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

# Installation

> Install the Python SDK and required runtime tools.

The Python SDK relies on the RamaLama CLI and a container manager to provision and run models locally.

## Installation

<Steps>
  <Step title="Prerequisites">
    In order for you or your users to run use the SDK they will need to:

    * Install a container manager like `docker` or `Podman`.
    * Make sure the container manager is running
  </Step>

  <Step title="Install the SDK from PyPI">
    ```bash theme={"system"}
    pip install ramalama-sdk
    ```

    After installing the SDK the ramalama CLI will be installed by default.
    Additional platform specific installation instructions are available [here](/cli/getting-started/installation).
  </Step>

  <Step title="Get chatting">
    Head to the [quick start](/sdk/python/quickstart) to run your first prompt.
  </Step>
</Steps>

## Verify installation

```python theme={"system"}
import ramalama_sdk

print(f"SDK Version: {ramalama_sdk.__version__}")
```

## Troubleshooting

* If the SDK cannot start a model, verify Docker or Podman is running.