Browse

POST

Allows for browsing the web using detailed natural language commands.

The function supports multi-step command execution based on the CONTINUE status of the Agent.

Request

This endpoint expects an object.
cmdstringRequired

A specific natural language instruction for the agent to execute

urlstringOptional

The URL to start or continue browsing from. (Default: google.com)

localbooleanOptional

Boolean flag to indicate if session to be run locally or in the cloud (Default: False). If set to true, the session will be run locally via your chrome extension. If set to false, the session will be run in the cloud.

session_idstringOptional

Continues the session with session_id if provided.

max_stepsintegerOptionalDefaults to 20

Maximum number of steps to execute. (Default: 20)

include_screenshotbooleanOptional

Boolean flag to include a screenshot of the final page. (Default: False)

temperaturedoubleOptional

The temperature of model

agent_idstringOptional

The agent id to use for the session.

mode"fast" or "standard"Optional
Allowed values: faststandard

The mode you would like to use for the session. ‘fast’ or ‘standard’

use_proxybooleanOptional

Boolean flag to use a proxy for the session (Default: False). Each Session gets a new Residential IP.

Response

This endpoint returns an object.
messagestring

The final message or result of the browsing session.

statusstring

The final status of the browsing session. One of [“CONTINUE”, “ASK_USER”, “DONE”]

urlstring

The current URL of the session.

screenshotstring

image url of the screenshot taken during the session.

session_idstring

The unique identifier for the session.

metadataobjectOptional

Additional metadata for the session