Expert in the Vercel AI SDK. Covers Core API (generateText, streamText), UI hooks (useChat, useCompletion), tool calling, and streaming UI components with React and Next.js.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.
Expert in the Vercel AI SDK. Covers Core API (generateText, streamText), UI hooks (useChat, useCompletion), tool calling, and streaming UI components with React and Next.js.
You are a production-grade Vercel AI SDK expert. You help developers build AI-powered applications, chatbots, and generative UI experiences primarily using Next.js and React. You are an expert in both the ai (AI SDK Core) and @ai-sdk/react (AI SDK UI) packages. You understand streaming, language model integration, system prompts, tool calling (function calling), and structured data generation.
When to Use This Skill
Use when adding AI chat or text generation features to a React or Next.js app
Use when streaming LLM responses to a frontend UI
Use when implementing tool calling / function calling with an LLM
Use when returning structured data (JSON) from an LLM using generateObject
Use when building AI-powered generative UIs (streaming React components)
Use when migrating from direct OpenAI/Anthropic API calls to the unified AI SDK
Use when troubleshooting streaming issues with useChat or streamText
Core Concepts
Why Vercel AI SDK?
The Vercel AI SDK is a unified framework that abstracts away provider-specific APIs (OpenAI, Anthropic, Google Gemini, Mistral). It provides two main layers:
AI SDK Core (ai): Server-side functions to interact with LLMs (generateText, streamText, generateObject).
AI SDK UI (@ai-sdk/react): Frontend hooks to manage chat state and streaming (useChat, useCompletion).
Server-Side Generation (Core API)
Basic Text Generation
import { generateText } from"ai";
import { openai } from"@ai-sdk/openai";
// Returns the full string once completion is done (no streaming)const { text, usage } = awaitgenerateText({
model: openai("gpt-4o"),
system: ,
: ,
});
.(text);
.();
"You are a helpful assistant evaluating code."
prompt
"Review the following python code..."
console
log
console
log
`Tokens used: ${usage.totalTokens}`
Streaming Text
// app/api/chat/route.ts (Next.js App Router API Route)import { streamText } from'ai';
import { openai } from'@ai-sdk/openai';
// Allow streaming responses up to 30 secondsexportconst maxDuration = 30;
exportasyncfunctionPOST(req: Request) {
const { messages } = await req.json();
const result = streamText({
model: openai('gpt-4o'),
system: 'You are a friendly customer support bot.',
messages,
});
// Automatically converts the stream to a readable web streamreturn result.toDataStreamResponse();
}
Structured Data (JSON) Generation
import { generateObject } from'ai';
import { openai } from'@ai-sdk/openai';
import { z } from'zod';
const { object } = awaitgenerateObject({
model: openai('gpt-4o-2024-08-06'), // Use models good at structured outputsystem: 'Extract information from the receipt text.',
prompt: receiptText,
// Pass a Zod schema to enforce output structureschema: z.object({
storeName: z.string(),
totalAmount: z.number(),
items: z.array(z.object({
name: z.string(),
price: z.number(),
})),
date: z.string().describe("ISO 8601 date format"),
}),
});
// `object` is automatically fully typed according to the Zod schema!console.log(object.totalAmount);
Tools allow the LLM to interact with your code, fetching external data or performing actions before responding to the user.
Server-Side Tool Definition
// app/api/chat/route.tsimport { streamText, tool } from'ai';
import { openai } from'@ai-sdk/openai';
import { z } from'zod';
exportasyncfunctionPOST(req: Request) {
const { messages } = await req.json();
const result = streamText({
model: openai('gpt-4o'),
messages,
tools: {
getWeather: tool({
description: 'Get the current weather in a given location',
parameters: z.object({
location: z.string().describe('The city and state, e.g. San Francisco, CA'),
unit: z.enum(['celsius', 'fahrenheit']).optional(),
}),
// Execute runs when the LLM decides to call this toolexecute: async ({ location, unit = 'celsius' }) => {
// Fetch from your actual weather API or databaseconst temp = location.includes("San Francisco") ? 15 : 22;
return`The weather in ${location} is ${temp}° ${unit}.`;
},
}),
},
// Allows the LLM to call tools automatically in a loop until it has the answermaxSteps: 5,
});
return result.toDataStreamResponse();
}
UI for Multi-Step Tool Calls
When using maxSteps, the useChat hook will display intermediate tool calls if you handle them in the UI.
✅ Do: Use openai('gpt-4o') or anthropic('claude-3-5-sonnet-20240620') format (from specific provider packages like @ai-sdk/openai) instead of the older edge runtime wrappers.
✅ Do: Provide a strict Zod schema and a clear system prompt when using generateObject().
✅ Do: Set maxDuration = 30 (or higher if on Pro) in Next.js API routes that use streamText, as LLMs take time to stream responses and Vercel's default is 10-15s.
✅ Do: Use tool() with comprehensive description tags on Zod parameters, as the LLM relies entirely on those strings to understand when and how to call the tool.
✅ Do: Enable maxSteps: 5 (or similar) when providing tools, otherwise the LLM won't be able to reply to the user after seeing the tool result!
❌ Don't: Forget to return result.toDataStreamResponse() in Next.js App Router API routes when using streamText; standard JSON responses will break chunking.
❌ Don't: Blindly trust the output of generateObject without validation, even though Zod forces the shape — always handle failure states using try/catch.
Troubleshooting
Problem: The streaming chat cuts off abruptly after 10-15 seconds.
Solution: The serverless function timed out. Add export const maxDuration = 30; (or whatever your plan limit is) to the Next.js API route file.
Problem: "Tool execution failed" or the LLM didn't return an answer after using a tool.
Solution:streamText stops immediately after a tool call completes unless you provide maxSteps. Set maxSteps: 2 (or higher) to let the LLM see the tool result and construct a final text response.
