AI Docs
Chat & Streaming
Transports
Structured Outputs
Tools
Middleware
UI
Chat UI Recipes
Interrupts
MCP
- MCP Server ToolsUpdated
- Managed MCP with chat()Updated
- Manual MCPUpdated
- MCP Type GenerationUpdated
- MCP Client InputUpdated
- MCP Server Tools: AdvancedNew
- MCP EventsNew
- MCP AppsUpdated
- Serve Tools over HTTPUpdated
- Serve Resources and PromptsUpdated
- Ask for InputUpdated
- Draft Text from a ToolUpdated
- MCP Server TasksUpdated
- MCP Server AuthUpdated
- MCP Server SessionsUpdated
- MCP Server on stdioUpdated
Persistence
Persistence (Advanced)
Media
- GenerationsUpdated
- Realtime Voice ChatUpdated
- Text-to-SpeechUpdated
- TranscriptionUpdated
- Transcription: AdvancedNew
- Voice CreationUpdated
- Audio RecordingUpdated
- Audio GenerationUpdated
- Image GenerationUpdated
- Image Generation: AdvancedNew
- Video GenerationUpdated
- Video Generation: AdvancedNew
- Live GenerationUpdated
- World GenerationUpdated
- Generation HooksUpdated
Embeddings
Reranking
Evaluate
Code Mode
Sandboxes
- OverviewUpdated
- Quick StartUpdated
- ProvidersUpdated
- HarnessesUpdated
- Harness AuthUpdated
- WorkspaceUpdated
- ToolsUpdated
- PolicyUpdated
- Lifecycle & SnapshotsUpdated
- Portable SnapshotsUpdated
- Keep Files After ReloadUpdated
- Save a Named VersionUpdated
- Branch From a VersionUpdated
- Send a Frozen FileUpdated
- Let the Agent Save and ForkUpdated
- Pick Which Files to KeepUpdated
- What a Snapshot StoresUpdated
- Instance DurabilityUpdated
- Durable RunsUpdated
- EventsUpdated
Sandboxes (Advanced)
Advanced
- Runtime ContextUpdated
- Bring Your Own KeyUpdated
- Debug LoggingUpdated
- Multimodal ContentUpdated
- Files APIUpdated
- Per-Model Type SafetyUpdated
- Runtime Adapter SwitchingUpdated
- Tree-ShakingUpdated
- Extend AdapterUpdated
- Extend Adapter: AdvancedNew
- Typed Pre-Configured OptionsUpdated
- Test with a Fake ModelUpdated
- Prompt CachingUpdated
- Mid-Conversation ChangesUpdated
- Approval Flow ProcessingUpdated
AI/LLM: This documentation page is available in plain markdown format at/ai/latest/docs/ui/recipes/basic-chat.md
Chat UI Recipes
A chat box with no tools
Start here. This chat has no tools, no interrupts, and no styling.
For a Start app with BYOK, open Basic Chat.
You need three components: a layout, a message, and a text part. Leave the rest out.
Server#
tsx
import { chat, toServerSentEventsResponse } from '@tanstack/ai'
import { openaiText } from '@tanstack/ai-openai'
export async function POST(request: Request) {
const json: unknown = await request.json()
if (typeof json !== 'object' || json === null || !('messages' in json)) {
return new Response('Invalid body', { status: 400 })
}
const messages = json.messages
const stream = chat({
adapter: openaiText('gpt-5.6'),
messages: Array.isArray(messages) ? messages : [],
})
return toServerSentEventsResponse(stream)
}Client#
tsx
import { fetchServerSentEvents } from '@tanstack/ai-react'
import { createChatHook } from '@tanstack/ai-react/ui'
const chatOptions = {
connection: fetchServerSentEvents('/api/chat'),
}
const { useAppChat, useChatContext } = createChatHook({
options: chatOptions,
components: {
input: () => {
const chat = useChatContext()
return (
<form
onSubmit={(event) => {
event.preventDefault()
const field = event.currentTarget.elements.namedItem('message')
if (!(field instanceof HTMLInputElement)) return
const text = field.value.trim()
if (!text) return
field.value = ''
void chat.sendMessage(text)
}}
>
<input name="message" />
<button type="submit">Send</button>
</form>
)
},
layout: ({ Messages, Input }) => (
<main>
<Messages />
<Input />
</main>
),
message: ({ message, Parts }) => (
<article data-role={message.role}>
<Parts />
</article>
),
},
partsComponents: {
text: ({ part }) => <p>{part.content}</p>,
fallback: () => null,
},
})
export function ChatScreen() {
const chat = useAppChat()
return <chat.AppChat />
}Render <ChatScreen />. Type a message. The reply streams into the page.
What each piece does#
layout gets Messages, Interrupts, and Input as components. Render them where you want them. Interrupts is unused here, so leave it out.
message gets one message plus a Parts component. Parts walks that message and picks a component per part.
partsComponents.text renders text parts. fallback catches every part type you did not register. It returns null here, so anything else is silent.
Next#
- One tool that renders as raw JSON? See format a tool.
- Need the user to approve something? See tool approval.
- Want markdown with colored fences? See Highlight markdown code.
- Using Solid, Vue, or Svelte? The same shape applies. See Solid, Vue, or Svelte.