# Profiles

Profiles combine a connection with model-specific settings for use cases. They define which AI model to use and how it should behave.

## Base URL

```
/umbraco/ai/management/api/v1/profiles
```

## Endpoints

| Method | Endpoint                                                    | Description                                                          |
| ------ | ----------------------------------------------------------- | -------------------------------------------------------------------- |
| GET    | `/umbraco/ai/management/api/v1/profiles`                    | [List all profiles](/ai-in-umbraco/management-api/profiles/list.md)  |
| GET    | `/umbraco/ai/management/api/v1/profiles/{profileIdOrAlias}` | [Get a profile](/ai-in-umbraco/management-api/profiles/get.md)       |
| POST   | `/umbraco/ai/management/api/v1/profiles`                    | [Create a profile](/ai-in-umbraco/management-api/profiles/create.md) |
| PUT    | `/umbraco/ai/management/api/v1/profiles/{profileIdOrAlias}` | [Update a profile](/ai-in-umbraco/management-api/profiles/update.md) |
| DELETE | `/umbraco/ai/management/api/v1/profiles/{profileIdOrAlias}` | [Delete a profile](/ai-in-umbraco/management-api/profiles/delete.md) |

## Profile Object

{% code title="Profile Response" %}

```json
{
    "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "alias": "content-assistant",
    "name": "Content Assistant",
    "capability": "Chat",
    "model": {
        "providerId": "openai",
        "modelId": "gpt-4o"
    },
    "connectionId": "d290f1ee-6c54-4b01-90e6-d701748f0851",
    "settings": {
        "$type": "chat",
        "temperature": 0.7,
        "maxTokens": 4096,
        "systemPromptTemplate": "You are a helpful content assistant."
    },
    "tags": ["content", "assistant"]
}
```

{% endcode %}

## Profile Properties

| Property       | Type   | Description                                     |
| -------------- | ------ | ----------------------------------------------- |
| `id`           | guid   | Unique identifier                               |
| `alias`        | string | Unique alias for code references                |
| `name`         | string | Display name                                    |
| `capability`   | string | Capability type (`Chat`, `Embedding`)           |
| `model`        | object | Model reference with `providerId` and `modelId` |
| `connectionId` | guid   | ID of the connection to use                     |
| `settings`     | object | Capability-specific settings (polymorphic)      |
| `tags`         | array  | Optional tags for categorization                |

## Settings Types

Settings are polymorphic based on the `$type` discriminator.

### Chat Settings

{% code title="Chat Settings" %}

```json
{
    "$type": "chat",
    "temperature": 0.7,
    "maxTokens": 4096,
    "systemPromptTemplate": "You are a helpful assistant."
}
```

{% endcode %}

| Property               | Type   | Description             |
| ---------------------- | ------ | ----------------------- |
| `temperature`          | float  | Randomness (0.0-1.0)    |
| `maxTokens`            | int    | Maximum response tokens |
| `systemPromptTemplate` | string | Default system prompt   |

### Embedding Settings

{% code title="Embedding Settings" %}

```json
{
    "$type": "embedding"
}
```

{% endcode %}

Embedding profiles currently have no additional settings.

## ID or Alias

Most endpoints accept either a GUID or alias to identify profiles:

```bash
# By ID
GET /umbraco/ai/management/api/v1/profiles/3fa85f64-5717-4562-b3fc-2c963f66afa6

# By alias
GET /umbraco/ai/management/api/v1/profiles/content-assistant
```

This flexibility allows referencing profiles by memorable aliases in configuration while using GUIDs internally.

## In This Section

{% content-ref url="/pages/qB9lWQOfLtuYRdh27nw7" %}
[List Profiles](/ai-in-umbraco/management-api/profiles/list.md)
{% endcontent-ref %}

{% content-ref url="/pages/NcoMt3Ks3EMitH14rBIr" %}
[Get Profile](/ai-in-umbraco/management-api/profiles/get.md)
{% endcontent-ref %}

{% content-ref url="/pages/YAmyog09VPBoPdCu22gA" %}
[Create Profile](/ai-in-umbraco/management-api/profiles/create.md)
{% endcontent-ref %}

{% content-ref url="/pages/0Qz9iHFMc1tAK53aRZwo" %}
[Update Profile](/ai-in-umbraco/management-api/profiles/update.md)
{% endcontent-ref %}

{% content-ref url="/pages/mPtOXHKOyxRKvToxjjDz" %}
[Delete Profile](/ai-in-umbraco/management-api/profiles/delete.md)
{% endcontent-ref %}


---

# Agent Instructions: 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.umbraco.com/ai-in-umbraco/management-api/profiles.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.