> ## Documentation Index
> Fetch the complete documentation index at: https://docs.latitude.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Amazon SageMaker

> Connect your Amazon SageMaker-powered application to Latitude for observability.

## Overview

This guide shows you how to integrate **Latitude Telemetry** into an application that invokes models hosted on **Amazon SageMaker** through `boto3`.

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

<Note>
  Auto-instrumentation for SageMaker is available in the **Python** SDK. For other
  languages, send traces via the [OpenTelemetry exporter](/telemetry/otel-exporter).
</Note>

***

## Requirements

* A **Latitude account** and **API key**
* A **Latitude project slug**
* A project that uses **boto3** with a deployed SageMaker endpoint
* AWS credentials (`AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_REGION`) and a `SAGEMAKER_ENDPOINT_NAME`

***

## Steps

<Steps>
  <Step title="Install">
    <CodeGroup>
      ```bash pip theme={"theme":{"light":"github-light","dark":"github-dark"}}
      pip install latitude-telemetry boto3
      ```

      ```bash uv theme={"theme":{"light":"github-light","dark":"github-dark"}}
      uv add latitude-telemetry boto3
      ```

      ```bash poetry theme={"theme":{"light":"github-light","dark":"github-dark"}}
      poetry add latitude-telemetry boto3
      ```
    </CodeGroup>
  </Step>

  <Step title="Initialize and use">
    ```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
    import json
    import os

    import boto3

    from latitude_telemetry import Latitude, capture

    latitude = Latitude(
        api_key="your-api-key",
        project="your-project-slug",
        instrumentations={"sagemaker": boto3},
    )

    client = boto3.client("sagemaker-runtime", region_name="eu-central-1")

    def generate_reply():
        response = client.invoke_endpoint(
            EndpointName=os.environ["SAGEMAKER_ENDPOINT_NAME"],
            ContentType="application/json",
            Body=json.dumps({"inputs": "Hello", "parameters": {"max_new_tokens": 50}}),
        )
        return json.loads(response["Body"].read().decode())

    capture("generate-reply", generate_reply)

    latitude.shutdown()
    ```
  </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