TavilyMap

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 Map, which traverses websites like a graph and can explore hundreds of paths in parallel with intelligent discovery to generate comprehensive site maps.

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

Class	Package	PY support	Version
TavilyMap	@langchain/tavily	✅

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 TavilyMap tool like this:

import { TavilyMap } from "@langchain/tavily";

const tool = new TavilyMap({
  maxDepth: 3,
  maxBreadth: 50,
  // limit: 100,
  // allowExternal: false,
});

Invocation

Invoke directly with args

The Tavily map tool accepts the following arguments during invocation:

• url (required): A natural language search query

• The following arguments can also be set during invocation : instructions, selectPaths , selectDomains, excludePaths, excludeDomains, allowExternal, categories.

await tool.invoke({
  url: "https://docs.tavily.com"
});

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: {
    url: "https://docs.tavily.com"
  },
  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://docs.tavily.com");

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 Map API features and configurations head to the API reference:

docs.tavily.com/documentation/api-reference/endpoint/map

Related

• Tool docs