ai-sdk-core

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

AI SDK Core

Production-ready backend AI with Vercel AI SDK v5.

Last Updated: 2025-11-21

基于Vercel AI SDK v5的生产级后端AI解决方案。

最后更新时间：2025-11-21

Quick Start (5 Minutes)

快速开始（5分钟）

Installation

安装

bash

bun add ai @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google workers-ai-provider zod  # preferred

bash

bun add ai @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google workers-ai-provider zod  # 推荐方式

or: npm install ai @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google workers-ai-provider zod

或使用npm安装：npm install ai @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google workers-ai-provider zod

undefined

undefined

Environment Variables

环境变量

bash

undefined

bash

undefined

.env

OPENAI_API_KEY=sk-... ANTHROPIC_API_KEY=sk-ant-... GOOGLE_GENERATIVE_AI_API_KEY=...

undefined

OPENAI_API_KEY=sk-... ANTHROPIC_API_KEY=sk-ant-... GOOGLE_GENERATIVE_AI_API_KEY=...

undefined

First Example: Generate Text

第一个示例：生成文本

typescript

import { generateText } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await generateText({
  model: openai('gpt-4-turbo'),
  prompt: 'What is TypeScript?',
});

console.log(result.text);

typescript

import { generateText } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await generateText({
  model: openai('gpt-4-turbo'),
  prompt: 'What is TypeScript?',
});

console.log(result.text);

First Example: Streaming Chat

第一个示例：流式聊天

typescript

import { streamText } from 'ai';
import { anthropic } from '@ai-sdk/anthropic';

const stream = streamText({
  model: anthropic('claude-sonnet-4-5-20250929'),
  messages: [
    { role: 'user', content: 'Tell me a story' },
  ],
});

for await (const chunk of stream.textStream) {
  process.stdout.write(chunk);
}

typescript

import { streamText } from 'ai';
import { anthropic } from '@ai-sdk/anthropic';

const stream = streamText({
  model: anthropic('claude-sonnet-4-5-20250929'),
  messages: [
    { role: 'user', content: 'Tell me a story' },
  ],
});

for await (const chunk of stream.textStream) {
  process.stdout.write(chunk);
}

First Example: Structured Output

第一个示例：结构化输出

typescript

import { generateObject } from 'ai';
import { openai } from '@ai-sdk/openai';
import { z } from 'zod';

const result = await generateObject({
  model: openai('gpt-4'),
  schema: z.object({
    name: z.string(),
    age: z.number(),
    skills: z.array(z.string()),
  }),
  prompt: 'Generate a person profile for a software engineer',
});

console.log(result.object);
// { name: "Alice", age: 28, skills: ["TypeScript", "React"] }

typescript

import { generateObject } from 'ai';
import { openai } from '@ai-sdk/openai';
import { z } from 'zod';

const result = await generateObject({
  model: openai('gpt-4'),
  schema: z.object({
    name: z.string(),
    age: z.number(),
    skills: z.array(z.string()),
  }),
  prompt: 'Generate a person profile for a software engineer',
});

console.log(result.object);
// { name: "Alice", age: 28, skills: ["TypeScript", "React"] }

Secure Installation

安全安装

This installs 6+ AI provider packages simultaneously — a large dependency surface to audit. Before installing, follow supply chain security best practices:

Block post-install scripts —
```
npm config set ignore-scripts true
```
(or Bun: disabled by default)
Cooldown period — Wait 7 days for new package versions to be vetted by the community

Audit before installing — Run

socket package score npm <pkg>

or use

socket npm install <pkg>

to check packages

Load the

dependency-upgrade

skill for full security configuration including Socket CLI integration, cooldown setup, lockfile validation, and CI enforcement.

此命令会同时安装6+个AI供应商包，依赖面较广需要审核。安装前请遵循供应链安全最佳实践：

阻止安装后脚本 —
```
npm config set ignore-scripts true
```
（Bun默认已禁用）
冷却期 — 等待7天，让社区验证新版本包的安全性

安装前审核 — 运行

socket package score npm <pkg>

或使用

socket npm install <pkg>

检查包安全性

加载

dependency-upgrade

技能以获取完整安全配置，包括Socket CLI集成、冷却期设置、锁文件验证和CI强制执行。

Core Functions

核心功能

Load
references/core-functions.md
for complete API reference of all 4 core functions.

加载
references/core-functions.md
获取所有4个核心函数的完整API参考

Quick Overview

快速概览

AI SDK v5 provides 4 core functions:

Function	Output	Streaming	Use Case
`generateText()`	Text	No	Batch processing, simple completions
`streamText()`	Text	Yes	Chat UIs, long responses
`generateObject()`	Structured	No	Data extraction, JSON generation
`streamObject()`	Structured	Yes	Real-time forms, progressive UIs

AI SDK v5提供4个核心函数：

函数	输出类型	是否支持流式	使用场景
`generateText()`	文本	否	批量处理、简单补全
`streamText()`	文本	是	聊天UI、长文本响应
`generateObject()`	结构化数据	否	数据提取、JSON生成
`streamObject()`	结构化数据	是	实时表单、渐进式UI

Basic Example

基础示例

typescript

import { generateText } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await generateText({
  model: openai('gpt-4-turbo'),
  prompt: 'Explain quantum computing',
});

console.log(result.text);

→ Load
references/core-functions.md
for: Complete signatures, tool usage patterns, error handling, streaming examples, comparison table

typescript

import { generateText } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await generateText({
  model: openai('gpt-4-turbo'),
  prompt: 'Explain quantum computing',
});

console.log(result.text);

→ 加载
references/core-functions.md
获取：完整签名、工具使用模式、错误处理、流式示例、对比表

Provider Setup & Configuration

供应商设置与配置

Load
references/provider-setup.md
for complete setup instructions for all providers.

加载
references/provider-setup.md
获取所有供应商的完整设置说明

Quick Overview

快速概览

AI SDK v5 supports 4 major providers:

Provider	Environment Variable	Latest Models
OpenAI	`OPENAI_API_KEY`	GPT-5, GPT-4 Turbo
Anthropic	`ANTHROPIC_API_KEY`	Claude Sonnet 4.5, Opus 4
Google	`GOOGLE_GENERATIVE_AI_API_KEY`	Gemini 2.5 Pro/Flash
Cloudflare	Workers AI binding	Llama 3.1, Qwen 2.5

AI SDK v5支持4大主流供应商：

供应商	环境变量	最新模型
OpenAI	`OPENAI_API_KEY`	GPT-5、GPT-4 Turbo
Anthropic	`ANTHROPIC_API_KEY`	Claude Sonnet 4.5、Opus 4
Google	`GOOGLE_GENERATIVE_AI_API_KEY`	Gemini 2.5 Pro/Flash
Cloudflare	Workers AI绑定	Llama 3.1、Qwen 2.5

Basic Setup

基础设置

typescript

import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';

// API key from environment
const result = await generateText({
  model: openai('gpt-4-turbo'),
  prompt: 'Hello',
});

→ Load
references/provider-setup.md
for: Complete API configuration, rate limiting, error handling, Cloudflare Workers optimization, model selection guides

typescript

import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';

// 从环境变量获取API密钥
const result = await generateText({
  model: openai('gpt-4-turbo'),
  prompt: 'Hello',
});

→ 加载
references/provider-setup.md
获取：完整API配置、速率限制、错误处理、Cloudflare Workers优化、模型选择指南

Tool Calling & Agents

工具调用与Agent

Load
references/tools-and-agents.md
for complete tool and agent documentation.

加载
references/tools-and-agents.md
获取完整的工具与Agent文档

Quick Overview

快速概览

Tools allow models to call external functions. Agents manage multi-step workflows.

v5 Tool Changes:

```
parameters
```
→
```
inputSchema
```
(Zod schema)
Tool properties:
```
args
```
→
```
input
```
,
```
result
```
→
```
output
```
```
maxSteps
```
→
```
stopWhen(stepCountIs(n))
```

工具允许模型调用外部函数，Agent用于管理多步骤工作流。

v5版本工具变更：

```
parameters
```
→
```
inputSchema
```
（Zod schema）
工具属性：
```
args
```
→
```
input
```
，
```
result
```
→
```
output
```
```
maxSteps
```
→
```
stopWhen(stepCountIs(n))
```

Basic Tool Example

基础工具示例

typescript

import { generateText, tool } from 'ai';
import { z } from 'zod';

const result = await generateText({
  model: openai('gpt-4'),
  tools: {
    weather: tool({
      description: 'Get weather for a location',
      inputSchema: z.object({ location: z.string() }),
      execute: async ({ location }) => {
        return { temperature: 72, condition: 'sunny' };
      },
    }),
  },
  prompt: 'What is the weather in Tokyo?',
});

→ Load
references/tools-and-agents.md
for: Agent class usage, multi-step execution, dynamic tools, stop conditions

typescript

import { generateText, tool } from 'ai';
import { z } from 'zod';

const result = await generateText({
  model: openai('gpt-4'),
  tools: {
    weather: tool({
      description: 'Get weather for a location',
      inputSchema: z.object({ location: z.string() }),
      execute: async ({ location }) => {
        return { temperature: 72, condition: 'sunny' };
      },
    }),
  },
  prompt: 'What is the weather in Tokyo?',
});

→ 加载
references/tools-and-agents.md
获取： Agent类使用方法、多步骤执行、动态工具、停止条件

Critical v4→v5 Migration

重要v4→v5迁移指南

Load
references/v4-to-v5-migration.md
for complete migration guide.

加载
references/v4-to-v5-migration.md
获取完整迁移指南

Key Breaking Changes

关键破坏性变更

AI SDK v5 has 9 major breaking changes:

```
maxTokens
```
→
```
maxOutputTokens
```
```
parameters
```
→
```
inputSchema
```
(Zod)
```
maxSteps
```
→
```
stopWhen(stepCountIs(n))
```
```
CoreMessage
```
→
```
ModelMessage
```
Package reorganization (
```
ai/rsc
```
→
```
@ai-sdk/rsc
```
)

AI SDK v5有9大破坏性变更：

```
maxTokens
```
→
```
maxOutputTokens
```
```
parameters
```
→
```
inputSchema
```
（Zod）
```
maxSteps
```
→
```
stopWhen(stepCountIs(n))
```
```
CoreMessage
```
→
```
ModelMessage
```
包重组（
```
ai/rsc
```
→
```
@ai-sdk/rsc
```
）

Automated Migration

自动化迁移

bash

bunx ai migrate  # Auto-migrates most changes

→ Load
references/v4-to-v5-migration.md
for: Complete breaking changes list, migration examples, checklist, official migration guide link

bash

bunx ai migrate  # 自动迁移大部分变更

→ 加载
references/v4-to-v5-migration.md
获取：完整破坏性变更列表、迁移示例、检查清单、官方迁移指南链接

Top 12 Errors & Solutions

12大常见错误与解决方案

1. AI_APICallError

Cause: API request failed (network, auth, rate limit).

Solution:

typescript

import { AI_APICallError } from 'ai';

try {
  const result = await generateText({
    model: openai('gpt-4'),
    prompt: 'Hello',
  });
} catch (error) {
  if (error instanceof AI_APICallError) {
    console.error('API call failed:', error.message);
    console.error('Status code:', error.statusCode);
    console.error('Response:', error.responseBody);

    // Check common causes
    if (error.statusCode === 401) {
      // Invalid API key
    } else if (error.statusCode === 429) {
      // Rate limit - implement backoff
    } else if (error.statusCode >= 500) {
      // Provider issue - retry
    }
  }
}

Prevention:

Validate API keys at startup
Implement retry logic with exponential backoff
Monitor rate limits
Handle network errors gracefully

原因： API请求失败（网络问题、认证错误、速率限制）。

解决方案：

typescript

import { AI_APICallError } from 'ai';

try {
  const result = await generateText({
    model: openai('gpt-4'),
    prompt: 'Hello',
  });
} catch (error) {
  if (error instanceof AI_APICallError) {
    console.error('API调用失败:', error.message);
    console.error('状态码:', error.statusCode);
    console.error('响应内容:', error.responseBody);

    // 检查常见原因
    if (error.statusCode === 401) {
      // API密钥无效
    } else if (error.statusCode === 429) {
      // 速率限制 - 实现退避策略
    } else if (error.statusCode >= 500) {
      // 供应商服务问题 - 重试请求
    }
  }
}

预防措施：

在启动时验证API密钥
实现带指数退避的重试逻辑
监控速率限制
优雅处理网络错误

2. AI_NoObjectGeneratedError

Cause: Model didn't generate valid object matching schema.

Solution:

typescript

import { AI_NoObjectGeneratedError } from 'ai';

try {
  const result = await generateObject({
    model: openai('gpt-4'),
    schema: z.object({ /* complex schema */ }),
    prompt: 'Generate data',
  });
} catch (error) {
  if (error instanceof AI_NoObjectGeneratedError) {
    console.error('No valid object generated');

    // Solutions:
    // 1. Simplify schema
    // 2. Add more context to prompt
    // 3. Provide examples in prompt
    // 4. Try different model (gpt-4 better than gpt-3.5 for complex objects)
  }
}

Prevention:

Start with simple schemas, add complexity incrementally
Include examples in prompt: "Generate a person like: { name: 'Alice', age: 30 }"
Use GPT-4 for complex structured output
Test schemas with sample data first

原因： 模型未生成符合schema的有效对象。

解决方案：

typescript

import { AI_NoObjectGeneratedError } from 'ai';

try {
  const result = await generateObject({
    model: openai('gpt-4'),
    schema: z.object({ /* 复杂schema */ }),
    prompt: 'Generate data',
  });
} catch (error) {
  if (error instanceof AI_NoObjectGeneratedError) {
    console.error('未生成有效对象');

    // 解决方法:
    // 1. 简化schema
    // 2. 在提示词中添加更多上下文
    // 3. 在提示词中提供示例
    // 4. 尝试使用不同模型（gpt-4处理复杂对象优于gpt-3.5）
  }
}

预防措施：

从简单schema开始，逐步增加复杂度
在提示词中包含示例："生成如下格式的人物信息：{ name: 'Alice', age: 30 }"
使用GPT-4处理复杂结构化输出
先使用样本数据测试schema

3. Worker Startup Limit (270ms+)

3. Worker启动超时（270ms+）

Cause: AI SDK v5 + Zod initialization overhead in Cloudflare Workers exceeds startup limits.

Solution:

typescript

// BAD: Top-level imports cause startup overhead
import { createWorkersAI } from 'workers-ai-provider';
import { complexSchema } from './schemas';

const workersai = createWorkersAI({ binding: env.AI });

// GOOD: Lazy initialization inside handler
export default {
  async fetch(request, env) {
    const { createWorkersAI } = await import('workers-ai-provider');
    const workersai = createWorkersAI({ binding: env.AI });

    // Use workersai here
  }
}

Prevention:

Move AI SDK imports inside route handlers
Minimize top-level Zod schemas
Monitor Worker startup time (must be <400ms)
Use Wrangler's startup time reporting

GitHub Issue: Search for "Workers startup limit" in Vercel AI SDK issues

→ Load
references/error-catalog.md
for errors #4-#12 with complete solutions.

Remaining 9 errors: 4. streamText Fails Silently (RESOLVED in v4.1.22) 5. AI_LoadAPIKeyError 6. AI_InvalidArgumentError 7. AI_NoContentGeneratedError 8. AI_TypeValidationError 9. AI_RetryError 10. Rate Limiting Errors 11. TypeScript Performance with Zod 12. Invalid JSON Response (Provider-Specific)

For complete error catalog: See complete error reference at https://ai-sdk.dev/docs/reference/ai-sdk-errors

原因： Cloudflare Workers中AI SDK v5 + Zod初始化开销超过启动限制。

解决方案：

typescript

// 错误写法：顶层导入会导致启动开销
import { createWorkersAI } from 'workers-ai-provider';
import { complexSchema } from './schemas';

const workersai = createWorkersAI({ binding: env.AI });

// 正确写法：在处理器内部延迟初始化
export default {
  async fetch(request, env) {
    const { createWorkersAI } = await import('workers-ai-provider');
    const workersai = createWorkersAI({ binding: env.AI });

    // 在此处使用workersai
  }
}

预防措施：

将AI SDK导入移至路由处理器内部
减少顶层Zod schema数量
监控Worker启动时间（必须<400ms）
使用Wrangler的启动时间报告功能

GitHub Issue： 在Vercel AI SDK issues中搜索"Workers startup limit"

→ 加载
references/error-catalog.md
获取错误#4-#12的完整解决方案

剩余9个错误： 4. streamText静默失败（已在v4.1.22修复） 5. AI_LoadAPIKeyError 6. AI_InvalidArgumentError 7. AI_NoContentGeneratedError 8. AI_TypeValidationError 9. AI_RetryError 10. 速率限制错误 11. Zod相关TypeScript性能问题 12. 无效JSON响应（供应商特定）

完整错误目录： 查看完整错误参考：https://ai-sdk.dev/docs/reference/ai-sdk-errors

Production Best Practices

生产环境最佳实践

Load
references/production-guide.md
for complete production deployment guide.

加载
references/production-guide.md
获取完整生产部署指南

Key Categories

核心分类

Performance: Streaming patterns, token limits, provider caching, Zod optimization
Error Handling: try-catch patterns, retry logic, proper logging
Cost Optimization: Model selection, token limits, response caching
Cloudflare Workers: Lazy imports, startup monitoring, streaming responses
Next.js/Vercel: Server Actions, Server Components, loading states

性能优化：流式处理模式、令牌限制、供应商缓存、Zod优化
错误处理：try-catch模式、重试逻辑、正确日志记录
成本优化：模型选择、令牌限制、响应缓存
Cloudflare Workers：延迟导入、启动监控、流式响应
Next.js/Vercel：Server Actions、Server Components、加载状态

Quick Example

快速示例

typescript

// Use streaming for user-facing responses
const stream = streamText({
  model: openai('gpt-4'),
  prompt: 'Long essay',
  maxOutputTokens: 500,
  maxRetries: 3,
});

return stream.toDataStreamResponse();

→ Load
references/production-guide.md
for: Platform-specific patterns, deployment checklists, optimization strategies

typescript

// 面向用户的响应使用流式处理
const stream = streamText({
  model: openai('gpt-4'),
  prompt: 'Long essay',
  maxOutputTokens: 500,
  maxRetries: 3,
});

return stream.toDataStreamResponse();

→ 加载
references/production-guide.md
获取：平台特定模式、部署检查清单、优化策略

When to Load References

何时加载参考文档

Load
references/core-functions.md
when:

User needs complete API documentation for generateText, streamText, generateObject, or streamObject
Questions about function signatures, parameters, or return types
Need detailed tool usage patterns or streaming examples
Troubleshooting function-specific errors

Load
references/provider-setup.md
when:

Setting up OpenAI, Anthropic, Google, or Cloudflare Workers AI
Configuring API keys or environment variables
Troubleshooting provider-specific errors (rate limits, authentication)
Questions about model selection or best practices for each provider
Cloudflare Workers startup optimization needed

Load
references/tools-and-agents.md
when:

Implementing tool calling or agent workflows
Questions about Agent class vs raw generateText
Setting up multi-step execution with stopWhen
Dynamic tools or complex agentic patterns

Load
references/v4-to-v5-migration.md
when:

Migrating existing v4 codebase to v5
Questions about breaking changes
Need migration examples or automated migration tool
Troubleshooting migration-related errors

Load
references/error-catalog.md
when:

User encounters any of the 12 common errors (beyond top 3 shown inline)
Need complete error solutions with code examples
Troubleshooting production errors
Questions about error prevention strategies

Load
references/production-guide.md
when:

Deploying to production (any platform)
Performance optimization needed
Cost optimization questions
Platform-specific patterns (Cloudflare Workers, Next.js/Vercel)
Error handling or logging strategies

当以下情况时加载
references/core-functions.md
：

需要generateText、streamText、generateObject或streamObject的完整API文档
有关于函数签名、参数或返回类型的疑问
需要详细的工具使用模式或流式示例
排查特定函数相关的错误

当以下情况时加载
references/provider-setup.md
：

设置OpenAI、Anthropic、Google或Cloudflare Workers AI
配置API密钥或环境变量
排查供应商特定错误（速率限制、认证问题）
有关于模型选择或各供应商最佳实践的疑问
需要Cloudflare Workers启动优化方案

当以下情况时加载
references/tools-and-agents.md
：

实现工具调用或Agent工作流
有关于Agent类与原生generateText对比的疑问
设置带stopWhen的多步骤执行
动态工具或复杂Agent模式

当以下情况时加载
references/v4-to-v5-migration.md
：

将现有v4代码库迁移至v5
有关于破坏性变更的疑问
需要迁移示例或自动化迁移工具
排查迁移相关错误

当以下情况时加载
references/error-catalog.md
：

遇到12种常见错误中的任意一种（除了上面展示的前3种）
需要完整的错误解决方案及代码示例
排查生产环境错误
有关于错误预防策略的疑问

当以下情况时加载
references/production-guide.md
：

部署至生产环境（任意平台）
需要性能优化方案
有关于成本优化的疑问
平台特定模式（Cloudflare Workers、Next.js/Vercel）
错误处理或日志记录策略

When to Use This Skill

何时使用本技能

Use ai-sdk-core when:

适合使用ai-sdk-core的场景：

Building backend AI features (server-side text generation)
Implementing server-side text generation (Node.js, Workers, Next.js)
Creating structured AI outputs (JSON, forms, data extraction)
Building AI agents with tools (multi-step workflows)
Integrating multiple AI providers (OpenAI, Anthropic, Google, Cloudflare)
Migrating from AI SDK v4 to v5
Encountering AI SDK errors (AI_APICallError, AI_NoObjectGeneratedError, etc.)
Using AI in Cloudflare Workers (with workers-ai-provider)
Using AI in Next.js Server Components/Actions
Need consistent API across different LLM providers

构建后端AI功能（服务端文本生成）
实现服务端文本生成（Node.js、Workers、Next.js）
创建结构化AI输出（JSON、表单、数据提取）
构建带工具的AI Agent（多步骤工作流）
集成多个AI供应商（OpenAI、Anthropic、Google、Cloudflare）
从AI SDK v4迁移至v5
遇到AI SDK错误（AI_APICallError、AI_NoObjectGeneratedError等）
在Cloudflare Workers中使用AI（搭配workers-ai-provider）
在Next.js Server Components/Actions中使用AI
需要跨不同LLM供应商的统一API

Don't use this skill when:

不适合使用本技能的场景：

Building React chat UIs (use ai-sdk-ui skill instead)
Need frontend hooks like useChat (use ai-sdk-ui skill instead)
Need advanced topics like embeddings or image generation (check official docs)
Building native Cloudflare Workers AI apps without multi-provider (use cloudflare-workers-ai skill instead)
Need Generative UI / RSC (see https://ai-sdk.dev/docs/ai-sdk-rsc)

构建React聊天UI（请使用ai-sdk-ui技能）
需要useChat等前端钩子（请使用ai-sdk-ui技能）
需要嵌入或图像生成等高级功能（请查看官方文档）
构建无需多供应商的原生Cloudflare Workers AI应用（请使用cloudflare-workers-ai技能）
需要生成式UI / RSC（查看https://ai-sdk.dev/docs/ai-sdk-rsc）

Dependencies & Versions

依赖与版本

json

{
  "dependencies": {
    "ai": "^5.0.116",
    "@ai-sdk/openai": "^2.0.88",
    "@ai-sdk/anthropic": "^2.0.56",
    "@ai-sdk/google": "^2.0.51",
    "workers-ai-provider": "^2.0.0",
    "zod": "^3.23.8"
  },
  "devDependencies": {
    "@types/node": "^24.10.1",
    "typescript": "^5.9.3"
  }
}

Version Notes:

AI SDK v5.0.116+ (stable, latest as of December 2025)
v6 is in beta - not covered in this skill
Zod compatibility: This skill uses Zod 3.x, but AI SDK 5 officially supports both Zod 3.x and Zod 4.x (4.1.12 latest)
- Zod 4 recommended for new projects (released August 2025)
- Zod 4 has breaking changes: error APIs,
```
.default()
```
  behavior,
```
ZodError.errors
```
  removed
- Some peer dependency warnings may occur with
```
zod-to-json-schema
```
  when using Zod 4
- See https://zod.dev/v4/changelog for migration guide
Provider packages at 2.0+ for v5 compatibility

Check Latest Versions:

bash

npm view ai version
npm view @ai-sdk/openai version
npm view @ai-sdk/anthropic version
npm view @ai-sdk/google version
npm view workers-ai-provider version
npm view zod version  # Check for Zod 4.x updates

json

{
  "dependencies": {
    "ai": "^5.0.116",
    "@ai-sdk/openai": "^2.0.88",
    "@ai-sdk/anthropic": "^2.0.56",
    "@ai-sdk/google": "^2.0.51",
    "workers-ai-provider": "^2.0.0",
    "zod": "^3.23.8"
  },
  "devDependencies": {
    "@types/node": "^24.10.1",
    "typescript": "^5.9.3"
  }
}

版本说明：

AI SDK v5.0.116+（稳定版，截至2025年12月为最新版本）
v6处于测试阶段 - 本技能不包含相关内容
Zod兼容性：本技能使用Zod 3.x，但AI SDK 5官方同时支持Zod 3.x和Zod 4.x（最新版4.1.12）
- 新项目推荐使用Zod 4（2025年8月发布）
- Zod 4存在破坏性变更：错误API、
```
.default()
```
  行为、
```
ZodError.errors
```
  移除
- 使用Zod 4时，
```
zod-to-json-schema
```
  可能会出现一些对等依赖警告
- 查看https://zod.dev/v4/changelog获取迁移指南
供应商包版本需为2.0+以兼容v5

检查最新版本：

bash

npm view ai version
npm view @ai-sdk/openai version
npm view @ai-sdk/anthropic version
npm view @ai-sdk/google version
npm view workers-ai-provider version
npm view zod version  # 检查Zod 4.x更新

Links to Official Documentation

官方文档链接

Core Documentation

核心文档

AI SDK Introduction: https://ai-sdk.dev/docs/introduction
AI SDK Core Overview: https://ai-sdk.dev/docs/ai-sdk-core/overview
Generating Text: https://ai-sdk.dev/docs/ai-sdk-core/generating-text
Generating Structured Data: https://ai-sdk.dev/docs/ai-sdk-core/generating-structured-data
Tools and Tool Calling: https://ai-sdk.dev/docs/ai-sdk-core/tools-and-tool-calling
Agents Overview: https://ai-sdk.dev/docs/agents/overview
Foundations: https://ai-sdk.dev/docs/foundations/overview

AI SDK介绍： https://ai-sdk.dev/docs/introduction
AI SDK Core概述： https://ai-sdk.dev/docs/ai-sdk-core/overview
文本生成： https://ai-sdk.dev/docs/ai-sdk-core/generating-text
结构化数据生成： https://ai-sdk.dev/docs/ai-sdk-core/generating-structured-data
工具与工具调用： https://ai-sdk.dev/docs/ai-sdk-core/tools-and-tool-calling
Agent概述： https://ai-sdk.dev/docs/agents/overview
基础原理： https://ai-sdk.dev/docs/foundations/overview

Advanced Topics (Not Replicated in This Skill)

高级主题（本技能未覆盖）

Embeddings: https://ai-sdk.dev/docs/ai-sdk-core/embeddings
Image Generation: https://ai-sdk.dev/docs/ai-sdk-core/generating-images
Transcription: https://ai-sdk.dev/docs/ai-sdk-core/generating-transcriptions
Speech: https://ai-sdk.dev/docs/ai-sdk-core/generating-speech
MCP Tools: https://ai-sdk.dev/docs/ai-sdk-core/mcp-tools
Telemetry: https://ai-sdk.dev/docs/ai-sdk-core/telemetry
Generative UI: https://ai-sdk.dev/docs/ai-sdk-rsc

嵌入： https://ai-sdk.dev/docs/ai-sdk-core/embeddings
图像生成： https://ai-sdk.dev/docs/ai-sdk-core/generating-images
转录： https://ai-sdk.dev/docs/ai-sdk-core/generating-transcriptions
语音生成： https://ai-sdk.dev/docs/ai-sdk-core/generating-speech
MCP工具： https://ai-sdk.dev/docs/ai-sdk-core/mcp-tools
遥测： https://ai-sdk.dev/docs/ai-sdk-core/telemetry
生成式UI： https://ai-sdk.dev/docs/ai-sdk-rsc

Migration & Troubleshooting

迁移与故障排查

v4→v5 Migration Guide: https://ai-sdk.dev/docs/migration-guides/migration-guide-5-0
All Error Types (28 total): https://ai-sdk.dev/docs/reference/ai-sdk-errors
Troubleshooting Guide: https://ai-sdk.dev/docs/troubleshooting

v4→v5迁移指南： https://ai-sdk.dev/docs/migration-guides/migration-guide-5-0
所有错误类型（共28种）： https://ai-sdk.dev/docs/reference/ai-sdk-errors
故障排查指南： https://ai-sdk.dev/docs/troubleshooting

Provider Documentation

供应商文档

OpenAI Provider: https://ai-sdk.dev/providers/ai-sdk-providers/openai
Anthropic Provider: https://ai-sdk.dev/providers/ai-sdk-providers/anthropic
Google Provider: https://ai-sdk.dev/providers/ai-sdk-providers/google
All Providers (25+): https://ai-sdk.dev/providers/overview
Community Providers: https://ai-sdk.dev/providers/community-providers

OpenAI供应商： https://ai-sdk.dev/providers/ai-sdk-providers/openai
Anthropic供应商： https://ai-sdk.dev/providers/ai-sdk-providers/anthropic
Google供应商： https://ai-sdk.dev/providers/ai-sdk-providers/google
所有供应商（25+）： https://ai-sdk.dev/providers/overview
社区供应商： https://ai-sdk.dev/providers/community-providers

Cloudflare Integration

Cloudflare集成

Workers AI Provider (Community): https://ai-sdk.dev/providers/community-providers/cloudflare-workers-ai
Cloudflare Workers AI Docs: https://developers.cloudflare.com/workers-ai/
workers-ai-provider GitHub: https://github.com/cloudflare/ai/tree/main/packages/workers-ai-provider
Cloudflare AI SDK Configuration: https://developers.cloudflare.com/workers-ai/configuration/ai-sdk/

Workers AI供应商（社区）： https://ai-sdk.dev/providers/community-providers/cloudflare-workers-ai
Cloudflare Workers AI文档： https://developers.cloudflare.com/workers-ai/
workers-ai-provider GitHub： https://github.com/cloudflare/ai/tree/main/packages/workers-ai-provider
Cloudflare AI SDK配置： https://developers.cloudflare.com/workers-ai/configuration/ai-sdk/

Vercel / Next.js Integration

Vercel / Next.js集成

Vercel AI SDK 5.0 Blog: https://vercel.com/blog/ai-sdk-5
Next.js App Router Integration: https://ai-sdk.dev/docs/getting-started/nextjs-app-router
Next.js Pages Router Integration: https://ai-sdk.dev/docs/getting-started/nextjs-pages-router
Vercel Functions: https://vercel.com/docs/functions
Vercel Streaming: https://vercel.com/docs/functions/streaming

Vercel AI SDK 5.0博客： https://vercel.com/blog/ai-sdk-5
Next.js App Router集成： https://ai-sdk.dev/docs/getting-started/nextjs-app-router
Next.js Pages Router集成： https://ai-sdk.dev/docs/getting-started/nextjs-pages-router
Vercel Functions： https://vercel.com/docs/functions
Vercel流式处理： https://vercel.com/docs/functions/streaming

GitHub & Community

GitHub与社区

GitHub Repository: https://github.com/vercel/ai
GitHub Issues: https://github.com/vercel/ai/issues
Discord Community: https://discord.gg/vercel

GitHub仓库： https://github.com/vercel/ai
GitHub Issues： https://github.com/vercel/ai/issues
Discord社区： https://discord.gg/vercel

Templates & References

模板与参考资源

This skill includes:

13 Templates: Ready-to-use code examples in
```
templates/
```
5 Reference Docs: Detailed guides in
```
references/
```
1 Script: Version checker in
```
scripts/
```

All files are optimized for copy-paste into your project.

Last Updated: 2025-12-22 Skill Version: 1.1.0 AI SDK Version: 5.0.116+

本技能包含：

13个模板：
```
templates/
```
目录下的即用型代码示例
5份参考文档：
```
references/
```
目录下的详细指南
1个脚本：
```
scripts/
```
目录下的版本检查工具

所有文件均已优化，可直接复制粘贴到项目中使用。

最后更新时间： 2025-12-22 技能版本： 1.1.0 AI SDK版本： 5.0.116+

ai-sdk-core

Original

Translation

AI SDK Core

AI SDK Core

Table of Contents

目录

Quick Start (5 Minutes)

快速开始（5分钟）

Installation

安装

or: npm install ai @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google workers-ai-provider zod

或使用npm安装：npm install ai @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google workers-ai-provider zod

Environment Variables

环境变量

.env

.env

First Example: Generate Text

第一个示例：生成文本

First Example: Streaming Chat

第一个示例：流式聊天

First Example: Structured Output

第一个示例：结构化输出

Secure Installation

安全安装

Core Functions

核心功能

Quick Overview

快速概览

Basic Example

基础示例

Provider Setup & Configuration

供应商设置与配置

Quick Overview

快速概览

Basic Setup

基础设置

Tool Calling & Agents

工具调用与Agent

Quick Overview

快速概览

Basic Tool Example

基础工具示例

Critical v4→v5 Migration

重要v4→v5迁移指南

Key Breaking Changes

关键破坏性变更

Automated Migration

自动化迁移

Top 12 Errors & Solutions

12大常见错误与解决方案

1. AI_APICallError

1. AI_APICallError

2. AI_NoObjectGeneratedError

2. AI_NoObjectGeneratedError

3. Worker Startup Limit (270ms+)

3. Worker启动超时（270ms+）

Production Best Practices

生产环境最佳实践

Key Categories

核心分类

Quick Example

快速示例

When to Load References

何时加载参考文档

When to Use This Skill

何时使用本技能

Use ai-sdk-core when:

适合使用ai-sdk-core的场景：

Don't use this skill when:

不适合使用本技能的场景：

Dependencies & Versions

依赖与版本

Links to Official Documentation

官方文档链接

Core Documentation

核心文档

Advanced Topics (Not Replicated in This Skill)

高级主题（本技能未覆盖）

Migration & Troubleshooting