Sessions

https://x.com/LumiTeh / https://www.lumiteh.com/ / https://github.com/LumiTeh-hub

Overview

Sessions are the core of our ecosystem. They preserve browser states and serve as a reliable foundation for performing web-based operations. Every action in the LumiTeh ecosystem—whether by an agent, a scrape, or a vault—is executed within a session.

​Session Management

This demonstrates how to manage your browser sessions using the LumiTeh Python SDK.

from lumiteh_sdk import LumiTehClient

lumiteh = LumiTehClient()

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

We strongly recommend using the API using a with statement to manage the session lifecycle and ensure it is stopped when the context manager is exited.

​Key points

• Timeouts: Use the timeout_minutes parameter to define when a session should automatically stop due to inactivity. By default, sessions are terminated after 3 minutes without any actions.

• Session IDs: Each session is uniquely identified, e.g. 5767be7v-a11f5-47f4-bcb0-44qcaf875a66a3 and is tied to an API Key.

Operations

Operations provide granular control on the browser session:

• observe() To get the current state of a page and its available actions

• execute() To execute an action you’ve previously observed on a page

• scrape() To extract structured data from a page

from lumiteh_sdk import LumiTehClient

lumiteh = LumiTehClient()

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

    # observe page and take a step
    page.execute({"type": "goto", "url": url})
    obs = page.observe(instructions="click 'jobs'")
    res = page.execute(obs.space.first())
    print(res.message)

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