Tavily is a search engine built specifically for AI agents (LLMs), delivering real-time, accurate, and factual results at speed. Tavily offers four key endpoints, one of which being Extract, which provides raw extracted content from a URL. This guide provides a quick overview for getting started with the Tavily tool. For a complete breakdown of the Tavily tool, you can find more detailed documentation in the API reference.

​
Overview

​
Integration details

ClassPackagePY supportPackage latest
TavilyExtract@langchain/tavily✅NPM - Version

​
Setup

The integration lives in the @langchain/tavily package, which you can install as shown below: 
import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
<IntegrationInstallTooltip></IntegrationInstallTooltip>

<Npm2Yarn>
  @langchain/tavily @langchain/core
</Npm2Yarn>

​
Credentials

Set up an API key here 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

You can import and instantiate an instance of the TavilyExtract tool like this: 
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.
  • Both extractDepth and includeImages can also be set during invocation 
await tool.invoke({
  "urls": ["https://en.wikipedia.org/wiki/Lionel_Messi"]
});

​
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",
}

await tool.invoke(modelGeneratedToolCall)

​
Chaining

We can use our tool in a chain by first binding it to a tool-calling model and then calling it: 
<ChatModelTabs customVarName="llm" />

// @lc-docs-hide-cell

import { ChatOpenAI } from "@langchain/openai"

const llm = new ChatOpenAI({
  model: "gpt-4o",
  temperature: 0,
})

import { HumanMessage } from "@langchain/core/messages";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { RunnableLambda } from "@langchain/core/runnables";

const prompt = ChatPromptTemplate.fromMessages(
  [
    ["system", "You are a helpful assistant."],
    ["placeholder", "{messages}"],
  ]
)

const llmWithTools = llm.bindTools([tool]);

const chain = prompt.pipe(llmWithTools);

const toolChain = RunnableLambda.from(
  async (userInput: string, config) => {
    const humanMessage = new HumanMessage(userInput);
    const aiMsg = await chain.invoke({
      messages: [new HumanMessage(userInput)],
    }, config);
    const toolMsgs = await tool.batch(aiMsg.tool_calls, config);
    return chain.invoke({
      messages: [humanMessage, aiMsg, ...toolMsgs],
    }, config);
  }
);

const toolChainResult = await toolChain.invoke("['https://en.wikipedia.org/wiki/Albert_Einstein','https://en.wikipedia.org/wiki/Theoretical_physics']");

const { tool_calls, content } = toolChainResult;

console.log("AIMessage", JSON.stringify({
  tool_calls,
  content,
}, null, 2));

​
Agents

For guides on how to use LangChain tools in agents, see the LangGraph.js docs.

​
API reference

For detailed documentation of all Tavily Extract API features and configurations head to the API reference: https://docs.tavily.com/documentation/api-reference/endpoint/extract