docs: v0.6.0

docs/docusaurus.config.js

@@ -66,7 +66,7 @@ const config = {
         },
         items: [
           {
-            to: 'docs',
+            to: 'docs/fundamentals/getting-started',
             activeBasePath: 'docs',
             label: 'Docs',
             position: 'right',

docs/src/components/Hero/StartScreen/index.tsx

@@ -24,7 +24,7 @@ const StartScreen = () => {
         <div className={styles.lowerHeading}>
           <div className={styles.buttonContainer}>
             <HomepageButton
-              href="/react-native-executorch/docs"
+              href="/react-native-executorch/docs/fundamentals/getting-started"
               title="Get started"
             />
           </div>

docs/versioned_docs/version-0.4.x/fundamentals/getting-started.md

@@ -1,5 +1,6 @@
 ---
 title: Getting Started
+slug: /
 keywords:
   [
     react native,

docs/versioned_docs/version-0.5.x/01-fundamentals/_category_.json

@@ -1,6 +1,3 @@
 {
-  "label": "Fundamentals",
-  "link": {
-    "type": "generated-index"
-  }
+  "label": "Fundamentals"
 }

docs/versioned_docs/version-0.6.0/01-fundamentals/01-getting-started.md

@@ -0,0 +1,99 @@
+---
+title: Getting Started
+keywords:
+  [
+    react native,
+    react native ai,
+    react native llm,
+    react native qwen,
+    react native llama,
+    react native executorch,
+    executorch,
+    on-device ai,
+    pytorch,
+    mobile ai,
+  ]
+description: 'Get started with React Native ExecuTorch - a framework for running AI models on-device in your React Native applications.'
+---
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+## What is ExecuTorch?
+
+ExecuTorch is a novel AI framework developed by Meta, designed to streamline deploying PyTorch models on a variety of devices, including mobile phones and microcontrollers. This framework enables exporting models into standalone binaries, allowing them to run locally without requiring API calls. ExecuTorch achieves state-of-the-art performance through optimizations and delegates such as Core ML and XNNPACK. It provides a seamless export process with robust debugging options, making it easier to resolve issues if they arise.
+
+## React Native ExecuTorch
+
+React Native ExecuTorch is our way of bringing ExecuTorch into the React Native world. Our API is built to be simple, declarative, and efficient. Plus, we’ll provide a set of pre-exported models for common use cases, so you won’t have to worry about handling exports yourself. With just a few lines of JavaScript, you’ll be able to run AI models (even LLMs 👀) right on your device—keeping user data private and saving on cloud costs.
+
+## Compatibility
+
+React Native Executorch supports only the [New React Native architecture](https://reactnative.dev/architecture/landing-page).
+
+If your app still runs on the old architecture, please consider upgrading to the New Architecture.
+
+## Installation
+
+Installation is pretty straightforward, just use your favorite package manager.
+
+<Tabs>
+  <TabItem value="npm" label="NPM">
+
+    ```
+    npm install react-native-executorch
+    ```
+
+  </TabItem>
+  <TabItem value="pnpm" label="PNPM">
+
+    ```
+    pnpm install react-native-executorch
+    ```
+
+  </TabItem>
+  <TabItem value="yarn" label="YARN">
+
+    ```
+    yarn add react-native-executorch
+    ```
+
+  </TabItem>
+</Tabs>
+
+If you're using bare React Native (instead of a managed Expo project), you also need to install Expo Modules because the underlying implementation relies on expo-file-system. Since expo-file-system is an Expo package, bare React Native projects need **Expo Modules** to properly integrate and use it. The link provided (https://docs.expo.dev/bare/installing-expo-modules/) offers guidance on setting up Expo Modules in a bare React Native environment.
+
+If you plan on using your models via require() instead of fetching them from a url, you also need to add following lines to your `metro.config.js`:
+
+```json
+// metro.config.js
+...
+    defaultConfig.resolver.assetExts.push('pte')
+    defaultConfig.resolver.assetExts.push('bin')
+...
+```
+
+This allows us to use binaries, such as exported models or tokenizers for LLMs.
+
+:::caution
+When using Expo, please note that you need to use a custom development build of your app, not the standard Expo Go app. This is because we rely on native modules, which Expo Go doesn’t support.
+:::
+
+:::info
+Because we are using ExecuTorch under the hood, you won't be able to build iOS app for release with simulator selected as the target device. Make sure to test release builds on real devices.
+:::
+
+Running the app with the library:
+
+```bash
+yarn run expo:<ios | android> -d
+```
+
+## Good reads
+
+If you want to dive deeper into ExecuTorch or our previous work with the framework, we highly encourage you to check out the following resources:
+
+- [ExecuTorch docs](https://pytorch.org/executorch/stable/index.html)
+- [Native code for iOS](https://medium.com/swmansion/bringing-native-ai-to-your-mobile-apps-with-executorch-part-i-ios-f1562a4556e8?source=user_profile_page---------0-------------250189c98ccf---------------)
+- [Native code for Android](https://medium.com/swmansion/bringing-native-ai-to-your-mobile-apps-with-executorch-part-ii-android-29431b6b9f7f?source=user_profile_page---------2-------------b8e3a5cb1c63---------------)
+- [Exporting to Android with XNNPACK](https://medium.com/swmansion/exporting-ai-models-on-android-with-xnnpack-and-executorch-3e70cff51c59?source=user_profile_page---------1-------------b8e3a5cb1c63---------------)

docs/versioned_docs/version-0.6.0/01-fundamentals/02-loading-models.md

@@ -0,0 +1,50 @@
+---
+title: Loading Models
+---
+
+There are three different methods available for loading model files, depending on their size and location.
+
+**1. Load from React Native assets folder (For Files < 512MB)**
+
+```typescript
+useExecutorchModule({
+  modelSource: require('../assets/llama3_2.pte'),
+});
+```
+
+**2. Load from remote URL:**
+
+For files larger than 512MB or when you want to keep size of the app smaller, you can load the model from a remote URL (e.g. HuggingFace).
+
+```typescript
+useExecutorchModule({
+  modelSource: 'https://.../llama3_2.pte',
+});
+```
+
+**3. Load from local file system:**
+
+If you prefer to delegate the process of obtaining and loading model and tokenizer files to the user, you can use the following method:
+
+```typescript
+useExecutorchModule({
+  modelSource: 'file:///var/mobile/.../llama3_2.pte',
+});
+```
+
+:::info
+The downloaded files are stored in documents directory of your application.
+:::
+
+## Example
+
+The following code snippet demonstrates how to load model and tokenizer files using `useLLM` hook:
+
+```typescript
+import { useLLM } from 'react-native-executorch';
+
+const llama = useLLM({
+  modelSource: 'https://.../llama3_2.pte',
+  tokenizerSource: require('../assets/tokenizer.bin'),
+});
+```

docs/versioned_docs/version-0.6.0/01-fundamentals/03-frequently-asked-questions.md

@@ -0,0 +1,39 @@
+---
+title: Frequently Asked Questions
+---
+
+This section is meant to answer some common community inquiries, especially regarding the ExecuTorch runtime or adding your own models. If you can't see an answer to your question, feel free to open up a [discussion](https://github.com/software-mansion/react-native-executorch/discussions/new/choose).
+
+### What models are supported?
+
+Each hook documentation subpage (useClassification, useLLM, etc.) contains a supported models section, which lists the models that are runnable within the library with close to no setup. For running your custom models, refer to `ExecuTorchModule` or `useExecuTorchModule`.
+
+### How can I run my own AI model?
+
+To run your own model, you need to directly access the underlying [ExecuTorch Module API](https://pytorch.org/executorch/stable/extension-module.html). We provide an experimental [React hook](../02-hooks/03-executorch-bindings/useExecutorchModule.md) along with a [TypeScript alternative](../03-typescript-api/03-executorch-bindings/ExecutorchModule.md), which serve as a way to use the aforementioned API without the need of diving into native code. In order to get a model in a format runnable by the runtime, you'll need to get your hands dirty with some ExecuTorch knowledge. For more guides on exporting models, please refer to the [ExecuTorch tutorials](https://pytorch.org/executorch/stable/tutorials/export-to-executorch-tutorial.html). Once you obtain your model in a `.pte` format, you can run it with `useExecuTorchModule` and `ExecuTorchModule`.
+
+### Can you do function calling with useLLM?
+
+If your model supports tool calling (i.e. its chat template can process tools) you can use the method explained on the [useLLM page](../02-hooks/01-natural-language-processing/useLLM.md).
+
+If your model doesn't support it, you can still work around it using context. For details, refer to [this comment](https://github.com/software-mansion/react-native-executorch/issues/173#issuecomment-2775082278).
+
+### Can I use React Native ExecuTorch in bare React Native apps?
+
+To use the library, you need to install Expo Modules first. For a setup guide, refer to [this tutorial](https://docs.expo.dev/bare/installing-expo-modules/). This is because we use Expo File System under the hood to download and manage the model binaries.
+
+### Do you support the old architecture?
+
+The old architecture is not supported and we're currently not planning to add support.
+
+### Can I run GGUF models using the library?
+
+No, as of now ExecuTorch runtime doesn't provide a reliable way to use GGUF models, hence it is not possible.
+
+### Are the models leveraging GPU acceleration?
+
+While it is possible to run some models using Core ML on iOS, which is a backend that utilizes CPU, GPU and ANE, we currently don't have many models exported to Core ML. For Android, the current state of GPU acceleration is pretty limited. As of now, there are attempts of running the models using a Vulkan backend. However the operator support is very limited meaning that the resulting performance is often inferior to XNNPACK. Hence, most of the models use XNNPACK, which is a highly optimized and mature CPU backend that runs on both Android and iOS.
+
+### Does this library support XNNPACK and Core ML?
+
+Yes, all of the backends are linked, therefore the only thing that needs to be done on your end is to export the model with the backend that you're interested in using.

docs/versioned_docs/version-0.6.0/01-fundamentals/_category_.json

@@ -0,0 +1,6 @@
+{
+  "label": "Fundamentals",
+  "link": {
+    "type": "generated-index"
+  }
+}

docs/versioned_docs/version-0.6.0/02-hooks/01-natural-language-processing/_category_.json

@@ -0,0 +1,6 @@
+{
+  "label": "Natural Language Processing",
+  "link": {
+    "type": "generated-index"
+  }
+}