Camel.toolkits.browser toolkit

​

_get_str

def _get_str(d: Any, k: str):

​

_get_number

def _get_number(d: Any, k: str):

​

_get_bool

def _get_bool(d: Any, k: str):

​

BaseBrowser

class BaseBrowser:

​

init

def __init__(
    self,
    headless = True,
    cache_dir: Optional[str] = None,
    channel: Literal['chrome', 'msedge', 'chromium'] = 'chromium',
    cookie_json_path: Optional[str] = None,
    user_data_dir: Optional[str] = None
):

• headless (bool): Whether to run the browser in headless mode.
• cache_dir (Union[str, None]): The directory to store cache files.
• channel (Literal["chrome", "msedge", "chromium"]): The browser channel to use. Must be one of “chrome”, “msedge”, or “chromium”.
• cookie_json_path (Optional[str]): Path to a JSON file containing authentication cookies and browser storage state. If provided and the file exists, the browser will load this state to maintain authenticated sessions. This is primarily used when user_data_dir is not set.
• user_data_dir (Optional[str]): The directory to store user data for persistent context. If None, a fresh browser instance is used without saving data. (default: :obj:None)

​

init

def init(self):

​

clean_cache

def clean_cache(self):

​

_wait_for_load

def _wait_for_load(self, timeout: int = 20):

​

click_blank_area

def click_blank_area(self):

​

visit_page

def visit_page(self, url: str):

​

ask_question_about_video

def ask_question_about_video(self, question: str):

• question (str): The question to ask.

​

get_screenshot

def get_screenshot(self, save_image: bool = False):

• save_image (bool): Whether to save the image to the cache directory.

​

capture_full_page_screenshots

def capture_full_page_screenshots(self, scroll_ratio: float = 0.8):

• scroll_ratio (float): The ratio of viewport height to scroll each step. (default: :obj:0.8)

​

get_visual_viewport

def get_visual_viewport(self):

​

get_interactive_elements

def get_interactive_elements(self):

​

get_som_screenshot

def get_som_screenshot(self, save_image: bool = False):

• save_image (bool): Whether to save the image to the cache directory.

​

scroll_up

def scroll_up(self):

​

scroll_down

def scroll_down(self):

​

get_url

def get_url(self):

​

click_id

def click_id(self, identifier: Union[str, int]):

​

extract_url_content

def extract_url_content(self):

​

download_file_id

def download_file_id(self, identifier: Union[str, int]):

• identifier (str): The identifier of the file to download.

​

fill_input_id

def fill_input_id(self, identifier: Union[str, int], text: str):

• identifier (str): The identifier of the input field.
• text (str): The text to fill.

​

scroll_to_bottom

def scroll_to_bottom(self):

​

scroll_to_top

def scroll_to_top(self):

​

hover_id

def hover_id(self, identifier: Union[str, int]):

• identifier (str): The identifier of the element to hover over.

​

find_text_on_page

def find_text_on_page(self, search_text: str):

​

back

def back(self):

​

close

def close(self):

​

show_interactive_elements

def show_interactive_elements(self):

​

get_webpage_content

def get_webpage_content(self):

​

_ensure_browser_installed

def _ensure_browser_installed(self):

​

BrowserToolkit

class BrowserToolkit(BaseToolkit):

​

init

def __init__(
    self,
    headless: bool = False,
    cache_dir: Optional[str] = None,
    channel: Literal['chrome', 'msedge', 'chromium'] = 'chromium',
    history_window: int = 5,
    web_agent_model: Optional[BaseModelBackend] = None,
    planning_agent_model: Optional[BaseModelBackend] = None,
    output_language: str = 'en',
    cookie_json_path: Optional[str] = None,
    user_data_dir: Optional[str] = None
):

• headless (bool): Whether to run the browser in headless mode. When running inside a CAMEL runtime container, this is automatically set to True since containers typically don’t have a display.
• cache_dir (Union[str, None]): The directory to store cache files.
• channel (Literal["chrome", "msedge", "chromium"]): The browser channel to use. Must be one of “chrome”, “msedge”, or “chromium”.
• history_window (int): The window size for storing the history of actions.
• web_agent_model (Optional[BaseModelBackend]): The model backend for the web agent.
• planning_agent_model (Optional[BaseModelBackend]): The model backend for the planning agent.
• output_language (str): The language to use for output. (default: :obj:"en”)
• cookie_json_path (Optional[str]): Path to a JSON file containing authentication cookies and browser storage state. If provided and the file exists, the browser will load this state to maintain authenticated sessions without requiring manual login. (default: :obj:None)
• user_data_dir (Optional[str]): The directory to store user data for persistent context. If None, a fresh browser instance is used without saving data. (default: :obj:None)

​

_reset

def _reset(self):

​

_initialize_agent

def _initialize_agent(
    self,
    web_agent_model_backend: Optional[BaseModelBackend],
    planning_agent_model_backend: Optional[BaseModelBackend]
):

​

_observe

def _observe(self, task_prompt: str, detailed_plan: Optional[str] = None):

​

_act

def _act(self, action_code: str):

• action_code (str): The action code to act.

​

_get_final_answer

def _get_final_answer(self, task_prompt: str):

​

_task_planning

def _task_planning(self, task_prompt: str, start_url: str):

​

_task_replanning

def _task_replanning(self, task_prompt: str, detailed_plan: str):

• task_prompt (str): The original task prompt.
• detailed_plan (str): The detailed plan to replan.

​

browse_url

def browse_url(
    self,
    task_prompt: str,
    start_url: str,
    round_limit: int = 12
):

• task_prompt (str): The task prompt to solve.
• start_url (str): The start URL to visit.
• round_limit (int): The round limit to solve the task. (default: :obj:12).

​

get_tools

def get_tools(self):