> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/ai-in-umbraco/19.latest/reference/models/ai-capability.md).

# AICapability

Enumeration of AI capability types.

Enumeration defining the types of AI capabilities available.

## Namespace

```csharp
using Umbraco.AI.Core.Models;
```

## Definition

{% code title="AICapability" %}

```csharp
public enum AICapability
{
    Chat = 0,
    Embedding = 1,
    SpeechToText = 4,
    ImageGeneration = 5,
    Decision = 8,
    Extraction = 9
}
```

{% endcode %}

## Values

| Value             | Int | Description                               | Status       |
| ----------------- | --- | ----------------------------------------- | ------------ |
| `Chat`            | 0   | Conversational AI / chat completions      | Available    |
| `Embedding`       | 1   | Text to vector embeddings                 | Available    |
| `SpeechToText`    | 4   | Audio transcription and voice input       | Available    |
| `ImageGeneration` | 5   | Text-to-image and image editing           | Experimental |
| `Decision`        | 8   | Typed yes/no, pick-one, and score answers | Experimental |
| `Extraction`      | 9   | Typed values read out of text             | Experimental |

## Usage

### Filtering Profiles

{% code title="Example" %}

```csharp
// Get all chat profiles
var chatProfiles = await profileService.GetProfilesAsync(AICapability.Chat);

// Get all embedding profiles
var embeddingProfiles = await profileService.GetProfilesAsync(AICapability.Embedding);
```

{% endcode %}

### Getting Available Capabilities

{% code title="Example" %}

```csharp
// Get capabilities available from configured connections
var available = await connectionService.GetAvailableCapabilitiesAsync();

foreach (var capability in available)
{
    Console.WriteLine($"Available: {capability}");
}
```

{% endcode %}

### Creating Profiles

{% code title="Example" %}

```csharp
// Chat profile
var chatProfile = new AIProfile
{
    Alias = "chat-assistant",
    Name = "Chat Assistant",
    Capability = AICapability.Chat,
    // ...
};

// Embedding profile
var embeddingProfile = new AIProfile
{
    Alias = "document-embeddings",
    Name = "Document Embeddings",
    Capability = AICapability.Embedding,
    // ...
};
```

{% endcode %}

### Checking Provider Support

{% code title="Example" %}

```csharp
// Get connections that support chat
var chatConnections = await connectionService.GetConnectionsByCapabilityAsync(
    AICapability.Chat);

// Get connections that support embeddings
var embeddingConnections = await connectionService.GetConnectionsByCapabilityAsync(
    AICapability.Embedding);
```

{% endcode %}

## Notes

* `Chat`, `Embedding`, and `SpeechToText` are generally available
* `ImageGeneration` is experimental. It is hidden unless the `Umbraco:AI:Experimental:ImageGeneration` flag is enabled. See [Image Generation](/ai-in-umbraco/19.latest/using-the-api/image-generation.md)
* `Decision` is experimental. It is hidden unless the `Umbraco:AI:Experimental:Decision` flag is enabled. See [Decision](/ai-in-umbraco/19.latest/using-the-api/decision.md)
* `Extraction` is experimental. It is hidden unless the `Umbraco:AI:Experimental:Extraction` flag is enabled. See [Extraction](/ai-in-umbraco/19.latest/using-the-api/extraction.md)
* Capability is set on profile creation and cannot be changed


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.umbraco.com/ai-in-umbraco/19.latest/reference/models/ai-capability.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.