> ## 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.

# Step Decorator

The step decorator will log steps based on the decorated function. By default, the arguments of the function will be used as the input of the step and the return value will be used as the output.

Under the hood, the step decorator is using the [cl.Step](/api-reference/step-class) class.

## Parameters

<ParamField path="name" type="str" optional>
  The name of the step. Default to the name of the decorated function.
</ParamField>

<ParamField path="type" type="str" default="undefined" optional>
  The type of the step, useful for monitoring and debugging.
</ParamField>

<ParamField path="language" type="str" optional>
  Language of the output. See
  [https://react-code-blocks-rajinwonderland.vercel.app/?path=/story/codeblock--supported-languages](https://react-code-blocks-rajinwonderland.vercel.app/?path=/story/codeblock--supported-languages)
  for a list of supported languages.
</ParamField>

<ParamField path="show_input" type="Union[bool, str]" default={false} optional>
  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.
</ParamField>

<ParamField path="default_open" type="bool" default={false} optional>
  Whether the step should render expanded by default in the UI.

  <Note>
    Since version **2.3.0**. Requires a `defaultOpen` column in the `steps` table for SQL-based data layers. See the [migration guide](/guides/migration/2.3.0).
  </Note>
</ParamField>

<ParamField path="metadata" type="Dict" optional>
  Custom metadata dictionary to attach to the step. Persisted with the step in the data layer.
</ParamField>

<ParamField path="tags" type="List[str]" optional>
  Tags to attach to the step for filtering and categorization.
</ParamField>

<ParamField path="id" type="str" optional>
  Unique identifier for the step. Auto-generated as a UUID if not provided.
</ParamField>

<ParamField path="icon" type="str" optional>
  Name of a Lucide icon to display instead of the default step avatar. See [https://lucide.dev/icons](https://lucide.dev/icons) for available icons.

  <Note>
    Since version **2.11.0**.
  </Note>
</ParamField>

<ParamField path="parent_id" type="str" optional>
  ID of the parent step. Automatically resolved from the decorator nesting hierarchy if not provided.
</ParamField>

## Access the Current step

You can access the current step object using `cl.context.current_step` and override values.

```python theme={null}
import chainlit as cl

@cl.step
async def my_step():
    current_step = cl.context.current_step

    # Override the input of the step
    current_step.input = "My custom input"

    # Override the output of the step
    current_step.output = "My custom output"
```

## Stream the Output

```python theme={null}
from openai import AsyncOpenAI

import chainlit as cl

client = AsyncOpenAI(api_key="YOUR_API_KEY")

@cl.step(type="llm")
async def gpt4():
    settings = {
        "model": "gpt-4",
        "temperature": 0,
    }

    stream = await client.chat.completions.create(
        messages=message_history, stream=True, **settings
    )

    current_step = cl.context.current_step

    async for part in stream:
        delta = part.choices[0].delta

        if delta.content:
            # Stream the output of the step
            await current_step.stream_token(delta.content)
```

## Nest Steps

If another step decorated function is called inside the decorated function, the child step will be nested under the parent step.

```python theme={null}
import chainlit as cl

@cl.step
async def parent_step():
    await child_step()
    return "Parent step output"

@cl.step
async def child_step():
    return "Child step output"

@cl.on_chat_start
async def main():
    await parent_step()
```