aws-samples · zhu-xiaowei · Nov 7, 2025 · Nov 24, 2025 · Nov 24, 2025 · Nov 27, 2025
diff --git a/README.md b/README.md
@@ -16,17 +16,11 @@ across Android, iOS, and macOS platforms.
 ![](assets/promo.avif)
 
 ### What's New 🔥
+- 🚀 Support Web Search for real-time information retrieval (From v2.7.0).
+- 🚀 Support Create App to generate and preview mini web applications (From v2.7.0).
+- 🚀 Support Image Gallery for browsing and managing generated images (From v2.7.0).
 - 🚀 Support streaming rendering of Mermaid charts (From v2.6.0).
-   <div style="display: flex; flex-direction: 'row'; background-color: #888888;">
-   <img src="assets/animations/mermaid_en.avif" width=48%>
-   <img src="assets/animations/mermaid_save_en.avif" width=48%>
-   </div>
 - 🚀 Support using Bedrock API Key for Amazon Bedrock models (From v2.5.0).
-- 🚀 Support virtual try-on, automatically recognize clothes, pants, shoes and try them on (From v2.5.0).
-- 🚀 Support shortcuts for macOS (From v2.5.0).
-    - Use `Shift + Enter`, `Control + Enter` or `Option + Enter` to add a line break.
-    - Use `⌘ + V` to add images (Screenshot), videos, or documents from your clipboard.
-    - Use `⌘ + N` to opening multiple Mac windows for parallel operations.
 
 ## 📱 Quick Download
 
@@ -36,11 +30,6 @@ across Android, iOS, and macOS platforms.
 
 ## Getting Started with Amazon Bedrock
 
-### Prerequisites
-
-Click [Amazon Bedrock Model access](https://console.aws.amazon.com/bedrock/home#/modelaccess) to enable your models
-access.
-
 ### Configuration
 
 You can choose one of the following two methods for configuration
@@ -64,14 +53,9 @@ You can choose one of the following two methods for configuration
 
 ### Architecture
 
-![](/assets/architecture.avif)
+![](/assets/architecture.png)
 
-By default, we use **AWS App Runner**, which is commonly used to host Python FastAPI servers, offering high performance,
-scalability and low latency.
-
-Alternatively, we provide the option to replace App Runner with **AWS Lambda** using Function URL for a more
-cost-effective
-solution, as shown in
+We use **API Gateway** combined with **AWS Lambda** to enable streaming responses for up to 15 minutes, as shown in
 this [example](https://github.com/awslabs/aws-lambda-web-adapter/tree/main/examples/fastapi-response-streaming).
 
 ### Step 1: Set up your API Key
@@ -107,34 +91,28 @@ this [example](https://github.com/awslabs/aws-lambda-web-adapter/tree/main/examp
    - ECR repository name (or use default: `swift-chat-api`)
    - Image tag (please use default: `latest`)
    - AWS region (the region you want to deploy, e.g.,: `us-east-1`)
-   - Deployment type:
-     - Option 1 (default): **AppRunner** - uses amd64 architecture
-     - Option 2: **Lambda** - uses arm64 architecture
 
 4. The script will build and push the Docker image to your ECR repository.
 
 5. **Important**: Copy the image URI displayed at the end of the script output. You'll need this in the next step.
 
 ### Step 3: Deploy stack and get your API URL
 
-1. Download the CloudFormation template you want to use:
-   - For App Runner: [SwiftChatAppRunner.template](https://github.com/aws-samples/swift-chat/blob/main/server/template/SwiftChatAppRunner.template)
-   - For Lambda: [SwiftChatLambda.template](https://github.com/aws-samples/swift-chat/blob/main/server/template/SwiftChatLambda.template)
+1. Download the CloudFormation template:
+   - Lambda: [SwiftChatLambda.template](https://github.com/aws-samples/swift-chat/blob/main/server/template/SwiftChatLambda.template)
 
 2. Go to [CloudFormation Console](https://console.aws.amazon.com/cloudformation/home#/stacks/create/template?stackName=SwiftChatAPI) and select **Upload a template file** under **Specify template**, then upload the template file you downloaded. (Make sure you are in the same region where your API Key was created.)
 
 3. Click **Next**, On the "Specify stack details" page, provide the following information:
-    - **Stack name**: Keep the default "SwiftChatAPI" or change if needed
     - **ApiKeyParam**: Enter the parameter name you used for storing the API key (e.g., "SwiftChatAPIKey")
     - **ContainerImageUri**: Enter the ECR image URI from Step 2 output
-    - For App Runner, choose an **InstanceTypeParam** based on your needs
 
 4. Click **Next**, Keep the "Configure stack options" page as default, Read the Capabilities and Check the "I
    acknowledge that AWS CloudFormation might create IAM resources" checkbox at the bottom.
 5. Click **Next**, In the "Review and create" Review your configuration and click **Submit**.
 
 Wait about 3–5 minutes for the deployment to finish, then click the CloudFormation stack and go to **Outputs** tab, you
-can find the **API URL** which looks like: `https://xxx.xxx.awsapprunner.com` or `https://xxx.lambda-url.xxx.on.aws`
+can find the **API URL** which looks like: `https://xxx.execute-api.us-east-1.amazonaws.com/v1`
 
 ### Step 4: Open the App and setup with API URL and API Key
 
@@ -271,10 +249,15 @@ can enable the **Use Proxy** option to forward your requests.
 
 ![](assets/animations/english_teacher.avif)
 
-**Rich Markdown Support**: Paragraph, Code Blocks, Tables, LaTeX and More
+**Rich Markdown Support**: Paragraph, Code Blocks, Tables, LaTeX, Mermaid and More
 
 ![](assets/markdown.avif)
 
+<div style="display: flex; flex-direction: 'row'; background-color: #888888;">
+   <img src="assets/animations/mermaid_en.avif" width=48%>
+   <img src="assets/animations/mermaid_save_en.avif" width=48%>
+</div>
+
 We redesigned the UI with optimized font sizes and line spacing for a more elegant and clean presentation.
 All of these features are also seamlessly displayed on Android and macOS with native UI
 
@@ -464,10 +447,14 @@ the [release notes](https://github.com/aws-samples/swift-chat/releases) to see i
 
 ### Upgrade API
 
-- **For AppRunner**: Click and open [App Runner Services](https://console.aws.amazon.com/apprunner/home#/services) page,
-  find and open `swiftchat-api`, click top right **Deploy** button.
-- **For Lambda**: Click and open [Lambda Services](https://console.aws.amazon.com/lambda/home#/functions), find and open
-  your Lambda which start with `SwiftChatLambda-xxx`, click the **Deploy new image** button and click Save.
+1. First, re-run the build script to update the image:
+   ```bash
+   cd server/scripts
+   bash ./push-to-ecr.sh
+   ```
+
+2. Click and open [Lambda Services](https://console.aws.amazon.com/lambda/home#/functions), find and open
+   your Lambda which starts with `SwiftChatAPILambda-xxx`, click the **Deploy new image** button and click Save.
 
 ## Security
 

diff --git a/README_CN.md b/README_CN.md
@@ -15,18 +15,11 @@ SwiftChat 是一款快速响应的 AI 聊天应用，采用 [React Native](https
 ![](assets/promo.avif)
 
 ### 新功能 🔥
-
+- 🚀 支持网络搜索，获取实时信息（自 v2.7.0 起）。
+- 🚀 支持创建应用，生成并预览迷你 Web 应用（自 v2.7.0 起）。
+- 🚀 支持图片画廊，浏览和管理生成的图片（自 v2.7.0 起）。
 - 🚀 支持流式渲染 Mermaid 图表（自 v2.6.0 起）。
-   <div style="display: flex; flex-direction: 'row'; background-color: #888888;">
-   <img src="assets/animations/mermaid.avif" width=48%>
-   <img src="assets/animations/mermaid_save.avif" width=48%>
-   </div>
 - 🚀 支持使用 Bedrock API Key 连接 Amazon Bedrock 模型（自 v2.5.0 起）。
-- 🚀 支持虚拟试衣功能，自动识别衣服、裤子、鞋子并试穿（自 v2.5.0 起）。
-- 🚀 支持 macOS 快捷键操作（自 v2.5.0 起）。
-    - 使用 `Shift + Enter`、`Control + Enter` 或 `Option + Enter` 添加换行。
-    - 使用 `⌘ + V` 从剪贴板添加图片（截图）、视频或文档。
-    - 使用 `⌘ + N` 打开多个 Mac 窗口进行并行操作。
 
 ## 📱 快速下载
 
@@ -36,10 +29,6 @@ SwiftChat 是一款快速响应的 AI 聊天应用，采用 [React Native](https
 
 ## Amazon Bedrock 入门指南
 
-### 前置条件
-
-点击 [Amazon Bedrock 模型访问](https://console.aws.amazon.com/bedrock/home#/modelaccess) 启用您的模型访问权限。
-
 ### 配置
 
 您可以选择以下两种配置方法中的一种
@@ -60,12 +49,9 @@ SwiftChat 是一款快速响应的 AI 聊天应用，采用 [React Native](https
 
 ### 架构
 
-![](/assets/architecture.avif)
-
-默认情况下，我们使用 **AWS App Runner**，它通常用于托管 Python FastAPI 服务器，提供高性能、可扩展性和低延迟。
+![](/assets/architecture.png)
 
-或者，我们提供用 **AWS Lambda** 使用 Function URL 替代 App Runner
-的选项，以获得更具成本效益的解决方案，如此 [示例](https://github.com/awslabs/aws-lambda-web-adapter/tree/main/examples/fastapi-response-streaming)
+我们提供用 **API Gateway** 与 **AWS Lambda** 结合的方式，实现最长15分钟的流式传输，如此 [示例](https://github.com/awslabs/aws-lambda-web-adapter/tree/main/examples/fastapi-response-streaming)
 所示。
 
 ### 步骤 1：设置您的 API 密钥
@@ -100,32 +86,26 @@ SwiftChat 是一款快速响应的 AI 聊天应用，采用 [React Native](https
    - ECR 仓库名称（或使用默认值：`swift-chat-api`）
    - 镜像标签（请使用默认值：`latest`）
    - AWS 区域（填写你希望部署的区域，例如：`us-east-1`）
-   - 部署类型：
-     - 选项 1（默认）：**AppRunner** - 使用 amd64 架构
-     - 选项 2：**Lambda** - 使用 arm64 架构
 
 4. 脚本将构建并推送 Docker 镜像到您的 ECR 仓库。
 
 5. **重要**：复制脚本输出末尾显示的镜像 URI。您将在下一步中需要它。
 
 ### 步骤 3：部署堆栈并获取 API URL
 
-1. 下载您想使用的 CloudFormation 模板：
-   - App Runner：[SwiftChatAppRunner.template](https://github.com/aws-samples/swift-chat/blob/main/server/template/SwiftChatAppRunner.template)
+1. 下载 CloudFormation 模板：
    - Lambda：[SwiftChatLambda.template](https://github.com/aws-samples/swift-chat/blob/main/server/template/SwiftChatLambda.template)
 
 2. 前往 [CloudFormation 控制台](https://console.aws.amazon.com/cloudformation/home#/stacks/create/template?stackName=SwiftChatAPI)，在**指定模板**下选择**上传模板文件**，然后上传您下载的模板文件。（确保您所在的区域与创建 API Key 的区域相同。）
 
 3. 点击 **下一步**，在"指定堆栈详细信息"页面，提供以下信息：
-    - **Stack name**：保持默认的 "SwiftChatAPI" 或根据需要更改
     - **ApiKeyParam**：输入您用于存储 API 密钥的参数名称（例如 "SwiftChatAPIKey"）
     - **ContainerImageUri**：输入步骤 2 输出的 ECR 镜像 URI
-    - 对于 App Runner，根据您的需求选择 **InstanceTypeParam**
 
 4. 点击 **下一步**，保持"配置堆栈选项"页面为默认，阅读功能并勾选底部的"我确认 AWS CloudFormation 可能会创建 IAM 资源"复选框。
 5. 点击 **下一步**，在"审核并创建"中检查您的配置并点击 **提交**。
 
-等待约 3-5 分钟完成部署，然后点击 CloudFormation 堆栈并转到 **输出** 选项卡，您可以找到 **API URL**，类似于：`https://xxx.xxx.awsapprunner.com` 或 `https://xxx.lambda-url.xxx.on.aws`
+等待约 3-5 分钟完成部署，然后点击 CloudFormation 堆栈并转到 **输出** 选项卡，您可以找到 **API URL**，类似于：`https://xxx.execute-api.us-east-1.amazonaws.com/v1`
 
 ### 步骤 4：打开应用并使用 API URL 和 API Key 进行设置
 
@@ -249,7 +229,7 @@ SwiftChat 是一款快速响应的 AI 聊天应用，采用 [React Native](https
 
 <div style="display: flex; flex-direction: 'row'; background-color: #888888;">
 <img src="assets/animations/gen_image.avif" width=24%>
-<img src="assets/animations/virtual_try_on.avif" width=24%>
+<img src="assets/animations/virtual_try_on_demo.avif" width=24%>
 <img src="assets/animations/similar_style.avif" width=24%>
 <img src="assets/animations/remove_background.avif" width=24%>
 </div>
@@ -258,10 +238,15 @@ SwiftChat 是一款快速响应的 AI 聊天应用，采用 [React Native](https
 
 ![](assets/animations/english_teacher.avif)
 
-**丰富的 Markdown 支持**：段落、代码块、表格、LaTeX 等
+**丰富的 Markdown 支持**：段落、代码块、表格、LaTeX、Mermaid 等
 
 ![](assets/markdown.avif)
 
+<div style="display: flex; flex-direction: 'row'; background-color: #888888;">
+   <img src="assets/animations/mermaid.avif" width=48%>
+   <img src="assets/animations/mermaid_save.avif" width=48%>
+</div>
+
 我们重新设计了 UI，优化了字体大小和行间距，提供更优雅、清洁的展示效果。
 所有这些功能也在 Android 和 macOS 上以原生 UI 无缝显示
 
@@ -441,10 +426,14 @@ npm run ios
 
 ### 升级 API
 
-- **对于 AppRunner**：点击打开 [App Runner 服务](https://console.aws.amazon.com/apprunner/home#/services) 页面，找到并打开
-  `swiftchat-api`，点击右上角 **部署** 按钮。
-- **对于 Lambda**：点击打开 [Lambda 服务](https://console.aws.amazon.com/lambda/home#/functions) 页面，找到并打开以
-  `SwiftChatLambda-xxx` 开头的 Lambda，点击 **部署新镜像** 按钮并点击保存。
+1. 首先重新运行构建脚本以更新镜像：
+   ```bash
+   cd server/scripts
+   bash ./push-to-ecr.sh
+   ```
+
+2. 点击打开 [Lambda 服务](https://console.aws.amazon.com/lambda/home#/functions) 页面，找到并打开以
+   `SwiftChatAPILambda-xxx` 开头的 Lambda，点击 **部署新镜像** 按钮并点击保存。
 
 ## 安全
 

diff --git a/assets/architecture.avif b/assets/architecture.avif
diff --git a/assets/architecture.png b/assets/architecture.png
diff --git a/react-native/android/app/src/main/java/com/aws/swiftchat/MainApplication.kt b/react-native/android/app/src/main/java/com/aws/swiftchat/MainApplication.kt
@@ -19,7 +19,7 @@ class MainApplication : Application(), ReactApplication {
             override fun getPackages(): List<ReactPackage> =
                 PackageList(this).packages.apply {
                     // Packages that cannot be autolinked yet can be added manually here, for example:
-                    // add(MyReactNativePackage())
+                    add(NavigationBarPackage())
                 }
 
             override fun getJSMainModuleName(): String = "index"

diff --git a/react-native/android/app/src/main/java/com/aws/swiftchat/NavigationBarModule.kt b/react-native/android/app/src/main/java/com/aws/swiftchat/NavigationBarModule.kt
@@ -0,0 +1,72 @@
+package com.aws.swiftchat
+
+import android.graphics.Color
+import android.os.Build
+import android.view.View
+import com.facebook.react.bridge.ReactApplicationContext
+import com.facebook.react.bridge.ReactContextBaseJavaModule
+import com.facebook.react.bridge.ReactMethod
+
+class NavigationBarModule(reactContext: ReactApplicationContext) : ReactContextBaseJavaModule(reactContext) {
+
+    override fun getName(): String = "NavigationBarModule"
+
+    @ReactMethod
+    fun setImmersiveMode(enabled: Boolean) {
+        val activity = currentActivity ?: return
+
+        activity.runOnUiThread {
+            if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.R) {
+                if (enabled) {
+                    // Make navigation bar transparent and content extend behind it
+                    activity.window.setDecorFitsSystemWindows(false)
+                    activity.window.navigationBarColor = Color.TRANSPARENT
+                } else {
+                    activity.window.setDecorFitsSystemWindows(true)
+                }
+            } else {
+                @Suppress("DEPRECATION")
+                if (enabled) {
+                    activity.window.decorView.systemUiVisibility =
+                        activity.window.decorView.systemUiVisibility or
+                                View.SYSTEM_UI_FLAG_LAYOUT_HIDE_NAVIGATION or
+                                View.SYSTEM_UI_FLAG_LAYOUT_STABLE
+                    activity.window.navigationBarColor = Color.TRANSPARENT
+                } else {
+                    activity.window.decorView.systemUiVisibility =
+                        activity.window.decorView.systemUiVisibility and
+                                View.SYSTEM_UI_FLAG_LAYOUT_HIDE_NAVIGATION.inv() and
+                                View.SYSTEM_UI_FLAG_LAYOUT_STABLE.inv()
+                }
+            }
+        }
+    }
+
+    @ReactMethod
+    fun resetToDefault() {
+        val activity = currentActivity ?: return
+
+        activity.runOnUiThread {
+            // Trigger MainActivity's updateNavigationBarColor
+            if (activity is MainActivity) {
+                // Reset immersive mode first
+                if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.R) {
+                    activity.window.setDecorFitsSystemWindows(true)
+                } else {
+                    @Suppress("DEPRECATION")
+                    activity.window.decorView.systemUiVisibility =
+                        activity.window.decorView.systemUiVisibility and
+                                View.SYSTEM_UI_FLAG_LAYOUT_HIDE_NAVIGATION.inv() and
+                                View.SYSTEM_UI_FLAG_LAYOUT_STABLE.inv()
+                }
+            }
+
+            // Restore default navigation bar color based on theme
+            val isDarkMode = activity.resources.configuration.uiMode and
+                    android.content.res.Configuration.UI_MODE_NIGHT_MASK ==
+                    android.content.res.Configuration.UI_MODE_NIGHT_YES
+
+            activity.window.navigationBarColor = if (isDarkMode) Color.BLACK else Color.WHITE
+        }
+    }
+}
diff --git a/react-native/android/app/src/main/java/com/aws/swiftchat/NavigationBarPackage.kt b/react-native/android/app/src/main/java/com/aws/swiftchat/NavigationBarPackage.kt
@@ -0,0 +1,16 @@
+package com.aws.swiftchat
+
+import com.facebook.react.ReactPackage
+import com.facebook.react.bridge.NativeModule
+import com.facebook.react.bridge.ReactApplicationContext
+import com.facebook.react.uimanager.ViewManager
+
+class NavigationBarPackage : ReactPackage {
+    override fun createNativeModules(reactContext: ReactApplicationContext): List<NativeModule> {
+        return listOf(NavigationBarModule(reactContext))
+    }
+
+    override fun createViewManagers(reactContext: ReactApplicationContext): List<ViewManager<*, *>> {
+        return emptyList()
+    }
+}