> ## Documentation Index
> Fetch the complete documentation index at: https://rasa.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Natural Language Generation (NLG) Servers

> Rasa enables separating response generation by outsourcing responses to an external NLG server, optimizing workflow efficiency.

## Responding to Requests

### Request Format

When your model predicts that your bot should send a response to the user,
it will send a request to your server, giving you the information
required to select or generate a response.

The body of the `POST` request sent to your NLG endpoint will be structured
like this:

<Info>
  **New in 3.6**

  We have added an `id` field to the request body.
  This field contains the ID of the response variation.
  You can use this information to compose/select a proper response variation on your NLG server.
</Info>

```json theme={null}
{
  "response": "utter_what_can_do",
  "arguments": {},
  "id": "<response_variation_id>",
  "tracker": {
    "sender_id": "user_0",
    "slots": {},
    "latest_message": {
      "intent": {
        "id": 3014457480322877053,
        "name": "greet",
        "confidence": 0.9999994039535522
      },
      "entities": [],
      "text": "Hello",
      "message_id": "94838d6f49ff4366b254b6f6d23a90cf",
      "metadata": {},
      "intent_ranking": [
        {
          "id": 3014457480322877053,
          "name": "greet",
          "confidence": 0.9999994039535522
        },
        {
          "id": 8842445304628198686,
          "name": "ask_forget_reminders",
          "confidence": 5.675940428773174e-7
        },
        {
          "id": -2566831912141022859,
          "name": "bye",
          "confidence": 3.418941929567154e-8
        },
        {
          "id": 8340513453672591403,
          "name": "ask_id",
          "confidence": 2.5274500714544956e-8
        },
        {
          "id": 5822154213939471096,
          "name": "ask_remind_call",
          "confidence": 2.4177523982871207e-8
        }
      ]
    },
    "latest_event_time": 1599476297.694504,
    "followup_action": null,
    "paused": false,
    "events": [
      {
        "event": "action",
        "timestamp": 1599476297.68784,
        "name": "action_session_start",
        "policy": null,
        "confidence": null
      },
      {
        "event": "session_started",
        "timestamp": 1599476297.6878452
      },
      {
        "event": "action",
        "timestamp": 1599476297.6878562,
        "name": "action_listen",
        "policy": null,
        "confidence": null
      },
      {
        "event": "user",
        "timestamp": 1599476297.694504,
        "text": "Hello",
        "parse_data": {
          "intent": {
            "id": 3014457480322877053,
            "name": "greet",
            "confidence": 0.9999994039535522
          },
          "entities": [],
          "text": "Hello",
          "message_id": "94838d6f49ff4366b254b6f6d23a90cf",
          "metadata": {},
          "intent_ranking": [
            {
              "id": 3014457480322877053,
              "name": "greet",
              "confidence": 0.9999994039535522
            },
            {
              "id": 8842445304628198686,
              "name": "ask_forget_reminders",
              "confidence": 5.675940428773174e-7
            },
            {
              "id": -2566831912141022859,
              "name": "bye",
              "confidence": 3.418941929567154e-8
            },
            {
              "id": 8340513453672591403,
              "name": "ask_id",
              "confidence": 2.5274500714544956e-8
            },
            {
              "id": 5822154213939471096,
              "name": "ask_remind_call",
              "confidence": 2.4177523982871207e-8
            }
          ]
        },
        "input_channel": "rest",
        "message_id": "94838d6f49ff4366b254b6f6d23a90cf",
        "metadata": {}
      }
    ],
    "latest_input_channel": "rest",
    "active_loop": {},
    "latest_action_name": "action_listen",
    "user_id": "usr-12345",
    "conversation_started_timestamp": "1599476297.68784"
  },
  "channel": {
    "name": "collector"
  }
}
```

Here is an overview of the high-level keys in the post request:

| Key         | Description                                                             |
| ----------- | ----------------------------------------------------------------------- |
| `response`  | The name of the response predicted by Rasa.                             |
| `id`        | An optional string representing the response variation ID, can be null. |
| `arguments` | Optional keyword arguments that can be provided by custom actions.      |
| `tracker`   | A dictionary containing the entire conversation history.                |
| `channel`   | The output channel this message will be sent to.                        |

You can use any or all of this information to decide
how to generate your response.

### Response Format

The endpoint needs to respond with the generated response.
Rasa will then send this response back to the user.

Below are the possible keys of a response and their (empty) types:

```json theme={null}
{
    "text": "Some text",
    "buttons": [],
    "image": null,  # string of image URL
    "elements": [],
    "attachments": [],
    "custom": {}
}
```

You can choose to provide just text, or a combination of different types of rich responses.
Just like [the responses defined in the domain file](/docs/reference/primitives/responses), a response needs to contain at the very least
either `text` or `custom` to be a valid response.

<Warning>
  **Calling responses from stories**

  If you use an external NLG service, you don't need to specify the
  responses under `responses` in the domain. However, you still need to add the response names
  to the `actions` list of the domain if you want to call them directly from
  your stories.
</Warning>

## Configuration

To set up Rasa with your NLG server the following steps are required:

1. Add required configuration to your `endpoints.yml`

```yaml title="endpoints.yml" theme={null}
nlg:
  url: http://localhost:5055/nlg
```

If your NLG server is protected and Rasa will need authentication to
access it, you can configure authentication in the endpoints:

```yaml title="endpoints.yml" theme={null}
nlg:
  url: http://localhost:5055/nlg
  #
  # You can also specify additional parameters, if you need them:
  # headers:
  #   my-custom-header: value
  # token: "my_authentication_token"  # will be passed as a GET parameter
  # basic_auth:
  #   username: user
  #   password: pass
```

2. To start the Rasa server using your NLG backend, add the `--endpoints`
   flag, e.g.:

```bash theme={null}
rasa run -m models --endpoints endpoints.yml
```


## Related topics

- [How to Set Up Your Assistant](/docs/studio/build/set-up-your-assistant.md)
- [Rasa Pro Change Log](/docs/reference/changelogs/rasa-pro-changelog.md)
- [Rasa Architecture](/docs/reference/architecture/rasa-pro.md)
- [Designing Natural and Engaging Conversations](/docs/learn/best-practices/conversation-design.md)
- [Deploying Fine-Tuned LLMs for Command Generation](/docs/pro/deploy/deploy-fine-tuned-model.md)