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

# ADK

The Agent Development Kit (ADK) is a modular, model-agnostic framework developed by Google for building AI agents. It supports workflows, tool usage, multimodal input/output, and evaluation, making it ideal for creating flexible and interactive agents.

This guide walks you through connecting SambaCloud LLMs to ADK so you can start building your own agents quickly.

### Prerequisites

Before you begin, ensure you have:

* A SambaCloud API key. Get one by creating a [SambaCloud](https://cloud.sambanova.ai/apis) account and getting one in the API keys tab.
* Python 3.9 or newer installed on your machine

### Setup

1. To create a virtual environment, open your terminal and run:

   ```
   python -m venv .venv
   source .venv/bin/activate
   ```
2. To install the ADK and LiteLLM libraries, run:

   ```
   pip install google-adk
   pip install litellm
   ```

### Example use case

To see ADK and SambaCloud working together, check out our [multimodal agent example](https://github.com/sambanova/integrations/tree/main/adk).

This example shows how to:

* Understand and process images
* Use external tools during a workflow
* Turn a visual mockup into a simple web page

### Agent Development Kit docs

See the [official ADK documentation](https://google.github.io/adk-docs/agents/) for more details and advanced features.