> 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/management-api/connections/capabilities.md).

# List Capabilities

List available AI capabilities and find connections that support them.

Get information about available AI capabilities across all connections.

## Endpoints

| Method | Endpoint                                                                       | Description                                         |
| ------ | ------------------------------------------------------------------------------ | --------------------------------------------------- |
| GET    | `/umbraco/ai/management/api/v1/connections/capabilities`                       | List all available capabilities                     |
| GET    | `/umbraco/ai/management/api/v1/connections?capability={capability}`            | Get connections that support a capability           |
| GET    | `/umbraco/ai/management/api/v1/connections/{connectionIdOrAlias}/capabilities` | Get capabilities supported by a specific connection |
| GET    | `/umbraco/ai/management/api/v1/capabilities/enabled`                           | List capabilities enabled on this install           |

## List All Capabilities

### Endpoint

```
GET /umbraco/ai/management/api/v1/connections/capabilities
```

### Response (200 OK)

{% code title="Response" %}

```json
["Chat", "Embedding"]
```

{% endcode %}

The response is a plain JSON array of the capabilities that at least one configured connection supports. Experimental capabilities that are not enabled are left out.

### Example

{% code title="cURL" %}

```bash
curl -X GET "https://your-site.com/umbraco/ai/management/api/v1/connections/capabilities" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN"
```

{% endcode %}

## Get Connections by Capability

### Endpoint

Use the `capability` query parameter on the [List Connections](/ai-in-umbraco/19.latest/management-api/connections/list.md) endpoint.

```
GET /umbraco/ai/management/api/v1/connections?capability={capability}
```

### Query Parameters

| Parameter    | Type   | Description                                                         |
| ------------ | ------ | ------------------------------------------------------------------- |
| `capability` | string | Capability name, such as `Chat` or `Embedding`. Not case-sensitive. |

The `filter`, `providerId`, `skip`, and `take` parameters from [List Connections](/ai-in-umbraco/19.latest/management-api/connections/list.md) still apply.

If the value is not a known capability name, the filter is ignored and all connections are returned. If the capability is experimental and not enabled, the list is empty.

### Response (200 OK)

{% code title="Response" %}

```json
{
    "total": 1,
    "items": [
        {
            "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
            "alias": "openai-prod",
            "name": "OpenAI Production",
            "providerId": "openai",
            "isActive": true,
            "dateCreated": "2024-01-15T10:30:00Z",
            "dateModified": "2024-01-20T14:45:00Z",
            "version": 2
        }
    ]
}
```

{% endcode %}

### Example

{% code title="cURL" %}

```bash
curl -X GET "https://your-site.com/umbraco/ai/management/api/v1/connections?capability=Chat" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN"
```

{% endcode %}

## Get Capabilities for a Connection

### Endpoint

```
GET /umbraco/ai/management/api/v1/connections/{connectionIdOrAlias}/capabilities
```

### Path Parameters

| Parameter             | Type   | Description              |
| --------------------- | ------ | ------------------------ |
| `connectionIdOrAlias` | string | Connection GUID or alias |

### Response (200 OK)

{% code title="Response" %}

```json
["Chat", "Embedding"]
```

{% endcode %}

The response is a plain JSON array of the capabilities that the connection's provider supports. Experimental capabilities that are not enabled are left out. If the connection does not exist, the endpoint returns `404 Not Found`.

### Example

{% code title="cURL" %}

```bash
curl -X GET "https://your-site.com/umbraco/ai/management/api/v1/connections/openai-prod/capabilities" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN"
```

{% endcode %}

## List Enabled Capabilities

Returns the capabilities enabled on this install, whether or not any connection supports them. Use it to check whether an experimental capability is switched on.

### Endpoint

```
GET /umbraco/ai/management/api/v1/capabilities/enabled
```

### Response (200 OK)

{% code title="Response" %}

```json
["Chat", "Embedding", "SpeechToText", "Decision", "Extraction"]
```

{% endcode %}

The response is a plain JSON array of capability names:

* Generally available capabilities are always included.
* An experimental capability, such as `Decision` or `Extraction`, is only included when its feature flag is enabled.
* Reserved values that have no implementation are never included.

The endpoint requires access to the AI section, like the other capability endpoints.

### Example

{% code title="cURL" %}

```bash
curl -X GET "https://your-site.com/umbraco/ai/management/api/v1/capabilities/enabled" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN"
```

{% endcode %}

## Available Capabilities

| Capability   | Description                                              |
| ------------ | -------------------------------------------------------- |
| `Chat`       | Conversational AI and text generation                    |
| `Embedding`  | Vector embeddings for semantic search                    |
| `Decision`   | Typed yes/no, pick-one, and score answers (experimental) |
| `Extraction` | Typed values read out of text (experimental)             |

## Use Cases

### Check Before Creating Profile

{% code title="JavaScript" %}

```javascript
async function canCreateChatProfile() {
    const response = await fetch("/umbraco/ai/management/api/v1/connections?capability=Chat", {
        credentials: "include",
    });

    const { items } = await response.json();
    return items.length > 0;
}
```

{% endcode %}

### Get Available Capabilities

{% code title="JavaScript" %}

```javascript
async function getAvailableCapabilities() {
    const response = await fetch("/umbraco/ai/management/api/v1/connections/capabilities", { credentials: "include" });

    return await response.json();
}

// Usage
const capabilities = await getAvailableCapabilities();
// ["Chat", "Embedding"]
```

{% endcode %}


---

# 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/management-api/connections/capabilities.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.