Agent

askui.VisionAgent

class VisionAgent()

A vision-based agent that can interact with user interfaces through computer vision and AI.

This agent can perform various UI interactions like clicking, typing, scrolling, and more. It uses computer vision models to locate UI elements and execute actions on them.

Arguments:

log_level int | str, optional - The logging level to use. Defaults to logging.INFO.
display int, optional - The display number to use for screen interactions. Defaults to 1.
reporters list[Reporter] | None, optional - List of reporter instances for logging and reporting. If None, an empty list is used.
tools AgentToolbox | None, optional - Custom toolbox instance. If None, a default one will be created with AskUiControllerClient.
model ModelChoice | ModelComposition | str | None, optional - The default choice or name of the model(s) to be used for vision tasks. Can be overridden by the model parameter in the click(), get(), act() etc. methods.
retry Retry, optional - The retry instance to use for retrying failed actions. Defaults to ConfigurableRetry with exponential backoff. Currently only supported for locate() method.
models ModelRegistry | None, optional - A registry of models to make available to the VisionAgent so that they can be selected using the model parameter of VisionAgent or the model parameter of its click(), get(), act() etc. methods. Entries in the registry override entries in the default model registry.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.click("Submit button")
    agent.type("Hello World")
    agent.act("Open settings menu")

act

def act(
    goal: Annotated[str | list[MessageParam],
                    Field(min_length=1)],
    model: str | None = None,
    on_message: OnMessageCb | None = None
) -> None

Instructs the agent to achieve a specified goal through autonomous actions.

The agent will analyze the screen, determine necessary steps, and perform actions to accomplish the goal. This may include clicking, typing, scrolling, and other interface interactions.

Arguments:

goal str - A description of what the agent should achieve.
model str | None, optional - The composition or name of the model(s) to be used for achieving the goal.
on_message OnMessageCb | None, optional - Callback for new messages. If it returns None, stops and does not add the message.

Returns:

None

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.act("Open the settings menu")
    agent.act("Search for 'printer' in the search box")
    agent.act("Log in with username 'admin' and password '1234'")

cli

def cli(command: Annotated[str, Field(min_length=1)]) -> None

Executes a command on the command line interface.

This method allows running shell commands directly from the agent. The command is split on spaces and executed as a subprocess.

Arguments:

command str - The command to execute on the command line.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.cli(fr'start "" "C:\Program Files\VideoLAN\VLC\vlc.exe"') # Start in VLC Non-Blocking
    agent.cli(fr'"C:\Program Files\VideoLAN\VLC\vlc.exe"') # Start in VLC Blocking
    agent.cli("echo Hello World")  # Prints "Hello World"
    agent.cli("ls -la")  # Lists files in current directory with details
    agent.cli("python --version")  # Displays Python version

click

def click(
    locator: Optional[str | Locator] = None,
    button: Literal['left', 'middle', 'right'] = 'left',
    repeat: Annotated[int, Field(gt=0)] = 1,
    model: ModelComposition | str | None = None
) -> None

Simulates a mouse click on the user interface element identified by the provided locator.

Arguments:

locator str | Locator | None, optional - The identifier or description of the element to click. If None, clicks at current position.
button ‘left’ | ‘middle’ | ‘right’, optional - Specifies which mouse button to click. Defaults to 'left'.
repeat int, optional - The number of times to click. Must be greater than 0. Defaults to 1.
model ModelComposition | str | None, optional - The composition or name of the model(s) to be used for locating the element to click on using the locator.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.click()              # Left click on current position
    agent.click("Edit")        # Left click on text "Edit"
    agent.click("Edit", button="right")  # Right click on text "Edit"
    agent.click(repeat=2)      # Double left click on current position
    agent.click("Edit", button="middle", repeat=4)   # 4x middle click on text "Edit"

get

def get(
    query: Annotated[str, Field(min_length=1)],
    response_schema: Type[ResponseSchema] | None = None,
    model: str | None = None,
    image: Optional[Img] = None
) -> ResponseSchema | str

Retrieves information from an image (defaults to a screenshot of the current screen) based on the provided query.

Arguments:

query str - The query describing what information to retrieve.
image Img | None, optional - The image to extract information from. Defaults to a screenshot of the current screen. Can be a path to an image file, a PIL Image object or a data URL.
response_schema Type[ResponseSchema] | None, optional - A Pydantic model class that defines the response schema. If not provided, returns a string.
model str | None, optional - The composition or name of the model(s) to be used for retrieving information from the screen or image using the query. Note: response_schema is not supported by all models.

Returns:

ResponseSchema | str: The extracted information, str if no response_schema is provided.

Limitations:

Nested Pydantic schemas are not currently supported
Schema support is only available with “askui” model (default model if ASKUI_WORKSPACE_ID and ASKUI_TOKEN are set) at the moment

Example:

from askui import ResponseSchemaBase, VisionAgent
from PIL import Image

class UrlResponse(ResponseSchemaBase):
    url: str

with VisionAgent() as agent:
    # Get URL as string
    url = agent.get("What is the current url shown in the url bar?")

    # Get URL as Pydantic model from image at (relative) path
    response = agent.get(
        "What is the current url shown in the url bar?",
        response_schema=UrlResponse,
        image="screenshot.png",
    )
    print(response.url)

    # Get boolean response from PIL Image
    is_login_page = agent.get(
        "Is this a login page?",
        response_schema=bool,
        image=Image.open("screenshot.png"),
    )

    # Get integer response
    input_count = agent.get(
        "How many input fields are visible on this page?",
        response_schema=int,
    )

    # Get float response
    design_rating = agent.get(
        "Rate the page design quality from 0 to 1",
        response_schema=float,
    )

key_down

def key_down(key: PcKey | ModifierKey) -> None

Simulates the pressing of a key.

Arguments:

key PcKey | ModifierKey - The key to be pressed.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.key_down('a')  # Press the 'a' key
    agent.key_down('shift')  # Press the 'Shift' key

key_up

def key_up(key: PcKey | ModifierKey) -> None

Simulates the release of a key.

Arguments:

key PcKey | ModifierKey - The key to be released.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.key_up('a')  # Release the 'a' key
    agent.key_up('shift')  # Release the 'Shift' key

keyboard

def keyboard(
    key: PcKey | ModifierKey,
    modifier_keys: Optional[list[ModifierKey]] = None,
    repeat: Annotated[int, Field(gt=0)] = 1
) -> None

Simulates pressing (and releasing) a key or key combination on the keyboard.

Arguments:

key PcKey | ModifierKey - The main key to press. This can be a letter, number, special character, or function key.
modifier_keys list[ModifierKey] | None, optional - List of modifier keys to press along with the main key. Common modifier keys include 'ctrl', 'alt', 'shift'.
repeat int, optional - The number of times to press (and release) the key. Must be greater than 0. Defaults to 1.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.keyboard('a')  # Press 'a' key
    agent.keyboard('enter')  # Press 'Enter' key
    agent.keyboard('v', ['control'])  # Press Ctrl+V (paste)
    agent.keyboard('s', ['control', 'shift'])  # Press Ctrl+Shift+S
    agent.keyboard('a', repeat=2)  # Press 'a' key twice

locate

def locate(
    locator: str | Locator,
    screenshot: Optional[Img] = None,
    model: ModelComposition | str | None = None
) -> Point

Locates the UI element identified by the provided locator.

Arguments:

locator str | Locator - The identifier or description of the element to locate.
screenshot Img | None, optional - The screenshot to use for locating the element. Can be a path to an image file, a PIL Image object or a data URL. If None, takes a screenshot of the currently selected display.
model ModelComposition | str | None, optional - The composition or name of the model(s) to be used for locating the element using the locator.

Returns:

Point - The coordinates of the element as a tuple (x, y).

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    point = agent.locate("Submit button")
    print(f"Element found at coordinates: {point}")

mouse_down

def mouse_down(button: Literal["left", "middle", "right"] = "left") -> None

Simulates the pressing of a mouse button.

Arguments:

button ‘left’ | ‘middle’ | ‘right’, optional - The mouse button to be pressed. Defaults to 'left'.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.mouse_down()  # Press the left mouse button
    agent.mouse_down('right')  # Press the right mouse button
    agent.mouse_down('middle')  # Press the middle mouse button

mouse_move

def mouse_move(
    locator: str | Locator,
    model: ModelComposition | str | None = None
) -> None

Moves the mouse cursor to the UI element identified by the provided locator.

Arguments:

locator str | Locator - The identifier or description of the element to move to.
model ModelComposition | str | None, optional - The composition or name of the model(s) to be used for locating the element to move the mouse to using the locator.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.mouse_move("Submit button")  # Moves cursor to submit button
    agent.mouse_move("Close")  # Moves cursor to close element
    agent.mouse_move("Profile picture", model="custom_model")  # Uses specific model

mouse_scroll

def mouse_scroll(x: int, y: int) -> None

Simulates scrolling the mouse wheel by the specified horizontal and vertical amounts.

Arguments:

x int - The horizontal scroll amount. Positive values typically scroll right, negative values scroll left.
y int - The vertical scroll amount. Positive values typically scroll down, negative values scroll up.

Notes:

The actual scroll direction depends on the operating system’s configuration. Some systems may have “natural scrolling” enabled, which reverses the traditional direction.

The meaning of scroll units varies across operating systems and applications. A scroll value of 10 might result in different distances depending on the application and system settings.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.mouse_scroll(0, 10)  # Usually scrolls down 10 units
    agent.mouse_scroll(0, -5)  # Usually scrolls up 5 units
    agent.mouse_scroll(3, 0)   # Usually scrolls right 3 units

mouse_up

def mouse_up(button: Literal["left", "middle", "right"] = "left") -> None

Simulates the release of a mouse button.

Arguments:

button ‘left’ | ‘middle’ | ‘right’, optional - The mouse button to be released. Defaults to 'left'.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.mouse_up()  # Release the left mouse button
    agent.mouse_up('right')  # Release the right mouse button
    agent.mouse_up('middle')  # Release the middle mouse button

type

def type(text: Annotated[str, Field(min_length=1)]) -> None

Types the specified text as if it were entered on a keyboard.

Arguments:

text str - The text to be typed. Must be at least 1 character long.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.type("Hello, world!")  # Types "Hello, world!"
    agent.type("user@example.com")  # Types an email address
    agent.type("password123")  # Types a password

wait

def wait(sec: Annotated[float, Field(gt=0.0)]) -> None

Pauses the execution of the program for the specified number of seconds.

Arguments:

sec float - The number of seconds to wait. Must be greater than 0.0.

Example:

from askui import VisionAgent

with VisionAgent() as agent:
    agent.wait(5)  # Pauses execution for 5 seconds
    agent.wait(0.5)  # Pauses execution for 500 milliseconds

Python Vision Agent

AskUI Suite

Workspace Services API

Additional Resources

askui.VisionAgent

act

cli

click

get

key_down

key_up

keyboard

locate

mouse_down

mouse_move

mouse_scroll

mouse_up

type

wait

Python Vision Agent

AskUI Suite

Workspace Services API

Additional Resources

​askui.VisionAgent

​act

​cli

​click

​get

​key_down

​key_up

​keyboard

​locate

​mouse_down

​mouse_move

​mouse_scroll

​mouse_up

​type

​wait

askui.VisionAgent

act

cli

click

get

key_down

key_up

keyboard

locate

mouse_down

mouse_move

mouse_scroll

mouse_up

type

wait