# Chat

The chat endpoints provide access to AI chat completions through the Management API.

## Available Endpoints

| Method | Endpoint                                                         | Description                                     |
| ------ | ---------------------------------------------------------------- | ----------------------------------------------- |
| POST   | `/umbraco/ai/management/api/v1/chat/complete`                    | Get a chat completion using the default profile |
| POST   | `/umbraco/ai/management/api/v1/chat/{profileIdOrAlias}/complete` | Get a chat completion using a specific profile  |

## Request Format

All chat endpoints accept the same request body:

{% code title="Request Body" %}

```json
{
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Hello, how are you?"
        }
    ]
}
```

{% endcode %}

### Message Roles

| Role        | Description                             |
| ----------- | --------------------------------------- |
| `system`    | Instructions for the AI (sets behavior) |
| `user`      | Messages from the user                  |
| `assistant` | Previous responses from the AI          |

## Response Format

{% code title="Response" %}

```json
{
    "message": {
        "role": "assistant",
        "content": "Hello! I'm doing well, thank you for asking. How can I help you today?"
    },
    "finishReason": "stop",
    "usage": {
        "inputTokens": 25,
        "outputTokens": 18,
        "totalTokens": 43
    }
}
```

{% endcode %}

## In This Section

{% content-ref url="/pages/jJM8OYbyewFdFTq4bCrQ" %}
[Complete](/ai-in-umbraco/management-api/chat/complete.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/chat.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.