
Vercel AI SDK 5
FreeStreamline your AI feature development with SDK v5.
Free · Opens the source repo
What Vercel AI SDK 5 does
Vercel AI SDK 5 provides a modern approach to building AI features, allowing developers to seamlessly integrate chat, streaming, and function calling into their applications. This SDK is specifically designed for those migrating from AI SDK v4, offering a more structured and efficient way to manage chat interactions and message handling. With the updated useChat hook, developers can easily set up chat functionalities by defining transport mechanisms that streamline communication with backend APIs.
The SDK introduces a new message structure that enhances the way messages are handled and displayed. Instead of a single string for message content, messages are now represented as arrays of MessagePart, allowing for richer interactions that can include text, images, and tool calls. This change not only improves the flexibility of the chat interface but also enables developers to create more dynamic user experiences by rendering various message types appropriately.
For backend integration, the SDK supports server-side implementations that can handle chat requests and responses efficiently. By utilizing functions like streamText, developers can implement real-time chat features that respond to user inputs instantly. The SDK also allows for easy integration with tools like LangChain, enabling the use of advanced AI models and streaming capabilities. This makes it an ideal choice for developers looking to leverage cutting-edge AI technologies in their applications.
Whether you're building a chat application, enhancing user interaction with AI, or migrating from an older SDK version, Vercel AI SDK 5 provides the tools and patterns necessary to create robust AI-driven features with ease.
When to use it
Use this skill when developing applications that require chat functionalities or AI interactions, especially when migrating from AI SDK v4.
When not to use it
This skill may not be suitable for projects that do not involve AI features or require a different architecture than what SDK v5 offers.
What you can build with it
Migrating from AI SDK 4
Transitioning to SDK v5 allows developers to leverage new features and improved message handling.
Building a Chat Application
Developers can create robust chat applications using the updated `useChat` hook for streamlined user interactions.
Integrating AI Models
Utilize the SDK to connect with advanced AI models and implement real-time streaming responses.
How to install Vercel AI SDK 5
View source1. Install with the skills CLI
npx skills add prowler-cloud/prowler/ai-sdk-5 --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by prowler-cloudBreaking Changes from AI SDK 4
// ❌ AI SDK 4 (OLD)
import { useChat } from "ai";
const { messages, handleSubmit, input, handleInputChange } = useChat({
api: "/api/chat",
});
// ✅ AI SDK 5 (NEW)
import { useChat } from "@ai-sdk/react";
import { DefaultChatTransport } from "ai";
const { messages, sendMessage } = useChat({
transport: new DefaultChatTransport({ api: "/api/chat" }),
});
Client Setup
import { useChat } from "@ai-sdk/react";
import { DefaultChatTransport } from "ai";
import { useState } from "react";
export function Chat() {
const [input, setInput] = useState("");
const { messages, sendMessage, isLoading, error } = useChat({
transport: new DefaultChatTransport({ api: "/api/chat" }),
});
const handleSubmit = (e: React.FormEvent) => {
e.preventDefault();
if (!input.trim()) return;
sendMessage({ text: input });
setInput("");
};
return (
<div>
<div>
{messages.map((message) => (
<Message key={message.id} message={message} />
))}
</div>
<form onSubmit={handleSubmit}>
<input
value={input}
onChange={(e) => setInput(e.target.value)}
placeholder="Type a message..."
disabled={isLoading}
/>
<button type="submit" disabled={isLoading}>
Send
</button>
</form>
{error && <div>Error: {error.message}</div>}
</div>
);
}
UIMessage Structure (v5)
// ❌ Old: message.content was a string
// ✅ New: message.parts is an array
interface UIMessage {
id: string;
role: "user" | "assistant" | "system";
parts: MessagePart[];
}
type MessagePart =
| { type: "text"; text: string }
| { type: "image"; image: string }
| { type: "tool-call"; toolCallId: string; toolName: string; args: unknown }
| { type: "tool-result"; toolCallId: string; result: unknown };
// Extract text from parts
function getMessageText(message: UIMessage): string {
return message.parts
.filter((part): part is { type: "text"; text: string } => part.type === "text")
.map((part) => part.text)
.join("");
}
// Render message
function Message({ message }: { message: UIMessage }) {
return (
<div className={message.role === "user" ? "user" : "assistant"}>
{message.parts.map((part, index) => {
if (part.type === "text") {
return <p key={index}>{part.text}</p>;
}
if (part.type === "image") {
return <img key={index} src={part.image} alt="" />;
}
return null;
})}
</div>
);
}
Server-Side (Route Handler)
// app/api/chat/route.ts
import { openai } from "@ai-sdk/openai";
import { streamText } from "ai";
export async function POST(req: Request) {
const { messages } = await req.json();
const result = await streamText({
model: openai("gpt-4o"),
messages,
system: "You are a helpful assistant.",
});
return result.toDataStreamResponse();
}
With LangChain
// app/api/chat/route.ts
import { toUIMessageStream } from "@ai-sdk/langchain";
import { ChatOpenAI } from "@langchain/openai";
import { HumanMessage, AIMessage } from "@langchain/core/messages";
export async function POST(req: Request) {
const { messages } = await req.json();
const model = new ChatOpenAI({
modelName: "gpt-4o",
streaming: true,
});
// Convert UI messages to LangChain format
const langchainMessages = messages.map((m) => {
const text = m.parts
.filter((p) => p.type === "text")
.map((p) => p.text)
.join("");
return m.role === "user"
? new HumanMessage(text)
: new AIMessage(text);
});
const stream = await model.stream(langchainMessages);
return toUIMessageStream(stream).toDataStreamResponse();
}
Streaming with Tools
import { openai } from "@ai-sdk/openai";
import { streamText, tool } from "ai";
import { z } from "zod";
const result = await streamText({
model: openai("gpt-4o"),
messages,
tools: {
getWeather: tool({
description: "Get weather for a location",
parameters: z.object({
location: z.string().describe("City name"),
}),
execute: async ({ location }) => {
// Fetch weather data
return { temperature: 72, condition: "sunny" };
},
}),
},
});
useCompletion (Text Generation)
import { useCompletion } from "@ai-sdk/react";
import { DefaultCompletionTransport } from "ai";
const { completion, complete, isLoading } = useCompletion({
transport: new DefaultCompletionTransport({ api: "/api/complete" }),
});
// Trigger completion
await complete("Write a haiku about");
Error Handling
const { error, messages, sendMessage } = useChat({
transport: new DefaultChatTransport({ api: "/api/chat" }),
onError: (error) => {
console.error("Chat error:", error);
toast.error("Failed to send message");
},
});
// Display error
{error && (
<div className="error">
{error.message}
<button onClick={() => sendMessage({ text: lastInput })}>
Retry
</button>
</div>
)}
Frequently asked questions about Vercel AI SDK 5
Similar skills
WinMD API Search
Easily find and explore Windows desktop APIs.
WebMCPify
Transform any web app into an agent-ready platform.
Phoenix Tracing
Instrument LLM applications with OpenInference tracing.
Foundry Hosted Agent CopilotKit
Guidance for developing agentic web apps on Azure.
Power Automate Foundation
Connect AI agents to Power Automate seamlessly.
Power Automate Flow Builder
Efficiently build and deploy Power Automate flows programmatically.
