Skip to main content
Deprecation NoticeThis tool has been deprecated. Please use the TavilySearch tool in the @langchain/tavily package, instead.
Tavily Search is a robust search API tailored specifically for LLM Agents. It seamlessly integrates with diverse data sources to ensure a superior, relevant search experience. This guide provides a quick overview for getting started with the TavilySearchResults tool.

​
Overview

​
Integration details

ClassPackagePY supportVersion
TavilySearchResults@langchain/community✅NPM - Version

​
Setup

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

You can import and instantiate an instance of the TavilySearchResults tool like this: 
import { TavilySearchResults } from "@langchain/community/tools/tavily_search";

const tool = new TavilySearchResults({
  maxResults: 2,
  // ...
});

​
Invocation

​
Invoke directly with args

You can invoke the tool directly like this: 
await tool.invoke({
  input: "what is the current weather in SF?",
});

​
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: {
    query: "what is the current weather in SF?"
  },
  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: 
// @lc-docs-hide-cell

import { ChatOpenAI } from "@langchain/openai"

const llm = new ChatOpenAI({
  model: "gpt-4.1",
  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("what is the current weather in sf?");

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.
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.