Step

LLM powered Assistants take a series of steps to process a user’s request. Unlike a Message, a Step has an input/output, a start/end and can be nested.

Together, Steps form a Chain of Thought. Displaying the steps of a Chain of Thought is useful both for the end user (to understand what the Assistant is doing) and for the developer (to debug the Assistant).

​

A Simple Chain of Thought

Lets take a simple example of a Chain of Thought that takes a user’s message, process it and sends a response.

import chainlit as cl


@cl.step
async def tool():
    # Simulate a running task
    await cl.sleep(2)

    return "Response from the tool!"


@cl.on_message
async def main(message: cl.Message):
    # Call the tool
    tool_res = await tool()

    # Send the final answer.
    await cl.Message(content="This is the final answer").send()

Output of the code above

​

Step API

There are two ways to create steps, either by using the the @cl.step decorator or by using the cl.Step class.