Skip to main content
Observation Response:
  • a list of actions that can be taken on the page (e.g. click on a button, scroll, etc.)
  • a screenshot of the page (base64 encoded)
  • some metadata about the page (title, url, etc.)
Once you have selected an action (either manually or using an LLM), you can execute it with:
Note that by default, a very simple page perception is used to generate the action space (i.e perception_type='fast') to make the query fast. If you want a more powerful and LLM-ready action space, you can use:
At the cost of a slower query since this uses an LLM call to format the interactive elements. Additionally, you can use the instructions parameter to narrow down the action space to a specific intent on a website. This is useful if you want to quickly create a workflow using natural language:

Parameters

min_nb_actions
int | None
The minimum number of actions to list before stopping. If not provided, the listing will continue until the maximum number of actions is reached.
max_nb_actions
int
The maximum number of actions to list after which the listing will stop. Used when min_nb_actions is not provided.
instructions
str | None
Additional instructions to use for the observation.
perception_type
typing.Optional[typing.Literal['fast', 'deep']]

Returns

UnionType[Observation, list[Annotated[UnionType[ClickAction, FillAction, MultiFactorFillAction, FallbackFillAction, CheckAction, SelectDropdownOptionAction, UploadFileAction, DownloadFileAction], annotation=NoneType required=True discriminator='type']]]: The formatted observation result from the API response when no instructions provided. list[InteractionActionUnion]: The filtered list of actions when instructions is provided.