Skip to content

Send webpage html content along with screenshot in every loop #40

@kamranemergent

Description

@kamranemergent

Send webpage html content along with screenshot in every loop

when cua agent is running, as of now, after each browser action, i am seding screenshot of the current state, but it becomes a very very slow process. to make the agent faster, can i send html content data also? can i send html content only?

if yes, then in which 'key'

as of now sending screenshot like this

call_output = {
"type": "computer_call_output",
"call_id": item["call_id"],
"acknowledged_safety_checks": pending_checks,
"output": {
"type": "input_image",
"image_url": f"data:image/png;base64,{screenshot_base64}",
}
}

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions