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

# Python SDK v7

> Use the Arize Python SDK v7 to create datasets, run experiments, get traces, log evaluations, and monitor ML models.

Use the Arize Python package to create datasets, run experiments, get traces, and log evaluations to Arize AX. You can also use our ML features to log predictions and actuals. See our API reference below.

<CardGroup cols={1}>
  <Card title="Python SDK API Reference Documentation" href="https://arize-client-python.readthedocs.io/en/latest/" />
</CardGroup>

# Installing the package

```bash theme={null}
pip install arize
```

<CardGroup cols={1}>
  <Card title="Changelog" href="https://github.com/Arize-ai/client_python/blob/main/CHANGELOG.md" />
</CardGroup>

# Available packages

The main package is `arize`, and you can add additional functionality by adding extra dependencies. Python 3.8 is the minimum required for the additional packages.

<table>
  <thead>
    <tr>
      <th width="236">
        Package
      </th>

      <th>
        What It's For
      </th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        <code>
          arize
        </code>
      </td>

      <td>
        The primary Arize package for interfacing with Arize AX APIs.
      </td>
    </tr>

    <tr>
      <td>
        <code>
          arize\[Tracing]
        </code>
      </td>

      <td>
        Components for logging traces and running experiments for LLM applications.
      </td>
    </tr>

    <tr>
      <td>
        <a href="/ax/machine-learning/machine-learning/api-reference-ml/python-sdk/arize-pandas/autoembeddings">
          <code>
            arize\[AutoEmbeddings]
          </code>
        </a>
      </td>

      <td>
        Automatically generate embeddings vectors for your predictions and actuals for ML models.
      </td>
    </tr>

    <tr>
      <td>
        <a href="/ax/machine-learning/machine-learning/api-reference-ml/python-sdk/arize-pandas/llm-evaluation">
          <code>
            arize\[NLP\_Metrics]
          </code>
        </a>
      </td>

      <td>
        Calculate evaluation metrics for your NLP Generative tasks.
      </td>
    </tr>

    <tr>
      <td>
        <a href="/ax/machine-learning/machine-learning/how-to-ml/explainability">
          <code>
            arize\[MimicExplainer]
          </code>
        </a>
      </td>

      <td>
        Produce SHAP values using the surrogate explainability approach.
      </td>
    </tr>
  </tbody>
</table>