Merge pull request #141 from vvincent1234/fix/docker_vnc

warmshao · web-flow · commit 6e553218eea0 · 2025-01-24T20:01:25.000+08:00
Fix/docker vnc
diff --git a/.dockerignore b/.dockerignore
@@ -0,0 +1,2 @@
+data
+tmp
diff --git a/Dockerfile b/Dockerfile
@@ -61,6 +61,7 @@ RUN pip install --no-cache-dir -r requirements.txt
 ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
 RUN playwright install --with-deps chromium
 RUN playwright install-deps
+RUN apt-get install -y google-chrome-stable
 
 # Copy the application code
 COPY . .
diff --git a/docker-compose.yml b/docker-compose.yml
@@ -28,13 +28,9 @@ services:
       - RESOLUTION_WIDTH=${RESOLUTION_WIDTH:-1920}
       - RESOLUTION_HEIGHT=${RESOLUTION_HEIGHT:-1080}
       - VNC_PASSWORD=${VNC_PASSWORD:-vncpassword}
-      - PERSISTENT_BROWSER_PORT=9222
-      - PERSISTENT_BROWSER_HOST=localhost
       - CHROME_DEBUGGING_PORT=9222
       - CHROME_DEBUGGING_HOST=localhost
     volumes:
-      - ./data:/app/data
-      - ./data/chrome_data:/app/data/chrome_data
       - /tmp/.X11-unix:/tmp/.X11-unix
     restart: unless-stopped
     shm_size: '2gb'
diff --git a/src/browser/custom_browser.py b/src/browser/custom_browser.py
@@ -5,6 +5,7 @@
 # @FileName: browser.py
 
 import asyncio
+import pdb
 
 from playwright.async_api import Browser as PlaywrightBrowser
 from playwright.async_api import (
diff --git a/src/utils/default_config_settings.py b/src/utils/default_config_settings.py
@@ -17,7 +17,7 @@ def default_config():
         "llm_temperature": 1.0,
         "llm_base_url": "",
         "llm_api_key": "",
-        "use_own_browser": False,
+        "use_own_browser": os.getenv("CHROME_PERSISTENT_SESSION", False),
         "keep_browser_open": False,
         "headless": False,
         "disable_security": True,
diff --git a/src/utils/utils.py b/src/utils/utils.py
@@ -88,7 +88,7 @@ def get_llm_model(provider: str, **kwargs):
         return ChatOllama(
             model=kwargs.get("model_name", "qwen2.5:7b"),
             temperature=kwargs.get("temperature", 0.0),
-            num_ctx=128000,
+            num_ctx=kwargs.get("num_ctx", 32000),
             base_url=kwargs.get("base_url", "http://localhost:11434"),
         )
     elif provider == "azure_openai":
diff --git a/supervisord.conf b/supervisord.conf
@@ -58,8 +58,8 @@ startsecs=3
 depends_on=x11vnc
 
 [program:persistent_browser]
-command=bash -c 'if [ "%(ENV_CHROME_PERSISTENT_SESSION)s" = "true" ]; then mkdir -p /app/data/chrome_data && sleep 8 && google-chrome --user-data-dir=/app/data/chrome_data --window-position=0,0 --window-size=%(ENV_RESOLUTION_WIDTH)s,%(ENV_RESOLUTION_HEIGHT)s --start-maximized --no-sandbox --disable-dev-shm-usage --disable-gpu --disable-software-rasterizer --disable-setuid-sandbox --no-first-run --no-default-browser-check --no-experiments --ignore-certificate-errors --remote-debugging-port=9222 --remote-debugging-address=0.0.0.0 "data:text/html,<html><body style=\"background: \#f0f0f0; margin: 0; display: flex; justify-content: center; align-items: center; height: 100vh; font-family: Arial;\"><h1>Browser Ready for AI Interaction</h1></body></html>"; else echo "Persistent browser disabled"; fi'
-autorestart=%(ENV_CHROME_PERSISTENT_SESSION)s
+command=bash -c 'mkdir -p /app/data/chrome_data && sleep 8 && google-chrome --user-data-dir=/app/data/chrome_data --window-position=0,0 --window-size=%(ENV_RESOLUTION_WIDTH)s,%(ENV_RESOLUTION_HEIGHT)s --start-maximized --no-sandbox --disable-dev-shm-usage --disable-gpu --disable-software-rasterizer --disable-setuid-sandbox --no-first-run --no-default-browser-check --no-experiments --ignore-certificate-errors --remote-debugging-port=9222 --remote-debugging-address=0.0.0.0 "data:text/html,<html><body style=\"background: \#f0f0f0; margin: 0; display: flex; justify-content: center; align-items: center; height: 100vh; font-family: Arial;\"><h1>Browser Ready for AI Interaction</h1></body></html>"'
+autorestart=true
 stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0
 stderr_logfile=/dev/stderr
diff --git a/tests/test_browser_use.py b/tests/test_browser_use.py
@@ -247,18 +247,18 @@ async def test_browser_use_custom_v2():
     #     api_key=os.getenv("GOOGLE_API_KEY", "")
     # )
 
-    llm = utils.get_llm_model(
-        provider="deepseek",
-        model_name="deepseek-chat",
-        temperature=0.8
-    )
-
     # llm = utils.get_llm_model(
-    #     provider="ollama", model_name="qwen2.5:7b", temperature=0.8
+    #     provider="deepseek",
+    #     model_name="deepseek-chat",
+    #     temperature=0.8
     # )
 
+    llm = utils.get_llm_model(
+        provider="ollama", model_name="qwen2.5:7b", temperature=0.5
+    )
+
     controller = CustomController()
-    use_own_browser = True
+    use_own_browser = False
     disable_security = True
     use_vision = False  # Set to False when using DeepSeek
     tool_call_in_content = True  # Set to True when using Ollama

Original file line number	Diff line number	Diff line change
`@@ -88,7 +88,7 @@ def get_llm_model(provider: str, **kwargs):`
`88`	`88`	`return ChatOllama(`
`89`	`89`	`model=kwargs.get("model_name", "qwen2.5:7b"),`
`90`	`90`	`temperature=kwargs.get("temperature", 0.0),`
`91`		`- num_ctx=128000,`
	`91`	`+ num_ctx=kwargs.get("num_ctx", 32000),`
`92`	`92`	`base_url=kwargs.get("base_url", "http://localhost:11434"),`
`93`	`93`	`)`
`94`	`94`	`elif provider == "azure_openai":`