multi-on / cookbook Goto Github PK

MultiOn API

License: MIT License

Python 57.19% Jupyter Notebook 42.81%

cookbook's Introduction

MultiOn Cookbook

MultiOn is the Motor Cortex layer for AI, enabling autonomous Web actions using natural language

Enjoy our curated collection of examples and recipes for MultiOn. Use these patterns to build your own Agentic applications. We're going to be shipping new examples weekly. Stay tuned!

🌟 Features

🚀 Effortless Web Automation: Navigate, scrape, and manipulate the web with ease.
🤖 AI Agents: Build and deploy custom AI agents for complex tasks.
🛠 SDK Support: Native Python and JavaScript SDKs available.
💡 Rich Ecosystem: Seamlessly integrate with Crew AI, LangChain, LlamaIndex, and more.
🌐 Global Community: Get support and collaborate with like-minded developers in our Discord.

Prerequisites

To make the most of the examples in this cookbook, you'll need an MultiOn account and API key (sign up here).

Some recipes use the Agent API in local mode, which requires the MultiOn Chrome Extension (install here).

Table of recipes

Projects

Internet of Agents - deploy a swarm of web agents with MultiOn
Coding Agent - execute coding projects end-to-end using MultiOn Agents.
Competitor Research - use MultiOn Agents to do competitor analysis.
Job Search - use MultiOn Agents to find suitable jobs and apply to one.

Notebooks

Scrape LinkedIn - scrape LinkedIn with MultiOn
Recursively Scrape Hackernews - recursively scrape Hackernews posts and comments
Finding Accommodation - find and book accommodation on AirBnB using MultiOn
Restaurant Booking - find and book accommodation on AirBnB using MultiOn
News Analysis - use MultiOn to scrape and analyze news articles.
Personalized Travel Agent - Intelligent travel agent with MultiOn and Mem0

Explore further

Looking for more resources to build with MultiOn agents? Check out these helpful links:

📜 MultiOn Docs
🌐 Community Discord

Contributing

We welcome any contributions to the MultiOn Cookbook, whether it's submitting an idea, fixing a typo, adding a new guide, or improving an existing one. If you have ideas for new examples or guides, share them on the issues page.

If you want to directly contribute code, you can fork the repository, make your changes, and submit a pull request.

Happy building! 🙌

❤️ Loved MultiOn API? Give us a star to spread the word! ⭐️

cookbook's People

Contributors

Stargazers

Watchers

cookbook's Issues

Unable to run event rsvp langchain example

Hi,

I'm unable to execute example given here: https://docs.multion.ai/EXAMPLES/event_rsvps_using_langchain with latest langchain version.

I've tried running it with AgentExecutor but couldn't get it to work. Also tried to downgrade langchain to version <0.1.0 and tried a couple of 0.0.2xx and 0.0.3xx versions but couldn't find a version which runs this example like this.

Could anyone please tell which is the pinned langchain version to use which has stable multion support?

API Key Description text not visible in Dark mode

https://jam.dev/c/876f3180-47a7-4a8d-afaf-667322b3d7ad

Manage Billing button doesn't navigate anywhere

https://jam.dev/c/d9419065-1174-45e2-ae8b-72d78869eec6

getting internal server error, whenever i try to connect multioon

code:
import base64
import os
from io import BytesIO
from typing import Optional

import multion.client
multion.login()

from langchain.llms import OpenAI

from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType
from langchain.chat_models import ChatOpenAI

os.environ["LANGCHAIN_TRACING"] = "true"
os.environ['OPENAI_API_KEY'] = "sk-***************"
from langchain.tools import StructuredTool
from human import HumanInputRun

#import multion
import multion
from multion.client import MultiOn
#multion_toolkit = Multion(use_api=True, mode="auto")
multion.CreateSessionInputBrowserParams.

def agent(query: str):
#from multion.client import MultiOn
multion_toolkit = MultiOn(api_key="50***************")
# multion.set_remote(True)

tool = StructuredTool.from_function(multion_toolkit.browse(cmd="search flights in google"),description="This function performs a browsing operation based on the given query.")
human_input = HumanInputRun()

llm = OpenAI(temperature=0)

# Structured tools are compatible with the STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION agent type.
agent_executor = initialize_agent(
    [tool, human_input],
    llm,
    agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True,
)

return agent_executor.run(query)

PROMPT = f"""
You are an expert AI Agent whose job is to find and get a gpu on a given service HYPERSTACK (https://www.hyperstack.cloud). Pass in the full detailed instructions exactly as below to MultiOn for browsing.

Here are the high-level steps:
1. Login and go to reach the gpu selection page
2. Click on the Load Provising profile and then select the multion-profile and load it
3. After the profile has been correctly selected and loaded continue
4. If an on-demand A100 GPU is available with 80GB RAM, then reserve it
5. If reservation is successful, then enable ssh access and return public ip to access the machine

"""

agent(query=PROMPT)

error:

yping.cast(InternalServerErrorResponse, construct_type(type_=InternalServerErrorResponse, object_=response.json())) # type: ignore
File "C:\Users\tfd250\AppData\Local\miniconda3\envs\albert\lib\site-packages\httpx_models.py", line 764, in json
return jsonlib.loads(self.content, **kwargs)
File "C:\Users\tfd250\AppData\Local\miniconda3\envs\albert\lib\json_init.py", line 346, in loads
return _default_decoder.decode(s)
File "C:\Users\tfd250\AppData\Local\miniconda3\envs\albert\lib\json\decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "C:\Users\tfd250\AppData\Local\miniconda3\envs\albert\lib\json\decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

please help

or do a video on using multion with langchain.

i am trying tom build assistant which can book movie ticket flight ticket everything automatically and chat with the user also..

i am trying to implement the this

https://github.com/MULTI-ON/api/tree/main/examples/gpu_agent

Make multion-python sdk work with python <=3.10

latest pip package only works with python=3.11

Add .env to gitignore

venv adds a env/ directory that should be ignored

Link to publications leads to dead page (non-issue)

In the main README there is a hyperlink in the text under the "Media" heading indented to redirect the user to tech publications where MultiOn was mentioned, although this hyperlink leads to a dead page.

examples requirements.txt should have langchain version requirement

If an older version of langchain is installed, error ModuleNotFoundError: No module named 'langchain.agents.agent_toolkits.multion' is raised.

Needs browser/page refresh often within pages that have tabs to update properly

I have a page that I use often called products, and I was using multion to delete 20k products. I had to slow it down to doing one product delete at a time as it would get way off if I let it run for very long. Obviously it would work ok for a few and I wasn't trying to do 20k at once, but after about 4 correct iterations, it would suddenly be on the wrong page etc. The only thing I could surmise is that because it was a tab INside the browser window it would refresh the product count/numbers and the way it was labeling the page elements was being resorted so then it was trying to click the exact same element each time even though the page was being reordered or something? I am not much of a programmer so Im sorry if this doesnt make sense.... I can take a short video or something if you would like to see what task I am using it for and whatnot. Thanks for all your work!

GPU example not working

The example has lots of deprecation warnings and an error:

C:Workspace\multion-api\.venv\Lib\site-packages\langchain\llms\__init__.py:548:` LangChainDeprecationWarning: Importing LLMs from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:

`from langchain_community.llms import OpenAI`.

To install langchain-community run `pip install -U langchain-community`.
  warnings.warn(
C:Workspace\multion-api\.venv\Lib\site-packages\langchain\chat_models\__init__.py:31: LangChainDeprecationWarning: Importing chat models from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:

`from langchain_community.chat_models import ChatOpenAI`.

To install langchain-community run `pip install -U langchain-community`.
  warnings.warn(
C:Workspace\multion-api\.venv\Lib\site-packages\langchain_core\_api\deprecation.py:117: LangChainDeprecationWarning: The class `langchain_community.llms.openai.OpenAI` was deprecated in langchain-community 0.0.10 and will be removed in 0.2.0. An updated version of the class exists in the langchain-openai package and should be used instead. To use it run `pip install -U langchain-openai` and import as `from langchain_openai import OpenAI`.
  warn_deprecated(
C:Workspace\multion-api\.venv\Lib\site-packages\langchain_core\_api\deprecation.py:117: LangChainDeprecationWarning: The function `initialize_agent` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use Use new agent constructor methods like create_react_agent, create_json_agent, create_structured_chat_agent, etc. instead.
  warn_deprecated(
C:Workspace\multion-api\.venv\Lib\site-packages\langchain_core\_api\deprecation.py:117: LangChainDeprecationWarning: The function `run` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use invoke instead.
  warn_deprecated(
Traceback (most recent call last):
  File "C:Workspace\multion-api\examples\gpu_agent\agent_example.py", line 51, in <module>
    agent(query=PROMPT)
  File "C:Workspace\multion-api\examples\gpu_agent\agent_example.py", line 37, in agent
    return agent_executor.run(query)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:Workspace\multion-api\.venv\Lib\site-packages\langchain_core\_api\deprecation.py", line 145, in warning_emitting_wrapper
    return wrapped(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:Workspace\multion-api\.venv\Lib\site-packages\langchain\chains\base.py", line 538, in run      
    return self(args[0], callbacks=callbacks, tags=tags, metadata=metadata)[
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:Workspace\multion-api\.venv\Lib\site-packages\langchain_core\_api\deprecation.py", line 145, in warning_emitting_wrapper
    return wrapped(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:Workspace\multion-api\.venv\Lib\site-packages\langchain\chains\base.py", line 363, in __call__ 
    return self.invoke(
           ^^^^^^^^^^^^
  File "C:Workspace\multion-api\.venv\Lib\site-packages\langchain\chains\base.py", line 138, in invoke   
    inputs = self.prep_inputs(input)
             ^^^^^^^^^^^^^^^^^^^^^^^
  File "C:Workspace\multion-api\.venv\Lib\site-packages\langchain\chains\base.py", line 465, in prep_inputs
    raise ValueError(
ValueError: A single string input was passed in, but this chain expects multiple inputs ({'', 'input'}). When a chain expects multiple inputs, please call it by passing in a dictionary, eg `chain({'foo': 1, 'bar': 2})```

get_screenshot() throws exception for empty string

response:

{
  ...
  screenshot = ''
}

screenshot = response["screenshot"]
get_screenshot(screenshot)

When running Multion_api_example.ipynb with set_remote(True), browse() comes back with an empty screenshot - which might also be a bug, it works fine when set_remote(False). This empty screenshot causes get_screenshot() to throw an exception. May want to handle it elegantly so that the notebook continues.

test blackhole

[Bug] Python SDK: Fix root dir for token storage on Collab

Permission issues for the default token storage directory is making MultiOn not work on Colab currently

Add AgentOps

Add observability to MultiON sessions

Task scheluder example error.

After setting up task scheluder, i can't login to multion.

task-scheduler-py3.10) C:\Users\hu\Documents\multion_exampels\examples\task_scheduler>python scheduler_application.py
Getting OpenAI API Key...
Submitted API key:  SECRET
Set OPENAI_API_KEY:  SECRET
Exception in thread Thread-2 (login):
Traceback (most recent call last):
  File "C:\Users\hu\.pyenv\pyenv-win\versions\3.10.11\lib\threading.py", line 1016, in _bootstrap_inner
    self.run()
  File "C:\Users\hu\.pyenv\pyenv-win\versions\3.10.11\lib\threading.py", line 953, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Users\hu\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\multion\multion.py", line 300, in login
    _multion_instance.login()
  File "C:\Users\hu\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\multion\multion.py", line 72, in login
    self.client_id = self.register_client()
  File "C:\Users\hu\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\multion\multion.py", line 105, in register_client
    raise Exception("Failed to register client")
Exception: Failed to register client

After adding multion_token.txt with multion token i have errors:

Thread is still running. Closing the thread.
An error occurred when calling message handler
Traceback (most recent call last):
  File "C:\Users\ha\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\pystray\_win32.py", line 401, in _dispatcher
    return int(icon._message_handlers.get(
  File "C:\Users\ha\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\pystray\_win32.py", line 213, in _on_notify
    descriptors[index - 1](self)
  File "C:\Users\ha\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\pystray\_base.py", line 324, in inner
    callback(self)
  File "C:\Users\ha\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\pystray\_base.py", line 449, in __call__
    return self._action(icon, self)
  File "C:\Users\ha\Documents\multion_exampels\examples\task_scheduler\scheduler_application.py", line 590, in after_click
    login_multion()
  File "C:\Users\ha\Documents\multion_exampels\examples\task_scheduler\scheduler_application.py", line 444, in login_multion
    multion_login()
  File "C:\Users\ha\Documents\multion_exampels\examples\task_scheduler\scheduler_application.py", line 97, in multion_login
    t1.cancel()
AttributeError: 'Thread' object has no attribute 'cancel'
Exception in thread Thread-2 (login):
Traceback (most recent call last):
  File "C:\Users\ha\.pyenv\pyenv-win\versions\3.10.11\lib\threading.py", line 1016, in _bootstrap_inner
    self.run()
  File "C:\Users\ha\.pyenv\pyenv-win\versions\3.10.11\lib\threading.py", line 953, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Users\ha\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\multion\multion.py", line 300, in login
    _multion_instance.login()
  File "C:\Users\ha\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\multion\multion.py", line 72, in login
    self.client_id = self.register_client()
  File "C:\Users\ha\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\multion\multion.py", line 105, in register_client
    raise Exception("Failed to register client")
Exception: Failed to register client

When i use poetry and .env file with keys - i also have error:

PS C:\Users\hu\Documents\multion_exampels\examples\task_scheduler>  c:; cd 'c:\Users\hu\Documents\multion_exampels\examples\task_scheduler'; & 'c:\Users\hu\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\Scripts\python.exe' 'c:\Users\hu\.vscode\extensions\ms-python.debugpy-2024.1.10371006-win32-x64\bundled\libs\debugpy\adapter/../..\debugpy\launcher' '54935' '--' 'C:\Users\hu\Documents\multion_exampels\examples\task_scheduler\scheduler_application.py' 
Set OPENAI_API_KEY: 
Exception in thread Thread-7 (login):
Traceback (most recent call last):
  File "C:\Users\hu\.pyenv\pyenv-win\versions\3.10.11\lib\threading.py", line 1016, in _bootstrap_inner
    self.run()
  File "C:\Users\hu\.pyenv\pyenv-win\versions\3.10.11\lib\threading.py", line 953, in run
    self._target(*self._args, **self._kwargs)
  File "c:\Users\hu\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\multion\multion.py", line 300, in login
    _multion_instance.login()
  File "c:\Users\hu\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\multion\multion.py", line 72, in login
    self.client_id = self.register_client()
  File "c:\Users\hu\AppData\Local\pypoetry\Cache\virtualenvs\task-scheduler-KfTrUDer-py3.10\lib\site-packages\multion\multion.py", line 105, in register_client
    raise Exception("Failed to register client")
Exception: Failed to register client

@hackgoofer @0xmmo @omarshaya @tjdharani

Error with langchain integration

I am having an error while trying to integrate Multion with langchain.

here is the code I am executing:

def multion_agent(input):
    toolkit = MultionToolkit()
    tools = toolkit.get_tools()
    multion_api_key = os.getenv("MULTION_API_KEY")
    multion.login(use_api=True, multion_api_key=multion_api_key)
    
    agent = initialize_agent(
        tools,
        llm=model,
        agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,
        verbose=True,
    )
    
    result = agent.run(input)
    
    print(f"{result}")

multion_agent("What are top best restaruants in Ghana based on their ranks?")

The agent kicks off successfully and then there is an error:

$ python main.py
Logged in using API key.


> Entering new AgentExecutor chain...
Action:

{
"action": "create_multion_session",
"action_input": {
"url": "https://www.google.com/",
"query": "What are top best restaruants in Ghana based on their ranks?"
}
}

Request failed with status code: 405
Response text: {"detail":"Method Not Allowed"}
Request failed with status code: 405
Response text: {"detail":"Method Not Allowed"}
Request failed with status code: 405
Response text: {"detail":"Method Not Allowed"}
Request failed with status code: 405
Response text: {"detail":"Method Not Allowed"}
Traceback (most recent call last):
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain_community\tools\multion\create_session.py", line 61, in _run
    response = multion.new_session({"input": query, "url": url})
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\deprecated\classic.py", line 285, in wrapper_function       
    return wrapped_(*args_, **kwargs_)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\multion\multion.py", line 600, in new_session
    return _multion_instance.new_session(data)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\multion\multion.py", line 358, in new_session
    return self.post(url, data)
           ^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\multion\multion.py", line 289, in post
    raise Exception("Failed to get a valid response after 5 attempts")
Exception: Failed to get a valid response after 5 attempts

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\main.py", line 15, in <module>
    multion_agent("What are top best restaruants in Ghana based on their ranks?")
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\langchain_lab\lab.py", line 216, in multion_agent
    result = agent.run(input)
             ^^^^^^^^^^^^^^^^
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain_core\_api\deprecation.py", line 145, in warning_emitting_wrapper
    return wrapped(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain\chains\base.py", line 538, in run
    return self(args[0], callbacks=callbacks, tags=tags, metadata=metadata)[
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain_core\_api\deprecation.py", line 145, in warning_emitting_wrapper
    return wrapped(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain\chains\base.py", line 363, in __call__
    return self.invoke(
           ^^^^^^^^^^^^
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain\chains\base.py", line 162, in invoke
    raise e
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain\chains\base.py", line 156, in invoke
    self._call(inputs, run_manager=run_manager)
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain\agents\agent.py", line 1329, in _call
    next_step_output = self._take_next_step(
                       ^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain\agents\agent.py", line 1055, in _take_next_step   
    [
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain\agents\agent.py", line 1055, in <listcomp>
    [
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain\agents\agent.py", line 1151, in _iter_next_step
    observation = tool.run(
                  ^^^^^^^^^
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain_core\tools.py", line 401, in run
    raise e
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain_core\tools.py", line 358, in run
    self._run(*tool_args, run_manager=run_manager, **tool_kwargs)
  File "C:\Users\ERASMUS\Documents\projects\inboxgenius\.venv\Lib\site-packages\langchain_community\tools\multion\create_session.py", line 67, in _run
    raise Exception(f"An error occurred: {e}")
Exception: An error occurred: Failed to get a valid response after 5 attempts

Server Disconnected. Please press connect in the Multion extension popup

Getting "Server Disconnected. Please press connect in the Multion extension popup" when trying to use the client:

import multion

api_key = 'xxxx'

multion.login(use_api=True, multion_api_key=api_key)

multion.set_remote(False)

Logged in using API key.

response = multion.create_session({"url": "https://www.linkedin.com"})
session_id = response['session_id']
session_id

Request failed with status code: 404
Response text: {"detail":"Could not connect to the extension"}

Add Open source

Hi there,
Heard good things about your tech and approach
Just wanted to come and say I hope you'll consider developing MultiON AI openly

Soon there will be a plethora of ai projects like hyperwrite and yourselves and I can't wait to contribute to the ones that open

And in general I think most revenue will come from B2B/B2C business operations, open source would give you a super dev boost

All the best!

{
  'result': 'ANSWER: The weather today in San Francisco is mostly cloudy with a temperature of 57°F (13°C). The precipitation is 0%, humidity is at 90%, and the wind speed is 5 mph.\n\nSTATUS: DONE',
   'status': 'DONE',
   'lastUrl': 'https://www.google.com/search?q=weather+today+in+san+francisco',
   'content': '',
   'screenshot': '',
   'sessionId': '0c8dcab0-9a9b-46fc-96b4-02544d5c8d6e'
}

create_session:

{
  ...
  'session_id': ...
}

I can get a real sample result for create_session in a bit, having trouble connecting at the moment