorch-examples/llm/android/LlamaDemo`.
2. Run the app (^R). This builds and launches the app on the phone.

### Option 2: Command line

Without Android Studio UI, you can run gradle directly to build the app. You need to set up the Android SDK path and invoke gradle. Navigate to the newly cloned `executorch-examples` repository:
```bash
pushd llm/android/LlamaDemo
./gradlew :app:installDebug
popd
```

You should now see a running app on your phone that looks like this:

![First example prompt](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/example-prompt-1.png)
![Second example prompt](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/example-prompt-2.png)