Skip to main content

How to build an LLM generated UI

This guide will walk through some high level concepts and code snippets for building generative UI's using LangChain.js. To see the full code for generative UI, click here to visit our official LangChain Next.js template.

The sample implements a tool calling agent, which outputs an interactive UI element when streaming intermediate outputs of tool calls to the client.

We introduce two utilities which wraps the AI SDK to make it easier to yield React elements inside runnables and tool calls: createRunnableUI and streamRunnableUI.

  • The streamRunnableUI executes the provided Runnable with streamEvents method and sends every stream event to the client via the React Server Components stream.
  • The createRunnableUI wraps the createStreamableUI function from AI SDK to properly hook into the Runnable event stream.

The usage is then as follows:

"use server";

const tool = new DynamicStructuredTool({
// ...
func: async (input, config) => {
// create a new streamable UI and wire it up to the streamEvents
const stream = createRunnableUI(config);

const result = await images(input);

// update the UI element with the rendered results
.map((image) => image.thumbnail)
.slice(0, input.limit)}

return `[Returned ${result.images_results.length} images]`;

// add LLM, prompt, etc...

const tools = [tool];

export const agentExecutor = new AgentExecutor({
agent: createToolCallingAgent({ llm, tools, prompt }),

As of langchain version 0.2.8, the createToolCallingAgent function now supports OpenAI-formatted tools.

async function agent(inputs: { input: string }) {
"use server";
return streamRunnableUI(agentExecutor, inputs);

export const EndpointsContext = exposeEndpoints({ agent });

In order to ensure all of the client components are included in the bundle, we need to wrap all of the Server Actions into exposeEndpoints method. These endpoints will be accessible from the client via the Context API, seen in the useActions hook.

"use client";
import type { EndpointsContext } from "./agent";

export default function Page() {
const actions = useActions<typeof EndpointsContext>();
const [node, setNode] = useState();

return (

onClick={async () => {
setNode(await actions.agent({ input: "cats" }));
Get images of cats

Was this page helpful?

You can also leave detailed feedback on GitHub.