📄 ai-sdk/docs/reference/ai-sdk-rsc/create-streamable-ui
File: create-streamable-ui.md | Updated: 11/15/2025
Source: https://ai-sdk.dev/docs/reference/ai-sdk-rsc/create-streamable-ui
Menu
v5 (Latest)
AI SDK 5.x
Model Context Protocol (MCP) Tools
Copy markdown
=============================================================================================================
AI SDK RSC is currently experimental. We recommend using AI SDK UI for production. For guidance on migrating from RSC to UI, see our migration guide .
Create a stream that sends UI from the server to the client. On the client side, it can be rendered as a normal React node.
import { createStreamableUI } from "@ai-sdk/rsc"
Parameters
initialValue?:
ReactNode
The initial value of the streamable UI.
Returns
value:
ReactNode
The value of the streamable UI. This can be returned from a Server Action and received by the client.
Methods
update:
(ReactNode) => void
Updates the current UI node. It takes a new UI node and replaces the old one.
append:
(ReactNode) => void
Appends a new UI node to the end of the old one. Once appended a new UI node, the previous UI node cannot be updated anymore.
done:
(ReactNode | null) => void
Marks the UI node as finalized and closes the stream. Once called, the UI node cannot be updated or appended anymore. This method is always required to be called, otherwise the response will be stuck in a loading state.
error:
(Error) => void
Signals that there is an error in the UI stream. It will be thrown on the client side and caught by the nearest error boundary component.
Render a React component during a tool call
On this page
Deploy and Scale AI Apps with Vercel.
Vercel delivers the infrastructure and developer experience you need to ship reliable AI-powered applications at scale.
Trusted by industry leaders:
- OpenAI
- Photoroom
