> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/upstash/context7/llms.txt
> Use this file to discover all available pages before exploring further.

# AI SDK Integration Overview

> Add Context7 documentation lookup to your Vercel AI SDK workflows with tools and agents

## Introduction

`@upstash/context7-tools-ai-sdk` provides [Vercel AI SDK](https://ai-sdk.dev/) compatible tools and agents that give your AI applications access to up-to-date library documentation through Context7.

This package enables you to:

* Add documentation lookup tools to your AI SDK workflows with `generateText` or `streamText`
* Create documentation-aware agents using the pre-configured `Context7Agent`
* Build RAG pipelines that retrieve accurate, version-specific code examples

## Installation

```bash theme={null}
npm install @upstash/context7-tools-ai-sdk @upstash/context7-sdk ai zod
```

## Quick Start

### Using Tools with generateText

```typescript theme={null}
import { resolveLibraryId, queryDocs } from '@upstash/context7-tools-ai-sdk';
import { generateText, stepCountIs } from 'ai';
import { openai } from '@ai-sdk/openai';

const { text } = await generateText({
  model: openai('gpt-4o'),
  prompt: 'How do I use React Server Components?',
  tools: {
    resolveLibraryId: resolveLibraryId(),
    queryDocs: queryDocs(),
  },
  stopWhen: stepCountIs(5),
});

console.log(text);
```

### Using the Context7 Agent

```typescript theme={null}
import { Context7Agent } from '@upstash/context7-tools-ai-sdk';
import { anthropic } from '@ai-sdk/anthropic';

const agent = new Context7Agent({
  model: anthropic('claude-sonnet-4-20250514'),
});

const { text } = await agent.generate({
  prompt: 'How do I set up routing in Next.js?',
});

console.log(text);
```

## Authentication

Set your Context7 API key via environment variable:

```bash theme={null}
export CONTEXT7_API_KEY=ctx7sk-...
```

Alternatively, pass the API key directly to tools or agents:

```typescript theme={null}
const tool = resolveLibraryId({ apiKey: 'ctx7sk-...' });

const agent = new Context7Agent({
  model: anthropic('claude-sonnet-4-20250514'),
  apiKey: 'ctx7sk-...',
});
```

## Package Contents

The package provides:

### Tools

* **`resolveLibraryId`** - Searches Context7's database to find the correct library ID
* **`queryDocs`** - Fetches documentation for a specific library

### Agents

* **`Context7Agent`** - Pre-configured agent that handles multi-step documentation lookup

### Prompts

* **`SYSTEM_PROMPT`** - Basic documentation assistant prompt
* **`AGENT_PROMPT`** - Detailed multi-step workflow prompt
* **`RESOLVE_LIBRARY_ID_DESCRIPTION`** - Tool description for resolveLibraryId
* **`QUERY_DOCS_DESCRIPTION`** - Tool description for queryDocs

## Next Steps

<CardGroup cols={2}>
  <Card title="Tools" icon="wrench" href="/ai-sdk/tools">
    Learn about resolveLibraryId and queryDocs tools
  </Card>

  <Card title="Agent" icon="robot" href="/ai-sdk/agent">
    Use the pre-configured Context7Agent
  </Card>
</CardGroup>