> ## 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

> Arize AI for Model Monitoring, Troubleshooting, and Explainability

<Check>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/ca391741-arize.svg" className="inline m-0" />

  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/df6b4a82-arize.svg" className="inline m-0" />

  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/307e7d1f-arize.svg" className="inline m-0" />
</Check>

Use the Arize Python package to monitor machine learning predictions to observe your ML models and their features, predicted labels, and actual labels with just a few lines of code.

## Installing the package

```bash theme={null}
%pip install -q "arize<8.0.0"
```

In addition to the basic functionality installed by the command above, the Arize SDK has additional functionality that can be installed with some extra dependencies:

#### LLM Tracing

<Warning>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/7539e0ab-python-3_8-red.svg" className="inline m-0" /> minimum required for LLM Tracing
</Warning>

With this extra module, Arize can receive your traces and spans to break down your system's components into discrete inputs and outputs to help debug your LLM application. Learn more [here](/ax/observe/tracing).

```bash theme={null}
pip install arize[Tracing]
```

#### Auto Embeddings

<Warning>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/7539e0ab-python-3_8-red.svg" className="inline m-0" /> minimum required for Auto Embeddings
</Warning>

With this extra module, Arize properly extracts the embeddings depending on your use case, and we return it to you to include in your Pandas DataFrame. Learn more [here](https://arize.com/docs/ax/machine-learning/machine-learning/api-reference-ml/python-sdk/arize.pandas/autoembeddings). To install the Arize package including this functionality:

```bash theme={null}
%pip install -q "arize[AutoEmbeddings]<8.0.0"
```

#### NLP Metrics

<Warning>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/7539e0ab-python-3_8-red.svg" className="inline m-0" /> minimum required for NLP Metrics
</Warning>

With this extra module, Arize helps you calculate evaluation metrics for your NLP Generative tasks. Learn more [here](/ax/machine-learning/machine-learning/api-reference-ml/python-sdk/arize-pandas/llm-evaluation). To install the Arize package including this functionality:

```bash theme={null}
%pip install -q "arize[NLP_Metrics]<8.0.0"
```

#### Mimic Explainer

<Warning>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/7539e0ab-python-3_8-red.svg" className="inline m-0" /> minimum required for Mimic Explainer
</Warning>

With this extra module, Arize allows the user to pass a flag with their request to send data that would produce SHAP values using the surrogate explainability approach. Learn more [here](/ax/machine-learning/machine-learning/how-to-ml/explainability/surrogate-model). To install the Arize package including this functionality:

```bash theme={null}
%pip install -q "arize[MimicExplainer]<8.0.0"
```

## Logging Options

The Arize Python SDK offers 2 ways of logging data into the platform:

#### Pandas Batch Logging

Designed for logging a batch of your model inferences using Pandas DataFrames. Go to the following page for more information.

<Card title="Pandas batch logging" href="/ax/machine-learning/machine-learning/api-reference-ml/python-sdk/arize-pandas" />

#### Single Record Logging

Designed for low latency, one-at-a-time, logging of your model inferences. Go to the following page for more information.

<Card title="Single Record Logging" href="/ax/machine-learning/machine-learning/api-reference-ml/python-sdk/arize-log" />

## End of Support Table

| Major Release | First Released  | Latest                                    | Support                 |
| ------------- | --------------- | ----------------------------------------- | ----------------------- |
| 7.x           | June, 2023      | [latest](https://pypi.org/project/arize/) | Ends June 1st, 2026     |
| 6.x           | January, 2023   | 6.1.3                                     | Ends June 1st, 2025     |
| 5.x           | August, 2022    | 5.5.0                                     | Ends November 1st, 2024 |
| 4.x           | March, 2022     | 4.2.2                                     | Ended June 1st, 2024    |
| 3.x           | September, 2021 | 3.4.0                                     | Ended April 1st, 2024   |
| 2.x           | March, 2021     | 2.2.1                                     | Ended July 1st, 2023    |
| 1.x           | July, 2020      | 1.2.1                                     | Ended March 1st, 2022   |
| 0.x           | March, 2020     | 0.0.20                                    | Ended March 1st, 2022   |

## Changelog