安装
npm install firecrawl-aisdk ai
FIRECRAWL_API_KEY=fc-your-key # https://firecrawl.dev
AI_GATEWAY_API_KEY=your-key # https://vercel.com/ai-gateway
这些示例使用 Vercel AI Gateway 的 string 模型格式，但 Firecrawl 工具可以搭配任何 AI SDK 提供方使用。你也可以使用来自
@ai-sdk/anthropic 的提供方导入，例如 anthropic('claude-sonnet-4-5-20250514')。快速开始
FirecrawlTools() 默认集成了搜索、抓取和交互工具。
import { generateText, stepCountIs } from 'ai';
import { FirecrawlTools } from 'firecrawl-aisdk';
const { text } = await generateText({
model: 'anthropic/claude-sonnet-4-5',
tools: FirecrawlTools(),
stopWhen: stepCountIs(30),
prompt: `
1. Use interact on Hacker News to identify the top story
2. Search for other perspectives on the same topic
3. Scrape the most relevant pages you found
4. Summarize everything you found
`,
});
FirecrawlTools
FirecrawlTools() 会为你提供默认工具，以及一个可传给 generateText 的自动生成 systemPrompt。
import { generateText, stepCountIs } from 'ai';
import { FirecrawlTools } from 'firecrawl-aisdk';
const tools = FirecrawlTools();
const { text } = await generateText({
model: 'anthropic/claude-sonnet-4-5',
system: `${tools.systemPrompt}\n\nAnswer with citations when possible.`,
tools,
stopWhen: stepCountIs(20),
prompt: 'Find the current Firecrawl pricing page and explain the available plans.',
});
const tools = FirecrawlTools({
search: { limit: 5 },
scrape: { formats: ['markdown'], onlyMainContent: true },
interact: { profile: { name: 'my-session', saveChanges: true } },
crawl: true,
agent: true,
});
// 禁用 interact，保留 search + scrape
FirecrawlTools({ interact: false });
// 启用已废弃的浏览器兼容性
FirecrawlTools({ browser: {} });
// 包含所有可用工具
FirecrawlTools({ all: true });
formats: [{ type: 'query', prompt: 'What does this page say about pricing and rate limits?' }]
formats: ['markdown']。
单个工具
import { generateText } from 'ai';
import { scrape, search } from 'firecrawl-aisdk';
const { text } = await generateText({
model: 'anthropic/claude-sonnet-4-5',
prompt: '搜索 Firecrawl，然后抓取最相关的结果。',
tools: { search, scrape },
});
const customScrape = scrape({ apiKey: 'fc-custom-key', apiUrl: 'https://api.firecrawl.dev' });
搜索 + 抓取
import { generateText } from 'ai';
import { search, scrape } from 'firecrawl-aisdk';
const { text } = await generateText({
model: 'anthropic/claude-sonnet-4-5',
prompt: '搜索 Firecrawl,抓取首个官方结果,并说明其功能。',
tools: { search, scrape },
});
映射
import { generateText } from 'ai';
import { map } from 'firecrawl-aisdk';
const { text } = await generateText({
model: 'anthropic/claude-sonnet-4-5',
prompt: 'Map https://docs.firecrawl.dev and list the main sections.',
tools: { map },
});
流式
import { streamText, stepCountIs } from 'ai';
import { scrape } from 'firecrawl-aisdk';
const result = streamText({
model: 'anthropic/claude-sonnet-4-5',
prompt: 'What is the first 100 words of firecrawl.dev?',
tools: { scrape },
stopWhen: stepCountIs(3),
});
for await (const chunk of result.textStream) {
process.stdout.write(chunk);
}
await result.fullStream;
交互
interact() 会创建一个由抓取驱动的交互式会话。调用 start(url) 以初始化会话并获取 live view URL，然后让模型通过 interact 工具复用该会话。
import { generateText, stepCountIs } from 'ai';
import { interact, search } from 'firecrawl-aisdk';
const interactTool = interact();
console.log('Live view:', await interactTool.start('https://news.ycombinator.com'));
const { text } = await generateText({
model: 'anthropic/claude-sonnet-4-5',
tools: { interact: interactTool, search },
stopWhen: stepCountIs(25),
prompt: 'Use interact on the current Hacker News session, find the top story, then search for more context.',
});
await interactTool.close();
interactTool.interactiveLiveViewUrl。
使用配置文件在不同会话间复用浏览器状态：
const interactTool = interact({
profile: { name: 'my-session', saveChanges: true },
});
browser() 已弃用。建议改用 interact()。
异步工具
poll。
爬取
import { generateText } from 'ai';
import { crawl, poll } from 'firecrawl-aisdk';
const { text } = await generateText({
model: 'anthropic/claude-sonnet-4-5',
prompt: 'Crawl https://docs.firecrawl.dev (limit 3 pages) and summarize.',
tools: { crawl, poll },
});
批量抓取
import { generateText } from 'ai';
import { batchScrape, poll } from 'firecrawl-aisdk';
const { text } = await generateText({
model: 'anthropic/claude-sonnet-4-5',
prompt: 'Scrape https://firecrawl.dev and https://docs.firecrawl.dev, then compare them.',
tools: { batchScrape, poll },
});
代理
import { generateText, stepCountIs } from 'ai';
import { agent, poll } from 'firecrawl-aisdk';
const { text } = await generateText({
model: 'anthropic/claude-sonnet-4-5',
prompt: 'Find the founders of Firecrawl, their roles, and their backgrounds.',
tools: { agent, poll },
stopWhen: stepCountIs(10),
});
日志
import { generateText } from 'ai';
import { logStep, scrape, stepLogger } from 'firecrawl-aisdk';
const logger = stepLogger();
const { text, usage } = await generateText({
model: 'anthropic/claude-sonnet-4-5',
prompt: 'Scrape https://firecrawl.dev and summarize it.',
tools: { scrape },
onStepFinish: logger.onStep,
experimental_onToolCallFinish: logger.onToolCallFinish,
});
logger.close();
logger.summary(usage);
await generateText({
model: 'anthropic/claude-sonnet-4-5',
prompt: 'Scrape https://firecrawl.dev and summarize it again.',
tools: { scrape },
onStepFinish: logStep,
});
所有导出项
import {
// 核心工具
search, // 进行网页搜索
scrape, // 抓取单个 URL
map, // 发现站点上的 URL
crawl, // 爬取多个页面（异步，使用 poll）
batchScrape, // 批量抓取多个 URL（异步，使用 poll）
agent, // 自主网页调研（异步，使用 poll）
// 任务管理
poll, // 轮询异步任务以获取结果
status, // 查看任务状态
cancel, // 取消正在运行的任务
// 浏览器/会话工具
interact, // interact({ profile: { name: '...' } })
browser, // 已废弃的兼容性导出
// 一体化包
FirecrawlTools, // FirecrawlTools({ search, scrape, interact, crawl, agent })
// 辅助工具
stepLogger, // 每次工具调用的 Token 统计
logStep, // 简单的单行日志记录
} from 'firecrawl-aisdk';