Web Search Agent

There are two approaches you can take to building a web search agent with the AI SDK:

1. Use a model that has native web-searching capabilities
2. Use a tool to access the web and return search results.

Both approaches have their advantages and disadvantages. Models with native search capabilities tend to be faster and there is no additional cost to make the search. The disadvantage is that you have less control over what is being searched, and the functionality is limited to models that support it.

instead, by using a tool, you can achieve more flexibility and greater control over your search queries. It allows you to customize your search strategy, specify search parameters, and you can use it with any LLM that supports tool calling. This approach will incur additional costs for the search API you use, but gives you complete control over the search experience.

Using native web-search

There are several models that offer native web-searching capabilities (Perplexity, OpenAI, Gemini). Let's look at how you could build a Web Search Agent across providers.

OpenAI Responses API

OpenAI's Responses API has a built-in web search tool that can be used to search the web and return search results. This tool is called web_search and is accessed via the openai provider.

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

const { text, sources } = await generateText({
  model: 'openai/gpt-5-mini',
  prompt: 'What happened in San Francisco last week?',
  tools: {
    web_search: openai.tools.webSearch({}),
  },
});

console.log(text);
console.log(sources);

Perplexity

Perplexity's Sonar models combines real-time web search with natural language processing. Each response is grounded in current web data and includes detailed citations.

import { generateText } from 'ai';

const { text, sources } = await generateText({
  model: 'perplexity/sonar-pro',
  prompt: 'What are the latest developments in quantum computing?',
});

console.log(text);
console.log(sources);

Gemini

With compatible Gemini models, you can enable search grounding to give the model access to the latest information using Google search.

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

const { text, sources, providerMetadata } = await generateText({
  model: 'google/gemini-2.5-flash',
  tools: {
    google_search: google.tools.googleSearch({}),
  },
  prompt:
    'List the top 5 San Francisco news from the past week.' +
    'You must include the date of each article.',
});

console.log(text);
console.log(sources);

// access the grounding metadata.
const metadata = providerMetadata?.google;
const groundingMetadata = metadata?.groundingMetadata;
const safetyRatings = metadata?.safetyRatings;

Using tools

When using tools for web search, you have two options: use ready-made tools that integrate directly with the AI SDK, or build custom tools tailored to your specific needs.

Unlike the native web search examples where searching is built into the model, using web search tools requires multiple steps. The language model will make two generations - the first to call the relevant web search tool (extracting search queries from the context), and the second to process the results and generate a response. This multi-step process is handled automatically when you set stopWhen: stepCountIs(n) to a value greater than 1.

Use ready-made tools

If you prefer a ready-to-use web search tool without building one from scratch, there are several options that integrate directly with the AI SDK.

Exa

First, install the Exa webSearch tool:

pnpm install @exalabs/ai-sdk

Then, you can import and pass it into generateText, streamText, or your agent:

GatewayProviderCustom

Claude Sonnet 5.5

import { generateText, stepCountIs } from 'ai';
import { webSearch } from '@exalabs/ai-sdk';

const { text } = await generateText({
  model: "anthropic/claude-sonnet-5.5",
  prompt: 'Tell me the latest developments in AI',
  tools: {
    webSearch: webSearch(),
  },
  stopWhen: stepCountIs(3),
});

console.log(text);

For more configuration options and customization, see the Exa AI SDK documentation.

Parallel Web

First, install the Parallel Web AI SDK tools:

pnpm install @parallel-web/ai-sdk-tools

Then, you can import and pass the tools into generateText, streamText, or your agent. Parallel Web provides two tools: searchTool for web search and extractTool for extracting web page content:

GatewayProviderCustom

Claude Sonnet 5.5

import { generateText, stepCountIs } from 'ai';
import { searchTool, extractTool } from '@parallel-web/ai-sdk-tools';

const { text } = await generateText({
  model: "anthropic/claude-sonnet-5.5",
  prompt: 'When was Vercel Ship AI?',
  tools: {
    webSearch: searchTool,
    webExtract: extractTool,
  },
  stopWhen: stepCountIs(3),
});

console.log(text);

Perplexity Search

First, install the Perplexity Search tool:

pnpm install @perplexity-ai/ai-sdk

Then, you can import and pass it into generateText, streamText, or your agent. Perplexity Search provides real-time web search with advanced filtering options including domain, language, date range, and recency filters:

GatewayProviderCustom

Claude Sonnet 5.5

import { generateText, stepCountIs } from 'ai';
import { perplexitySearch } from '@perplexity-ai/ai-sdk';

const { text } = await generateText({
  model: "anthropic/claude-sonnet-5.5",
  prompt:
    'What are the latest AI developments? Use search to find current information.',
  tools: {
    search: perplexitySearch(),
  },
  stopWhen: stepCountIs(3),
});

console.log(text);

For more configuration options and customization, see the Perplexity Search API documentation.

Tavily

First, install the tavilySearch tool:

pnpm install @tavily/ai-sdk

Then, you can import and pass it into generateText, streamText, or your agent:

GatewayProviderCustom

Claude Sonnet 5.5

import { generateText, stepCountIs } from 'ai';
import { tavilySearch, tavilyExtract } from '@tavily/ai-sdk';

const { text } = await generateText({
  model: "anthropic/claude-sonnet-5.5",
  prompt: 'When was the latest update to the AI SDK?',
  tools: {
    webSearch: tavilySearch(),
    webExtract: tavilyExtract(),
  },
  stopWhen: stepCountIs(3),
});

console.log(text);

For more customization options over your agent's web-access functionality, visit the Tavily AI SDK Documentation.

Build and use custom tools

For more control over your web search functionality, you can build custom tools using web scraping and crawling APIs. This approach allows you to customize search parameters, handle specific data formats, and integrate with specialized search services.

Exa

Let's look at how you could implement a search tool using Exa:

pnpm install exa-js

GatewayProviderCustom

Claude Sonnet 5.5

import { generateText, tool, stepCountIs } from 'ai';
import { z } from 'zod';
import Exa from 'exa-js';

export const exa = new Exa(process.env.EXA_API_KEY);

export const webSearch = tool({
  description: 'Search the web for up-to-date information',
  inputSchema: z.object({
    query: z.string().min(1).max(100).describe('The search query'),
  }),
  execute: async ({ query }) => {
    const { results } = await exa.searchAndContents(query, {
      livecrawl: 'always',
      numResults: 3,
    });
    return results.map(result => ({
      title: result.title,
      url: result.url,
      content: result.text.slice(0, 1000), // take just the first 1000 characters
      publishedDate: result.publishedDate,
    }));
  },
});

const { text } = await generateText({
  model: "anthropic/claude-sonnet-5.5", // can be any model that supports tools
  prompt: 'What happened in San Francisco last week?',
  tools: {
    webSearch,
  },
  stopWhen: stepCountIs(5),
});

Firecrawl

Firecrawl provides an API for web scraping and crawling. Let's look at how you can build a custom scraping tool using Firecrawl:

pnpm install @mendable/firecrawl-js

GatewayProviderCustom

Claude Sonnet 5.5

import { generateText, tool, stepCountIs } from 'ai';
import { z } from 'zod';
import FirecrawlApp from '@mendable/firecrawl-js';
import 'dotenv/config';

const app = new FirecrawlApp({ apiKey: process.env.FIRECRAWL_API_KEY });

export const webSearch = tool({
  description: 'Search the web for up-to-date information',
  inputSchema: z.object({
    urlToCrawl: z
      .string()
      .url()
      .min(1)
      .max(100)
      .describe('The URL to crawl (including http:// or https://)'),
  }),
  execute: async ({ urlToCrawl }) => {
    const crawlResponse = await app.crawlUrl(urlToCrawl, {
      limit: 1,
      scrapeOptions: {
        formats: ['markdown', 'html'],
      },
    });
    if (!crawlResponse.success) {
      throw new Error(`Failed to crawl: ${crawlResponse.error}`);
    }
    return crawlResponse.data;
  },
});

const main = async () => {
  const { text } = await generateText({
    model: "anthropic/claude-sonnet-5.5", // can be any model that supports tools
    prompt: 'Get the latest blog post from vercel.com/blog',
    tools: {
      webSearch,
    },
    stopWhen: stepCountIs(5),
  });
  console.log(text);
};

main();