> ## Documentation Index
> Fetch the complete documentation index at: https://latitude-monitoring-docs-docs-sync-2026-08-14.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LangChain

> Connect your LangChain-powered application to Latitude for observability.

## Overview

This guide shows you how to integrate **Latitude Telemetry** into an application that uses **LangChain**.

<Check>
  You'll keep calling LangChain exactly as you do today. Telemetry simply
  observes and enriches those calls.
</Check>

***

## Requirements

* A **Latitude account** and **API key**
* A **Latitude project slug**
* A project that uses **LangChain**

***

## Steps

<Steps>
  <Step title="Install">
    <Tabs>
      <Tab title="TypeScript">
        <CodeGroup>
          ```bash npm theme={null}
          npm install @latitude-data/telemetry @langchain/openai @langchain/core
          ```

          ```bash pnpm theme={null}
          pnpm add @latitude-data/telemetry @langchain/openai @langchain/core
          ```

          ```bash yarn theme={null}
          yarn add @latitude-data/telemetry @langchain/openai @langchain/core
          ```

          ```bash bun theme={null}
          bun add @latitude-data/telemetry @langchain/openai @langchain/core
          ```
        </CodeGroup>
      </Tab>

      <Tab title="Python">
        <CodeGroup>
          ```bash pip theme={null}
          pip install latitude-telemetry
          ```

          ```bash uv theme={null}
          uv add latitude-telemetry
          ```

          ```bash poetry theme={null}
          poetry add latitude-telemetry
          ```
        </CodeGroup>
      </Tab>
    </Tabs>
  </Step>

  <Step title="Initialize and use">
    <Tabs>
      <Tab title="TypeScript">
        ```ts theme={null}
        import { createLangChainInstrumentation } from "@latitude-data/telemetry/instrumentations/langchain"
        import { Latitude, capture } from "@latitude-data/telemetry"
        import * as CallbackManagerModule from "@langchain/core/callbacks/manager"
        import { HumanMessage } from "@langchain/core/messages"
        import { ChatOpenAI } from "@langchain/openai"

        const latitude = new Latitude({
          apiKey: process.env.LATITUDE_API_KEY!,
          project: process.env.LATITUDE_PROJECT_SLUG!,
          instrumentations: [createLangChainInstrumentation(CallbackManagerModule)],
        })

        await latitude.ready
        const llm = new ChatOpenAI({ modelName: "gpt-4o" })

        await capture("langchain-query", async () => {
          const response = await llm.invoke([new HumanMessage("Hello")])
          return response.content
        })

        await latitude.shutdown()
        ```
      </Tab>

      <Tab title="Python">
        ```python theme={null}
        from latitude_telemetry import Latitude, capture
        import langchain_core
        from langchain_openai import ChatOpenAI
        from langchain_core.messages import HumanMessage

        latitude = Latitude(
            api_key="your-api-key",
            project="your-project-slug",
            instrumentations={"langchain": langchain_core},
        )

        llm = ChatOpenAI(model="gpt-4o")

        def langchain_query():
            response = llm.invoke([HumanMessage(content="Hello")])
            return response.content

        capture("langchain-query", langchain_query)

        latitude.shutdown()
        ```
      </Tab>
    </Tabs>
  </Step>
</Steps>

***

## Seeing Your Traces

Once connected, traces appear automatically in Latitude:

1. Open your **project** in the Latitude dashboard
2. Each execution shows input/output messages, model, token usage, latency, and errors
3. LangChain chain steps appear as child spans