fix dockerfile

Author: vvincent1234

.dockerignore

@@ -1,2 +1,5 @@
 data
-tmp
+tmp
+results
+
+.env

Dockerfile

@@ -2,6 +2,7 @@ FROM python:3.11-slim
 
 # Set platform for multi-arch builds (Docker Buildx will set this)
 ARG TARGETPLATFORM
+ARG NODE_MAJOR=20
 
 # Install system dependencies
 RUN apt-get update && apt-get install -y \
@@ -42,22 +43,33 @@ RUN apt-get update && apt-get install -y \
     fonts-dejavu \
     fonts-dejavu-core \
     fonts-dejavu-extra \
+    vim \
     && rm -rf /var/lib/apt/lists/*
 
 # Install noVNC
 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
 
+# Install Node.js using NodeSource PPA
+RUN mkdir -p /etc/apt/keyrings \
+    && curl -fsSL https://deb.nodesource.com/gpgkey/nodesource-repo.gpg.key | gpg --dearmor -o /etc/apt/keyrings/nodesource.gpg \
+    && echo "deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesource.com/node_$NODE_MAJOR.x nodistro main" | tee /etc/apt/sources.list.d/nodesource.list \
+    && apt-get update \
+    && apt-get install nodejs -y \
+    && rm -rf /var/lib/apt/lists/*
+
+# Verify Node.js and npm installation (optional, but good for debugging)
+RUN node -v && npm -v && npx -v
+
 # Set up working directory
 WORKDIR /app
 
 # Copy requirements and install Python dependencies
 COPY 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
+RUN pip install --no-cache-dir -r requirements.txt
 
 # Install Patchright browsers and dependencies
 # Patchright documentation suggests PLAYWRIGHT_BROWSERS_PATH is still relevant
@@ -69,32 +81,19 @@ 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
+RUN patchright install chrome --with-deps
 
 # Alternative: Install Chromium if Google Chrome is problematic in certain environments
-RUN patchright install chromium
-RUN patchright install-deps chromium
+RUN patchright install chromium --with-deps
 
 # Copy the application code
 COPY . .
 
-# Set environment variables (Updated Names)
-ENV PYTHONUNBUFFERED=1
-ENV BROWSER_USE_LOGGING_LEVEL=info
-# 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=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 9222
 
-CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]
+CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]
+#CMD ["/bin/bash"]

README.md

@@ -63,11 +63,11 @@ uv pip install -r requirements.txt
 
 Install Browsers in Patchright. 
 ```bash
-patchright install
+patchright install --with-deps
 ```
 Or you can install specific browsers by running:
 ```bash
-patchright install chromium --with-deps --no-shell
+patchright install chromium --with-deps
 ```
 
 #### Step 4: Configure Environment
@@ -82,25 +82,24 @@ cp .env.example .env
 ```
 2. Open `.env` in your preferred text editor and add your API keys and other settings
 
-#### Local Setup
+#### Step 5: Enjoy the web-ui
 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. **Access the WebUI:** Open your web browser and navigate to `http://127.0.0.1:7788`.
 3. **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.
+    - Set `BROWSER_PATH` to the executable path of your browser and `BROWSER_USER_DATA` to the user data directory of your browser. Leave `BROWSER_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"
+         BROWSER_PATH="C:\Program Files\Google\Chrome\Application\chrome.exe"
+         BROWSER_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"
+         BROWSER_PATH="/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"
+         BROWSER_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.
@@ -113,14 +112,14 @@ cp .env.example .env
   - [Docker Desktop](https://www.docker.com/products/docker-desktop/) (For Windows/macOS)
   - [Docker Engine](https://docs.docker.com/engine/install/) and [Docker Compose](https://docs.docker.com/compose/install/) (For Linux)
 
-#### Installation Steps
-1. Clone the repository:
+#### Step 1: Clone the Repository
 ```bash
 git clone https://github.com/browser-use/web-ui.git
 cd web-ui
 ```
 
-2. Create and configure environment file:
+#### Step 2: Configure Environment
+1. Create a copy of the example environment file:
 - Windows (Command Prompt):
 ```bash
 copy .env.example .env
@@ -129,25 +128,23 @@ copy .env.example .env
 ```bash
 cp .env.example .env
 ```
-Edit `.env` with your preferred text editor and add your API keys
+2. Open `.env` in your preferred text editor and add your API keys and other settings
 
-3. Run with Docker:
+#### Step 3: Docker Build and Run
 ```bash
-# Build and start the container with default settings (browser closes after AI tasks)
 docker compose up --build
 ```
+For ARM64 systems (e.g., Apple Silicon Macs), please run follow command:
 ```bash
-# Or run with persistent browser (browser stays open between AI tasks)
-CHROME_PERSISTENT_SESSION=true docker compose up --build
+TARGETPLATFORM=linux/arm64 docker compose up --build
 ```
 
-4. Access the Application:
-- Web Interface: Open `http://localhost:7788` in your browser
+#### Step 4: Enjoy the web-ui and vnc
+- Web-UI: 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
 
-
 ## Changelog
 - [x] **2025/01/26:** Thanks to @vvincent1234. Now browser-use-webui can combine with DeepSeek-r1 to engage in deep thinking!
 - [x] **2025/01/10:** Thanks to @casistack. Now we have Docker Setup option and also Support keep browser open between tasks.[Video tutorial demo](https://github.com/browser-use/web-ui/issues/1#issuecomment-2582511750).

docker-compose.yml

@@ -1,4 +1,5 @@
 services:
+  # debug: docker compose run --rm -it browser-use-webui bash
   browser-use-webui:
     build:
       context: .
@@ -11,7 +12,7 @@ services:
       - "5901:5901"
       - "9222:9222"
     environment:
-      # LLM API Keys & Endpoints (Your existing list)
+      # LLM API Keys & Endpoints
       - OPENAI_ENDPOINT=${OPENAI_ENDPOINT:-https://api.openai.com/v1}
       - OPENAI_API_KEY=${OPENAI_API_KEY:-}
       - ANTHROPIC_ENDPOINT=${ANTHROPIC_ENDPOINT:-https://api.anthropic.com}
@@ -42,7 +43,8 @@ services:
       - BROWSER_USE_LOGGING_LEVEL=${BROWSER_USE_LOGGING_LEVEL:-info}
 
       # Browser Settings
-      - BROWSER_USER_DATA=${BROWSER_USER_DATA:-/app/data/chrome_data}
+      - BROWSER_PATH=/usr/bin/google-chrome
+      - BROWSER_USER_DATA=/app/data/chrome_data
       - BROWSER_DEBUGGING_PORT=${BROWSER_DEBUGGING_PORT:-9222}
       - BROWSER_DEBUGGING_HOST=${BROWSER_DEBUGGING_HOST:-0.0.0.0}
       - KEEP_BROWSER_OPEN=${KEEP_BROWSER_OPEN:-true}

supervisord.conf

@@ -3,7 +3,7 @@ user=root
 nodaemon=true
 logfile=/dev/stdout
 logfile_maxbytes=0
-loglevel=debug
+loglevel=error
 
 [program:xvfb]
 command=Xvfb :99 -screen 0 %(ENV_RESOLUTION)s -ac +extension GLX +render -noreset

tests/test_llm_api.py

@@ -142,17 +142,17 @@ def test_ibm_model():
 
 
 def test_qwen_model():
-    config = LLMConfig(provider="alibaba", model_name="qwen3-30b-a3b")
+    config = LLMConfig(provider="alibaba", model_name="qwen-vl-max")
     test_llm(config, "How many 'r's are in the word 'strawberry'?")
 
 
 if __name__ == "__main__":
     # test_openai_model()
     # test_google_model()
-    # test_azure_openai_model()
+    test_azure_openai_model()
     # test_deepseek_model()
     # test_ollama_model()
-    test_deepseek_r1_model()
+    # test_deepseek_r1_model()
     # test_deepseek_r1_ollama_model()
     # test_mistral_model()
     # test_ibm_model()