​
Overview

Agents working on text-based tasks are highly prone to rewriting the text unnecessarily, editing parts that shouldn’t be modified, and introducing errors. This creates a process where developers must manually make adjustments and continuously implement checkpoints, especially when handling text-based use cases.

Within the Upsonic framework, we have a Canvas feature specifically designed to address this issue and provide a direct solution. This feature includes specialized and sensitive functions tailored for creating and editing a text canvas.

​
Creating an Canvas

A Canvas is created with a specific name and can be assigned to a Task or class as a tool. This enables Agents or Direct operations to easily perform text edits.

from upsonic.tools import Canvas

my_mail_canvas = Canvas("Mail to Joe") # Creating an canvas with an uniqe name

​
Putting Canvas to Task

Canvas objects are immediately ready to be used as tools. You can add them directly as elements within the tools parameter of a Task, configuring your task to utilize this Canvas.

from upsonic import Task

task = Task(
	"Write an mail to joe about our projects, Use Canvas",
	tools=[my_mail_canvas] # Adding canvas as tool
)

​
Running Over an Agent

You can execute tasks equipped with the Canvas tool through an Agent.

from upsonic import Agent

agent = Agent("Mail Writer")

agent.print_do(task)

​
Running Over an Direct

You can execute tasks equipped with the Canvas tool through Direct.

from upsonic import Direct

direct = Direct()

direct.print_do(task)

​
Getting Current Canvas State

You can retrieve the final state of canvases executed via Agent or Direct by using the get_current_state_of_canvas function.

result = my_mail_canvas.get_current_state_of_canvas()

print(result)