> For the complete documentation index, see [llms.txt](https://docs.wisej.com/ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.wisej.com/ai/components/api/smartendpoint/wisej.ai.endpoints.nvidiaaiendpoint.md).

# NvidiaAIEndpoint

Namespace: **Wisej.AI.Endpoints**

Assembly: **Wisej.AI** (3.5.0.0)

* [SmartEndpoint](/ai/components/api/smartendpoint.md)
  * [SmartHttpEndpoint](/ai/components/api/smartendpoint/wisej.ai.endpoints.smarthttpendpoint.md)
    * [OpenAIEndpoint](/ai/components/api/smartendpoint/wisej.ai.endpoints.openaiendpoint.md)
      * [NvidiaAIEndpoint](/ai/components/api/smartendpoint/wisej.ai.endpoints.nvidiaaiendpoint.md)

Represents a connection to NVIDIA AI endpoints, providing access to various AI models and services.

{% tabs %}
{% tab title="C#" %}

```csharp
public class NvidiaAIEndpoint : OpenAIEndpoint
```

{% endtab %}

{% tab title="VB.NET" %}

```visual-basic
Public Class NvidiaAIEndpoint
    Inherits OpenAIEndpoint
```

{% endtab %}
{% endtabs %}

This class extends the [OpenAIEndpoint](/ai/components/api/smartendpoint/wisej.ai.endpoints.openaiendpoint.md) to specifically connect to NVIDIA's AI services. It sets default values for the authentication method, model, embedding model, and URL.

## Constructors

### ![](/files/ptrKjmmRoQB76pvrIqh0) NvidiaAIEndpoint()

Initializes a new instance of the [NvidiaAIEndpoint](/ai/components/api/smartendpoint/wisej.ai.endpoints.nvidiaaiendpoint.md) class with default settings.

The default authentication method is set to "Bearer", the model to "meta/llama-3.1-405b-instruct", the embedding model to "nvidia/embed-qa-4", and the URL to "<https://integrate.api.nvidia.com/v1>".

## Properties

### ![](/files/ptrKjmmRoQB76pvrIqh0) EmbeddingModel

[String](https://docs.microsoft.com/dotnet/api/system.string): Gets or sets the embedding model used for AI processing. (Default: `"nvidia/embed-qa-4"`)

### ![](/files/ptrKjmmRoQB76pvrIqh0) Model

[String](https://docs.microsoft.com/dotnet/api/system.string): Gets or sets the model used for AI processing. (Default: `"meta/llama-3.1-405b-instruct"`)

### ![](/files/ptrKjmmRoQB76pvrIqh0) URL

[String](https://docs.microsoft.com/dotnet/api/system.string): Gets or sets the URL for the NVIDIA AI endpoint. (Default: `"https://integrate.api.nvidia.com/v1"`)

### ![](/files/ptrKjmmRoQB76pvrIqh0) UseNativeTools

[Boolean](https://docs.microsoft.com/dotnet/api/system.boolean): (Default: `True`)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.wisej.com/ai/components/api/smartendpoint/wisej.ai.endpoints.nvidiaaiendpoint.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.