merge dockerfile

Author: alexwarm

.env.example

@@ -40,14 +40,14 @@ ANONYMIZED_TELEMETRY=false
 # LogLevel: Set to debug to enable verbose logging, set to result to get results only. Available: result | debug | info
 BROWSER_USE_LOGGING_LEVEL=info
 
-# Chrome settings
-CHROME_PATH=
-CHROME_USER_DATA=
-CHROME_DEBUGGING_PORT=9222
-CHROME_DEBUGGING_HOST=localhost
+# Browser settings
+BROWSER_PATH=
+BROWSER_USER_DATA=
+BROWSER_DEBUGGING_PORT=9222
+BROWSER_DEBUGGING_HOST=localhost
 # Set to true to keep browser open between AI tasks
-CHROME_PERSISTENT_SESSION=false
-CHROME_CDP=
+KEEP_BROWSER_OPEN=true
+BROWSER_CDP=
 # Display settings
 # Format: WIDTHxHEIGHTxDEPTH
 RESOLUTION=1920x1080x24

Dockerfile

@@ -1,5 +1,8 @@
 FROM python:3.11-slim
 
+# Set platform for multi-arch builds (Docker Buildx will set this)
+ARG TARGETPLATFORM
+
 # Install system dependencies
 RUN apt-get update && apt-get install -y \
     wget \
@@ -28,7 +31,6 @@ RUN apt-get update && apt-get install -y \
     fonts-liberation \
     dbus \
     xauth \
-    xvfb \
     x11vnc \
     tigervnc-tools \
     supervisor \
@@ -47,40 +49,52 @@ RUN git clone https://github.com/novnc/noVNC.git /opt/novnc \
     && git clone https://github.com/novnc/websockify /opt/novnc/utils/websockify \
     && ln -s /opt/novnc/vnc.html /opt/novnc/index.html
 
-# Set platform for ARM64 compatibility
-ARG TARGETPLATFORM=linux/amd64
-
 # Set up working directory
 WORKDIR /app
 
 # Copy requirements and install Python dependencies
 COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+# Ensure 'patchright' is in your requirements.txt or install it directly
+# RUN pip install --no-cache-dir -r requirements.txt patchright # If not in requirements
+RUN pip install --no-cache-dir -r requirements.txt # Assuming patchright is in requirements.txt
+RUN pip install --no-cache-dir patchright # Or install it explicitly
+
+# Install Patchright browsers and dependencies
+# Patchright documentation suggests PLAYWRIGHT_BROWSERS_PATH is still relevant
+# or that Patchright installs to a similar default location that Playwright would.
+# Let's assume Patchright respects PLAYWRIGHT_BROWSERS_PATH or its default install location is findable.
+ENV PLAYWRIGHT_BROWSERS_PATH=/ms-browsers
+RUN mkdir -p $PLAYWRIGHT_BROWSERS_PATH
+
+# Install recommended: Google Chrome (instead of just Chromium for better undetectability)
+# The 'patchright install chrome' command might download and place it.
+# The '--with-deps' equivalent for patchright install is to run 'patchright install-deps chrome' after.
+RUN patchright install chrome
+RUN patchright install-deps chrome
 
-# Install Playwright and browsers with system dependencies
-ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
-RUN playwright install --with-deps chromium
-RUN playwright install-deps
+# Alternative: Install Chromium if Google Chrome is problematic in certain environments
+RUN patchright install chromium
+RUN patchright install-deps chromium
 
 # Copy the application code
 COPY . .
 
-# Set environment variables
+# Set environment variables (Updated Names)
 ENV PYTHONUNBUFFERED=1
 ENV BROWSER_USE_LOGGING_LEVEL=info
-ENV CHROME_PATH=/ms-playwright/chromium-*/chrome-linux/chrome
+# BROWSER_PATH will be determined by Patchright installation, supervisord will find it.
 ENV ANONYMIZED_TELEMETRY=false
 ENV DISPLAY=:99
 ENV RESOLUTION=1920x1080x24
-ENV VNC_PASSWORD=vncpassword
-ENV CHROME_PERSISTENT_SESSION=true
+ENV VNC_PASSWORD=youvncpassword
+ENV KEEP_BROWSER_OPEN=true
 ENV RESOLUTION_WIDTH=1920
 ENV RESOLUTION_HEIGHT=1080
 
 # Set up supervisor configuration
 RUN mkdir -p /var/log/supervisor
 COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
 
-EXPOSE 7788 6080 5901
+EXPOSE 7788 6080 5901 9222
 
-CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]
+CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

Dockerfile.arm64

@@ -23,10 +23,6 @@ We would like to officially thank [WarmShao](https://github.com/warmshao) for hi
 
 ## Installation Guide
 
-### Prerequisites
-- Python 3.11 or higher
-- Git (for cloning the repository)
-
 ### Option 1: Local Installation
 
 Read the [quickstart guide](https://docs.browser-use.com/quickstart#prepare-the-environment) or follow the steps below to get started.
@@ -65,10 +61,13 @@ Install Python packages:
 uv pip install -r requirements.txt
 ```
 
-Install Browsers in Playwright:
-You can install specific browsers by running:
+Install Browsers in Patchright. 
+```bash
+patchright install
+```
+Or you can install specific browsers by running:
 ```bash
-patchright install chromium
+patchright install chromium --with-deps --no-shell
 ```
 
 #### Step 4: Configure Environment
@@ -83,6 +82,42 @@ cp .env.example .env
 ```
 2. Open `.env` in your preferred text editor and add your API keys and other settings
 
+#### Local Setup
+1.  **Run the WebUI:**
+    After completing the installation steps above, start the application:
+    ```bash
+    python webui.py --ip 127.0.0.1 --port 7788
+    ```
+2. WebUI options:
+   - `--ip`: The IP address to bind the WebUI to. Default is `127.0.0.1`.
+   - `--port`: The port to bind the WebUI to. Default is `7788`.
+   - `--theme`: The theme for the user interface. Default is `Ocean`.
+     - **Default**: The standard theme with a balanced design.
+     - **Soft**: A gentle, muted color scheme for a relaxed viewing experience.
+     - **Monochrome**: A grayscale theme with minimal color for simplicity and focus.
+     - **Glass**: A sleek, semi-transparent design for a modern appearance.
+     - **Origin**: A classic, retro-inspired theme for a nostalgic feel.
+     - **Citrus**: A vibrant, citrus-inspired palette with bright and fresh colors.
+     - **Ocean** (default): A blue, ocean-inspired theme providing a calming effect.
+   - `--dark-mode`: Enables dark mode for the user interface.
+3.  **Access the WebUI:** Open your web browser and navigate to `http://127.0.0.1:7788`.
+4.  **Using Your Own Browser(Optional):**
+    - Set `CHROME_PATH` to the executable path of your browser and `CHROME_USER_DATA` to the user data directory of your browser. Leave `CHROME_USER_DATA` empty if you want to use local user data.
+      - Windows
+        ```env
+         CHROME_PATH="C:\Program Files\Google\Chrome\Application\chrome.exe"
+         CHROME_USER_DATA="C:\Users\YourUsername\AppData\Local\Google\Chrome\User Data"
+        ```
+        > Note: Replace `YourUsername` with your actual Windows username for Windows systems.
+      - Mac
+        ```env
+         CHROME_PATH="/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"
+         CHROME_USER_DATA="/Users/YourUsername/Library/Application Support/Google/Chrome"
+        ```
+    - Close all Chrome windows
+    - Open the WebUI in a non-Chrome browser, such as Firefox or Edge. This is important because the persistent browser context will use the Chrome data when running the agent.
+    - Check the "Use Own Browser" option within the Browser Settings.
+
 ### Option 2: Docker Installation
 
 #### Prerequisites
@@ -118,95 +153,12 @@ docker compose up --build
 CHROME_PERSISTENT_SESSION=true docker compose up --build
 ```
 
-
 4. Access the Application:
 - Web Interface: Open `http://localhost:7788` in your browser
 - VNC Viewer (for watching browser interactions): Open `http://localhost:6080/vnc.html`
   - Default VNC password: "youvncpassword"
   - Can be changed by setting `VNC_PASSWORD` in your `.env` file
 
-## Usage
-
-### Local Setup
-1.  **Run the WebUI:**
-    After completing the installation steps above, start the application:
-    ```bash
-    python webui.py --ip 127.0.0.1 --port 7788
-    ```
-2. WebUI options:
-   - `--ip`: The IP address to bind the WebUI to. Default is `127.0.0.1`.
-   - `--port`: The port to bind the WebUI to. Default is `7788`.
-   - `--theme`: The theme for the user interface. Default is `Ocean`.
-     - **Default**: The standard theme with a balanced design.
-     - **Soft**: A gentle, muted color scheme for a relaxed viewing experience.
-     - **Monochrome**: A grayscale theme with minimal color for simplicity and focus.
-     - **Glass**: A sleek, semi-transparent design for a modern appearance.
-     - **Origin**: A classic, retro-inspired theme for a nostalgic feel.
-     - **Citrus**: A vibrant, citrus-inspired palette with bright and fresh colors.
-     - **Ocean** (default): A blue, ocean-inspired theme providing a calming effect.
-   - `--dark-mode`: Enables dark mode for the user interface.
-3.  **Access the WebUI:** Open your web browser and navigate to `http://127.0.0.1:7788`.
-4.  **Using Your Own Browser(Optional):**
-    - Set `CHROME_PATH` to the executable path of your browser and `CHROME_USER_DATA` to the user data directory of your browser. Leave `CHROME_USER_DATA` empty if you want to use local user data.
-      - Windows
-        ```env
-         CHROME_PATH="C:\Program Files\Google\Chrome\Application\chrome.exe"
-         CHROME_USER_DATA="C:\Users\YourUsername\AppData\Local\Google\Chrome\User Data"
-        ```
-        > Note: Replace `YourUsername` with your actual Windows username for Windows systems.
-      - Mac
-        ```env
-         CHROME_PATH="/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"
-         CHROME_USER_DATA="/Users/YourUsername/Library/Application Support/Google/Chrome"
-        ```
-    - Close all Chrome windows
-    - Open the WebUI in a non-Chrome browser, such as Firefox or Edge. This is important because the persistent browser context will use the Chrome data when running the agent.
-    - Check the "Use Own Browser" option within the Browser Settings.
-5. **Keep Browser Open(Optional):**
-    - Set `CHROME_PERSISTENT_SESSION=true` in the `.env` file.
-
-### Docker Setup
-1. **Environment Variables:**
-   - All configuration is done through the `.env` file
-   - Available environment variables:
-     ```
-     # LLM API Keys
-     OPENAI_API_KEY=your_key_here
-     ANTHROPIC_API_KEY=your_key_here
-     GOOGLE_API_KEY=your_key_here
-
-     # Browser Settings
-     CHROME_PERSISTENT_SESSION=true   # Set to true to keep browser open between AI tasks
-     RESOLUTION=1920x1080x24         # Custom resolution format: WIDTHxHEIGHTxDEPTH
-     RESOLUTION_WIDTH=1920           # Custom width in pixels
-     RESOLUTION_HEIGHT=1080          # Custom height in pixels
-
-     # VNC Settings
-     VNC_PASSWORD=your_vnc_password  # Optional, defaults to "vncpassword"
-     ```
-
-2. **Platform Support:**
-   - Supports both AMD64 and ARM64 architectures
-   - For ARM64 systems (e.g., Apple Silicon Macs), the container will automatically use the appropriate image
-
-3. **Browser Persistence Modes:**
-   - **Default Mode (CHROME_PERSISTENT_SESSION=false):**
-     - Browser opens and closes with each AI task
-     - Clean state for each interaction
-     - Lower resource usage
-
-   - **Persistent Mode (CHROME_PERSISTENT_SESSION=true):**
-     - Browser stays open between AI tasks
-     - Maintains history and state
-     - Allows viewing previous AI interactions
-     - Set in `.env` file or via environment variable when starting container
-
-4. **Viewing Browser Interactions:**
-   - Access the noVNC viewer at `http://localhost:6080/vnc.html`
-   - Enter the VNC password (default: "vncpassword" or what you set in VNC_PASSWORD)
-   - Direct VNC access available on port 5900 (mapped to container port 5901)
-   - You can now see all browser interactions in real-time
-
 5. **Container Management:**
    ```bash
    # Start with persistent browser