add gemini supported

.env.example

@@ -0,0 +1,11 @@
+OPENAI_API_KEY=
+ANTHROPIC_API_KEY=
+GOOGLE_API_KEY=
+AZURE_OPENAI_ENDPOINT=
+AZURE_OPENAI_KEY=
+
+# Set to false to disable anonymized telemetry
+ANONYMIZED_TELEMETRY=true
+
+# LogLevel: Set to debug to enable verbose logging, set to result to get results only. Available: result | debug | info
+BROWSER_USE_LOGGING_LEVEL=info

.gitignore

@@ -0,0 +1,179 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+test_env/
+
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+temp
+tmp
+
+
+.DS_Store
+
+private_example.py
+private_example
+
+browser_cookies.json
+cookies.json
+AgentHistory.json
+cv_04_24.pdf
+AgentHistoryList.json
+*.gif

src/__init__.py

@@ -0,0 +1,6 @@
+# -*- coding: utf-8 -*-
+# @Time    : 2025/1/1
+# @Author  : wenshao
+# @Email   : wenshaoguo1026@gmail.com
+# @Project : browser-use-webui
+# @FileName: __init__.py.py

src/agent/__init__.py

@@ -0,0 +1,6 @@
+# -*- coding: utf-8 -*-
+# @Time    : 2025/1/1
+# @Author  : wenshao
+# @Email   : wenshaoguo1026@gmail.com
+# @Project : browser-use-webui
+# @FileName: __init__.py.py

src/browser/__init__.py

@@ -0,0 +1,6 @@
+# -*- coding: utf-8 -*-
+# @Time    : 2025/1/1
+# @Author  : wenshao
+# @Email   : wenshaoguo1026@gmail.com
+# @Project : browser-use-webui
+# @FileName: __init__.py.py

src/browser/context.py

@@ -0,0 +1,94 @@
+# -*- coding: utf-8 -*-
+# @Time    : 2025/1/1
+# @Author  : wenshao
+# @Email   : wenshaoguo1026@gmail.com
+# @Project : browser-use-webui
+# @FileName: context.py
+
+import asyncio
+import base64
+import json
+import logging
+import os
+
+from playwright.async_api import Browser as PlaywrightBrowser
+from browser_use.browser.context import BrowserContext, BrowserContextConfig
+from browser_use.browser.browser import Browser
+
+logger = logging.getLogger(__name__)
+
+
+class CustomBrowserContext(BrowserContext):
+    """
+    定制BrowserContext
+    """
+
+    def __init__(self,
+                 browser: 'Browser',
+                 config: BrowserContextConfig = BrowserContextConfig(),
+                 ):
+        super(CustomBrowserContext, self).__init__(browser, config)
+
+    async def _create_context(self, browser: PlaywrightBrowser):
+        """Creates a new browser context with anti-detection measures and loads cookies if available."""
+        if self.browser.config.chrome_instance_path and len(browser.contexts) > 0:
+            # Connect to existing Chrome instance instead of creating new one
+            context = browser.contexts[0]
+        else:
+            # Original code for creating new context
+            context = await browser.new_context(
+                viewport=self.config.browser_window_size,
+                no_viewport=False,
+                user_agent=(
+                    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 '
+                    '(KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'
+                ),
+                java_script_enabled=True,
+                bypass_csp=self.config.disable_security,
+                ignore_https_errors=self.config.disable_security,
+                record_video_dir=self.config.save_recording_path,
+                record_video_size=self.config.browser_window_size  # set record video size
+            )
+
+        if self.config.trace_path:
+            await context.tracing.start(screenshots=True, snapshots=True, sources=True)
+
+        # Load cookies if they exist
+        if self.config.cookies_file and os.path.exists(self.config.cookies_file):
+            with open(self.config.cookies_file, 'r') as f:
+                cookies = json.load(f)
+                logger.info(f'Loaded {len(cookies)} cookies from {self.config.cookies_file}')
+                await context.add_cookies(cookies)
+
+        # Expose anti-detection scripts
+        await context.add_init_script(
+            """
+            // Webdriver property
+            Object.defineProperty(navigator, 'webdriver', {
+                get: () => undefined
+            });
+
+            // Languages
+            Object.defineProperty(navigator, 'languages', {
+                get: () => ['en-US', 'en']
+            });
+
+            // Plugins
+            Object.defineProperty(navigator, 'plugins', {
+                get: () => [1, 2, 3, 4, 5]
+            });
+
+            // Chrome runtime
+            window.chrome = { runtime: {} };
+
+            // Permissions
+            const originalQuery = window.navigator.permissions.query;
+            window.navigator.permissions.query = (parameters) => (
+                parameters.name === 'notifications' ?
+                    Promise.resolve({ state: Notification.permission }) :
+                    originalQuery(parameters)
+            );
+            """
+        )
+
+        return context

src/utils/__init__.py

@@ -0,0 +1,6 @@
+# -*- coding: utf-8 -*-
+# @Time    : 2025/1/1
+# @Author  : wenshao
+# @Email   : wenshaoguo1026@gmail.com
+# @Project : browser-use-webui
+# @FileName: __init__.py.py

src/utils/utils.py

@@ -0,0 +1,58 @@
+# -*- coding: utf-8 -*-
+# @Time    : 2025/1/1
+# @Author  : wenshao
+# @Email   : wenshaoguo1026@gmail.com
+# @Project : browser-use-webui
+# @FileName: utils.py
+
+import base64
+from langchain_openai import ChatOpenAI, AzureChatOpenAI
+from langchain_anthropic import ChatAnthropic
+from langchain_google_genai import ChatGoogleGenerativeAI
+
+
+def get_llm_model(provider: str, **kwargs):
+    """
+    获取LLM 模型
+    :param provider: 模型类型
+    :param kwargs:
+    :return:
+    """
+    if provider == 'claude':
+        return ChatAnthropic(
+            model_name=kwargs.get("model_name", 'claude-3-5-sonnet-20240620'),
+            temperature=kwargs.get("temperature", 0.0),
+            base_url=kwargs.get("base_url", "https://api.anthropic.com"),
+            api_key=kwargs.get("api_key", None)
+        )
+    elif provider == 'openai':
+        return ChatOpenAI(
+            model=kwargs.get("model_name", 'gpt-4o'),
+            temperature=kwargs.get("temperature", 0.0),
+            base_url=kwargs.get("base_url", "https://api.openai.com/v1/"),
+            api_key=kwargs.get("api_key", None)
+        )
+    elif provider == 'gemini':
+        return ChatGoogleGenerativeAI(
+            model=kwargs.get("model_name", 'gemini-2.0-flash-exp'),
+            temperature=kwargs.get("temperature", 0.0),
+            google_api_key=kwargs.get("api_key", None),
+        )
+    elif provider == "azure_openai":
+        return AzureChatOpenAI(
+            model=kwargs.get("model_name", 'gpt-4o'),
+            temperature=kwargs.get("temperature", 0.0),
+            api_version="2024-05-01-preview",
+            azure_endpoint=kwargs.get("base_url", ""),
+            api_key=kwargs.get("api_key", None)
+        )
+    else:
+        raise ValueError(f'Unsupported provider: {provider}')
+
+
+def encode_image(img_path):
+    if not img_path:
+        return None
+    with open(img_path, "rb") as fin:
+        image_data = base64.b64encode(fin.read()).decode("utf-8")
+    return image_data

tests/test_llm_api.py

@@ -0,0 +1,74 @@
+# -*- coding: utf-8 -*-
+# @Time    : 2025/1/1
+# @Author  : wenshao
+# @Email   : wenshaoguo1026@gmail.com
+# @Project : browser-use-webui
+# @FileName: test_llm_api.py
+import os
+import pdb
+
+from dotenv import load_dotenv
+
+load_dotenv()
+
+import sys
+
+sys.path.append(".")
+
+
+def test_gemini_model():
+    # you need to enable your api key first: https://ai.google.dev/palm_docs/oauth_quickstart
+    from langchain_core.messages import HumanMessage
+    from src.utils import utils
+
+    llm = utils.get_llm_model(
+        provider="gemini",
+        model_name="gemini-2.0-flash-exp",
+        temperature=0.8,
+        api_key=os.getenv("GOOGLE_API_KEY", "")
+    )
+
+    image_path = "assets/examples/test.png"
+    image_data = utils.encode_image(image_path)
+    message = HumanMessage(
+        content=[
+            {"type": "text", "text": "describe this image"},
+            {
+                "type": "image_url",
+                "image_url": {"url": f"data:image/jpeg;base64,{image_data}"},
+            },
+        ]
+    )
+    ai_msg = llm.invoke([message])
+    print(ai_msg.content)
+
+
+def test_azure_openai_model():
+    from langchain_core.messages import HumanMessage
+    from src.utils import utils
+
+    llm = utils.get_llm_model(
+        provider="azure_openai",
+        model_name="gpt-4o",
+        temperature=0.8,
+        base_url=os.getenv("AZURE_OPENAI_ENDPOINT", ""),
+        api_key=os.getenv("AZURE_OPENAI_KEY", "")
+    )
+    image_path = "assets/examples/test.png"
+    image_data = utils.encode_image(image_path)
+    message = HumanMessage(
+        content=[
+            {"type": "text", "text": "describe this image"},
+            {
+                "type": "image_url",
+                "image_url": {"url": f"data:image/jpeg;base64,{image_data}"},
+            },
+        ]
+    )
+    ai_msg = llm.invoke([message])
+    print(ai_msg.content)
+
+
+if __name__ == '__main__':
+    test_gemini_model()
+    # test_azure_openai_model()

webui.py

@@ -0,0 +1,6 @@
+# -*- coding: utf-8 -*-
+# @Time    : 2025/1/1
+# @Author  : wenshao
+# @Email   : wenshaoguo1026@gmail.com
+# @Project : browser-use-webui
+# @FileName: webui.py