Skip to main content

​
Setup

npm i llamaindex @llamaindex/openai @nangohq/node
This example uses the Node SDK, a lightweight wrapper over Nango’s REST API. The same flow works in any language by using the API reference.
Requirements:
  • A Nango account with a Hubspot integration configured and the whoami action enabled.
  • An OpenAI account (or another LLM provider).

​
Usage

Example of a basic tool that calls an external API (Hubspot): 
import { ReActAgent, FunctionTool } from "llamaindex";
import { OpenAI } from "@llamaindex/openai";
import { Nango } from "@nangohq/node";

export async function runLlamaIndexAgent() {
    if (!process.env.OPENAI_API_KEY) {
        console.log("Missing environment variable: OPENAI_API_KEY.");
    }

    const nango = new Nango({ secretKey: process.env.NANGO_SECRET_KEY! });

    const userId = "user1", integrationId = "hubspot";

    // Step 1: Ensure the user is authorized
    console.log("🔒 Checking API authorization...");
    let connectionId = (await nango.listConnections({ integrationId, userId })).connections[0]?.connection_id;

    // Step 2: If the user is not authorized, redirect to the auth flow.
    if (!connectionId) {
        const session = await nango.createConnectSession({
            allowed_integrations: [integrationId],
            end_user: { id: userId },
        });

        console.log(`Please authorize the app by visiting this URL: ${session.data.connect_link}`);

        const connection = await nango.waitForConnection(integrationId, userId);
        connectionId = connection!.connection_id;
    }

    // Step 3: Define the tool
    const whoAmITool = FunctionTool.from(
        async () => {
            // Step 4: Execute the requested tool with Nango.
            const result = await nango.triggerAction(integrationId, connectionId, "whoami");
            return JSON.stringify(result);
        },
        {
            name: "who_am_i",
            description: "Get the current user info.",
            parameters: {
                type: "object",
                properties: {},
                required: [],
            },
        }
    );

    const agent = new ReActAgent({
        tools: [whoAmITool],
        llm: new OpenAI({ model: "gpt-4" }),
    });

    console.log("🤖 Agent running...");
    const response = await agent.chat({
        message: "Using the who_am_i tool, provide the current user info.",
    });

    console.log("✅ Agent retrieved your Hubspot user info:", response.response);
}
You can let agents or models introspect available tools and their specifications by calling this endpoint. Your model can then automatically decide which tool to call.