> 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/concepts/profiles.md).

# Profiles

Profiles combine a connection with model settings to create reusable AI configurations.

A profile is a named configuration that combines a connection with specific model settings. Profiles let you create reusable AI configurations for different use cases.

## What Profiles Store

| Property       | Description                                                            |
| -------------- | ---------------------------------------------------------------------- |
| `Id`           | Unique identifier (GUID)                                               |
| `Alias`        | Unique string for programmatic lookup                                  |
| `Name`         | Display name shown in the backoffice                                   |
| `Capability`   | The type of AI capability (Chat, Embedding, Speech-to-Text, and so on) |
| `ConnectionId` | Which connection provides credentials                                  |
| `Model`        | The specific AI model to use                                           |
| `Settings`     | Capability-specific settings                                           |
| `Tags`         | Optional tags for organization                                         |

## Profile Settings by Capability

### Chat Profiles

| Setting                | Description                          | Type   |
| ---------------------- | ------------------------------------ | ------ |
| `Temperature`          | Controls randomness (0-2)            | float  |
| `MaxTokens`            | Maximum response length              | int    |
| `SystemPromptTemplate` | Instructions sent with every request | string |

### Embedding Profiles

| Setting      | Description                                                               | Type |
| ------------ | ------------------------------------------------------------------------- | ---- |
| `Dimensions` | Number of dimensions for the generated embeddings (model default if null) | int  |

### Speech-to-Text Profiles

| Setting    | Description                                               | Type   |
| ---------- | --------------------------------------------------------- | ------ |
| `Language` | BCP-47 language hint for transcription (e.g., "en", "de") | string |

## Example Profile Configurations

| Profile          | Use Case        | Model                  | Temperature | System Prompt                         |
| ---------------- | --------------- | ---------------------- | ----------- | ------------------------------------- |
| `content-writer` | Blog posts      | gpt-4o                 | 0.8         | "You are a helpful content writer..." |
| `code-assistant` | Code help       | gpt-4o                 | 0.2         | "You are a code assistant..."         |
| `translator`     | Translation     | gpt-4o-mini            | 0.3         | "Translate to {language}..."          |
| `embeddings`     | Search indexing | text-embedding-3-small | -           | -                                     |

## Using Profiles in Code

### Default Profile

Configure a default profile through the backoffice. See [Managing Settings](/ai-in-umbraco/backoffice/managing-settings.md) for details.

Then use the service without specifying a profile:

{% code title="Example.cs" %}

```csharp
// Uses the default profile configured in Settings
var response = await _chatService.GetChatResponseAsync(
    chat => chat.WithAlias("content-chat"),
    messages);
```

{% endcode %}

### Named Profile

Pass the profile alias (or ID) to `WithProfile`:

{% code title="Example.cs" %}

```csharp
var response = await _chatService.GetChatResponseAsync(
    chat => chat.WithAlias("code-assistant").WithProfile("code-assistant"),
    messages);
```

{% endcode %}

### Override Settings

Profile settings are defaults that can be overridden per-request:

{% code title="Example.cs" %}

```csharp
var options = new ChatOptions
{
    Temperature = 0.9f,  // Override profile's temperature
    MaxOutputTokens = 500
};

var response = await _chatService.GetChatResponseAsync(
    chat => chat.WithAlias("content-chat").WithChatOptions(options),
    messages);
```

{% endcode %}

## Profile Resolution

When you make a request, the profile is resolved by ID or alias and its connection, model, and settings are applied as defaults. Any request-specific options override these defaults, and then middleware is applied before the request is sent.

## Managing Profiles

### Via Backoffice

You can create, edit, and delete profiles through the backoffice. See [Managing Profiles](/ai-in-umbraco/backoffice/managing-profiles.md) for step-by-step instructions.

### Via Code

For programmatic profile management, see the [IAIProfileService](/ai-in-umbraco/reference/services/ai-profile-service.md) reference.

## Related

* [Connections](/ai-in-umbraco/concepts/connections.md) - Provide credentials for profiles
* [Capabilities](/ai-in-umbraco/concepts/capabilities.md) - Determine available profile types
* [Using the Chat API](/ai-in-umbraco/using-the-api/chat.md) - Use profiles for chat


---

# 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/concepts/profiles.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.