Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From ai-sdk-core
Delivers production-ready backend AI using Vercel AI SDK v5 for text generation, structured output, tools, agents with multi-provider support (OpenAI, Anthropic, Google). Resolves errors like AI_APICallError and streaming issues.
npx claudepluginhub secondsky/claude-skills --plugin ai-sdk-coreHow this skill is triggered — by the user, by Claude, or both
Slash command
/ai-sdk-core:ai-sdk-coreThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Production-ready backend AI with Vercel AI SDK v5.
references/core-functions.mdreferences/error-catalog.mdreferences/links-to-official-docs.mdreferences/production-guide.mdreferences/production-patterns.mdreferences/provider-setup.mdreferences/providers-quickstart.mdreferences/tools-and-agents.mdreferences/top-errors.mdreferences/v4-to-v5-migration.mdreferences/v5-breaking-changes.mdscripts/check-versions.shtemplates/agent-with-tools.tstemplates/anthropic-setup.tstemplates/cloudflare-worker-integration.tstemplates/generate-object-zod.tstemplates/generate-text-basic.tstemplates/google-setup.tstemplates/multi-step-execution.tstemplates/nextjs-server-action.tsProvides expert guidance on Vercel AI SDK for building AI features like chat interfaces, text generation, structured output, tool calling, agents, streaming, embeddings, reranking, image generation, and LLM providers.
Helps build AI-powered apps with the Vercel AI SDK: core generation APIs, UI hooks for chat/streaming, tool calling, and structured data generation in Next.js and React.
Provides Vercel AI SDK v5 React hooks (useChat, useCompletion, useObject) for streaming AI chat UIs in Next.js apps. Fixes parse stream errors, no responses, and streaming issues.
Share bugs, ideas, or general feedback.
Production-ready backend AI with Vercel AI SDK v5.
Last Updated: 2025-11-21
bun add ai @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google workers-ai-provider zod # preferred
# or: npm install ai @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google workers-ai-provider zod
# .env
OPENAI_API_KEY=sk-...
ANTHROPIC_API_KEY=sk-ant-...
GOOGLE_GENERATIVE_AI_API_KEY=...
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);
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);
}
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"] }
Load references/core-functions.md for complete API reference of all 4 core functions.
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 |
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
Load references/provider-setup.md for complete setup instructions for all providers.
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_GENERATIVE_AI_API_KEY | Gemini 2.5 Pro/Flash | |
| Cloudflare | Workers AI binding | Llama 3.1, Qwen 2.5 |
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
Load references/tools-and-agents.md for complete tool and agent documentation.
Tools allow models to call external functions. Agents manage multi-step workflows.
v5 Tool Changes:
parameters → inputSchema (Zod schema)args → input, result → outputmaxSteps → stopWhen(stepCountIs(n))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
Load references/v4-to-v5-migration.md for complete migration guide.
AI SDK v5 has 9 major breaking changes:
maxTokens → maxOutputTokensparameters → inputSchema (Zod)maxSteps → stopWhen(stepCountIs(n))CoreMessage → ModelMessageai/rsc → @ai-sdk/rsc)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
Cause: API request failed (network, auth, rate limit).
Solution:
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:
Cause: Model didn't generate valid object matching schema.
Solution:
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:
Cause: AI SDK v5 + Zod initialization overhead in Cloudflare Workers exceeds startup limits.
Solution:
// 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:
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
Load references/production-guide.md for complete production deployment guide.
// 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
Load references/core-functions.md when:
Load references/provider-setup.md when:
Load references/tools-and-agents.md when:
Load references/v4-to-v5-migration.md when:
Load references/error-catalog.md when:
Load references/production-guide.md when:
{
"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:
.default() behavior, ZodError.errors removedzod-to-json-schema when using Zod 4Check Latest Versions:
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
This skill includes:
templates/references/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+