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

# Integrate NVIDIA G-Assist with LLM Controls

<Note>
  **important**

  This component is available only for LLM Controls users with NVIDIA GPUs on Windows systems.
</Note>

The **NVIDIA G-Assist** component enables interaction with NVIDIA GPU drivers through natural language prompts.

For example, prompt G-Assist with `"What is my current GPU temperature?"` or `"Show me the available GPU memory"` to get information, and then tell G-Assist to modify your GPU settings.

## Prerequisites

* Windows operating system
* NVIDIA GPU
* `gassist.rise` package installed. This package is already installed with LLM Controls.

## Use the G-Assist component in a flow

1. Create a flow with a **Chat input** component, a **G-Assist** component, and a **Chat output** component.
2. Connect the **Chat input** component to the **G-Assist** component's **Prompt** input, and then connect the **G-Assist** component's output to the **Chat output** component.
3. Open the **Playground**, and then ask a question about your GPU. For example, "What is my current GPU temperature?". The **G-Assist** component queries your GPU, and the response appears in the **Playground**.

### Inputs

The **NVIDIA G-Assist** component accepts a single input:

* `prompt`: A human-readable prompt processed by NVIDIA G-Assist.

### Outputs

The **NVIDIA G-Assist** component outputs a [Message](https://docs.llmcontrols.ai/Concepts/LLMCobjects#message-object%E2%80%8B) object that contains:

* `text`: The response from NVIDIA G-Assist containing the completed operation result.
* The NVIDIA G-Assist message response is wrapped in an LLM Controls [Message](https://docs.llmcontrols.ai/Concepts/LLMCobjects#message-object%E2%80%8B) object.