> ## 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.

# Aleph Alpha

> Connect your Aleph Alpha-powered application to Latitude for observability.

## Overview

This guide shows you how to integrate **Latitude Telemetry** into an application that uses the **Aleph Alpha** SDK (`aleph-alpha-client`).

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

<Note>
  Auto-instrumentation for Aleph Alpha 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 the **Aleph Alpha SDK** (`aleph-alpha-client`)
* An **Aleph Alpha API token** (set as `ALEPH_ALPHA_API_KEY`)

***

## Steps

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

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

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

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

    import aleph_alpha_client
    from aleph_alpha_client import Client, CompletionRequest, Prompt

    from latitude_telemetry import Latitude, capture

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

    def generate_reply():
        client = Client(token=os.environ["ALEPH_ALPHA_API_KEY"])
        request = CompletionRequest(prompt=Prompt.from_text("Hello:"), maximum_tokens=50)
        response = client.complete(request, model="luminous-base")
        return response.completions[0].completion

    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