Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.langchain.com/llms.txt

Use this file to discover all available pages before exploring further.

Tavily is a search engine built specifically for AI agents (LLMs), delivering real-time, accurate, and factual results at speed. Tavily offers an Extract endpoint that can be used to extract the cleaned, parsed content of one or more URLs.

​
Overview

​
Integration details

ClassPackagePY supportVersion
TavilyExtract@langchain/tavily✅NPM - Version

​
Tool features

Returns artifactNative asyncReturn dataPricing
❌✅raw content and images1,000 free credits / month

​
Setup

The integration lives in the @langchain/tavily package, which you can install as shown below: 
npm install @langchain/tavily @langchain/core

​
Credentials

Set up a Tavily API key and set it as an environment variable named TAVILY_API_KEY. 
process.env.TAVILY_API_KEY = "YOUR_API_KEY"
It’s also helpful (but not needed) to set up LangSmith for best-in-class observability: 
process.env.LANGSMITH_TRACING="true"
process.env.LANGSMITH_API_KEY="your-api-key"

​
Instantiation

The tool accepts the following parameters during instantiation:
  • extractDepth (optional, string): Depth of the extraction, either "basic" or "advanced". Default is "basic".
  • includeImages (optional, boolean): Whether to include images in the extraction. Default is false.
  • format (optional, string): Content format. "markdown" or "text". Default is "markdown".
  • includeFavicon (optional, boolean): Include each result’s favicon URL. Default is false.
For a comprehensive overview of the available parameters, refer to the Tavily Extract API documentation. 
import { TavilyExtract } from "@langchain/tavily";

const tool = new TavilyExtract({
  extractDepth: "basic",
  includeImages: false,
});

​
Invocation

​
Invoke directly with args

The Tavily extract tool accepts the following arguments during invocation:
  • urls (required): A list of URLs to extract content from.
  • The following arguments can also be set during invocation: extractDepth, includeImages.
NOTE: The optional arguments are available for agents to dynamically set. If you set an argument during instantiation and then invoke the tool with a different value, the tool will use the value you passed during invocation. 
await tool.invoke({ urls: ["https://en.wikipedia.org/wiki/Lionel_Messi"] });

{
  results: [{
    url: 'https://en.wikipedia.org/wiki/Lionel_Messi',
    raw_content: 'Lionel Messi - Wikipedia\nJump to content\nMain menu\n... (truncated)',
    images: []
  }],
  failed_results: [],
  response_time: 0.02
}

​
Invoke with ToolCall

We can also invoke the tool with a model-generated ToolCall, in which case a ToolMessage will be returned: 
// This is usually generated by a model, but we'll create a tool call directly for demo purposes.
const modelGeneratedToolCall = {
  args: { urls: ["https://en.wikipedia.org/wiki/Lionel_Messi"] },
  id: "1",
  name: tool.name,
  type: "tool_call",
};

const toolMsg = await tool.invoke(modelGeneratedToolCall);

// The content is a JSON string of results
console.log(toolMsg.content.slice(0, 400));

{"results": [{"url": "https://en.wikipedia.org/wiki/Lionel_Messi", "raw_content": "Lionel Messi - Wikipedia\nJump to content\nMain menu\nMain menu\nmove to sidebar hide\nNavigation\n\nMain page\nContents\nCurrent events\nRandom article\nAbout Wikipedia\nContact us\n\nContribute\n\nHelp\nLearn to edit\nCommunity portal\nRecent changes\nUpload file\nSpecial pages\n... (truncated)"}], "failed_results": [], "response_time": 0.02}

​
Use within an agent

We can use the extract tool directly with a LangChain agent by passing it to createAgent. The agent can dynamically set the list of URLs and toggles like extractDepth and includeImages as part of its tool call. 
// @lc-docs-hide-cell
import { ChatOpenAI } from "@langchain/openai";

const llm = new ChatOpenAI({
  model: "gpt-5.4",
  temperature: 0,
});

import { TavilyExtract } from "@langchain/tavily";
import { createAgent } from "langchain";

const tavilyExtractTool = new TavilyExtract();

const agent = createAgent({
  model: llm,
  tools: [tavilyExtractTool],
});

const userInput = "Summarize https://en.wikipedia.org/wiki/Albert_Einstein and https://en.wikipedia.org/wiki/Theoretical_physics.";

const events = await agent.stream(
  { messages: [["human", userInput]] },
  { streamMode: "values" },
);

for await (const event of events) {
  const lastMsg = event.messages[event.messages.length - 1];
  if (lastMsg.tool_calls?.length) {
    console.dir(lastMsg.tool_calls, { depth: null });
  } else if (lastMsg.content) {
    console.log(lastMsg.content);
  }
}

​
API reference

For detailed documentation of all Tavily Extract API features and configurations head to the API reference: docs.tavily.com/documentation/api-reference/endpoint/extract
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.
Edit this page on GitHub or file an issue.