​

Overview

Sessions are the heart of our ecosystem. They maintain browser states and provide a reliable foundation for executing web-based operations. Every operation in the Notte ecosystem is performed on behalf of a session (agent, scrape, vault, etc.)

​

Session Management

This shows how to manage your browser sessions using the Notte Python SDK

from notte_sdk import NotteClient

notte = NotteClient()

# The session is automatically stopped when the context manager is exited
with notte.Session(timeout_minutes=2) as session:
	status = session.status()
	print(status)

​

Key points

• Timeouts: Use the timeout_minutes parameter to specify when a session should be stopped if no actions are performed on it (no activity). Note that by default, sessions are stopped after 3 minutes of inactivity.
• Session IDs: Each session is uniquely identified, e.g. 5767be3c-aef5-47f8-bcb0-4f9f80fa66a3 and is tied to an API Key.
• The agent/start endpoint takes an optional session_id parameter. If not provided, sessions are automatically created at the start of the request and closed when the agent run is completed.

​

Session Features

For more information on the additional features that are available for sessions, see the following guides:

​

Operations

Operations provide granular control on the browser session:

• observe() To get the current state of a page and its available actions
• step() To take an action you’ve previously observed on a page
• scrape() To extract structured data from a page

from notte_sdk import NotteClient

with NotteClient().Session() as page:
    url="https://www.linkedin.com/"

    # observe page and take a step
    obs = page.observe(url=url, instructions="click 'jobs'")
    res = page.step(action=obs.space.first())
    print(res.message)

    # another one 
    obs = page.observe(instructions="dismiss the sign in check")
    res = page.step(action=obs.space.first())
    print(res.message)