Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.chainlit.io/llms.txt

Use this file to discover all available pages before exploring further.

The Step class is a Python Context Manager that can be used to create steps in your chainlit app. The step is created when the context manager is entered and is updated to the client when the context manager is exited.

​
Parameters

​
name
str
The name of the step. Default to the name of the decorated function.
​
type
Enum
default:"undefined"
The type of the step, useful for monitoring and debugging.
​
elements
List[Element]
Elements to attach to the step.
​
language
str
Language of the output. See https://react-code-blocks-rajinwonderland.vercel.app/?path=/story/codeblock—supported-languages for a list of supported languages.
​
show_input
Union[bool, str]
default:false
By default only the output of the step is shown. Set this to True to also show the input. You can also set this to a language like json or python to syntax highlight the input.
​
default_open
bool
default:false
Whether the step should render expanded by default in the UI.
Since version 2.3.0. Requires a defaultOpen column in the steps table for SQL-based data layers. See the migration guide.
​
metadata
Dict
Custom metadata dictionary to attach to the step. Persisted with the step in the data layer.
​
tags
List[str]
Tags to attach to the step for filtering and categorization.
​
id
str
Unique identifier for the step. Auto-generated as a UUID if not provided.
​
parent_id
str
ID of the parent step. Automatically resolved from the context manager nesting hierarchy if not provided.
​
icon
str
Name of a Lucide icon to display instead of the default step avatar. See https://lucide.dev/icons for available icons.
Since version 2.11.0.
​
thread_id
str
ID of the thread this step belongs to. Automatically resolved from the current session context if not provided.

​
Send a Step

import chainlit as cl

@cl.on_message
async def main():
    async with cl.Step(name="Test") as step:
        # Step is sent as soon as the context manager is entered
        step.input = "hello"
        step.output = "world"

    # Step is updated when the context manager is exited

​
Stream the Output

from openai import AsyncOpenAI

import chainlit as cl

client = AsyncOpenAI()

@cl.on_message
async def main(msg: cl.Message):

    async with cl.Step(name="gpt4", type="llm") as step:
        step.input = msg.content

        stream = await client.chat.completions.create(
            messages=[{"role": "user", "content": msg.content}],
            stream=True,
            model="gpt-4",
            temperature=0,
        )

        async for part in stream:
            delta = part.choices[0].delta
            if delta.content:
                # Stream the output of the step
                await step.stream_token(delta.content)

​
Nest Steps

To nest steps, simply create a step inside another step. 
import chainlit as cl


@cl.on_chat_start
async def main():
    async with cl.Step(name="Parent step") as parent_step:
        parent_step.input = "Parent step input"

        async with cl.Step(name="Child step") as child_step:
            child_step.input = "Child step input"
            child_step.output = "Child step output"

        parent_step.output = "Parent step output"

​
Update a Step

import chainlit as cl


@cl.on_chat_start
async def main():
    async with cl.Step(name="Parent step") as step:
        step.input = "Parent step input"
        step.output = "Parent step output"

    await cl.sleep(2)

    step.output = "Parent step output updated"
    await step.update()

​
Remove a Step

import chainlit as cl


@cl.on_chat_start
async def main():
    async with cl.Step(name="Parent step") as step:
        step.input = "Parent step input"
        step.output = "Parent step output"

    await cl.sleep(2)

    await step.remove()