# OpenAI Assistant Detection

This action will forward any user text to an existing OpenAI assistant. The conversation will not hold and will continue with all other actions.

<figure><img src="https://2532694803-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvGYwUmVjfELEiJzfmWLC%2Fuploads%2FMhk6WVbEhd6lKKTw5vEX%2Fimage.png?alt=media&#x26;token=cbe7e187-89dd-44b7-a945-0b5fc4768951" alt=""><figcaption></figcaption></figure>

### Settings

The action uses the following settings:

| Setting                | Description                                                                                    | [Parsed](https://docs.xenioo.com/actions-and-operations/dynamic-parsing) |
| ---------------------- | ---------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------ |
| OpenAI API Key         | The API Key that you can generate in your OpenAI account                                       | :white\_check\_mark:                                                     |
| Assistant Id           | The unique id of the trained assistant you wish to use                                         | :white\_check\_mark:                                                     |
| Auto-Generate Content  | If enabled, Xenioo will generate the bubble with the content of the assistant reply            | :no\_entry:                                                              |
| Split Paragraphs       | If enabled, Xenioo will follow your assistant line break to generate multiple bubbles          | :no\_entry:                                                              |
| React to Page Comments | If enabled, this action will be executed when a comment is added on the attached Facebook page | :no\_entry:                                                              |
| Post Id                | The uinque id of the post associated to the reaction flag                                      | :white\_check\_mark:                                                     |

### Remarks

The assistant reply is returned to the chat (or to a variable) directly without any intervention of Xenioo on the content.

Conversation with the assistant will stay in thread, based on the openai\_assistant\_thread variale. If you wish to start a new thread just empty the variable before making a new request.

{% hint style="info" %}
Depending on the OpenAI model, request complexity and OpenAI account level, replies might take more than 20 seconds to be generated.
{% endhint %}

### Trigger

On Reply Received. This action will trigger any child operation as soon as the result is available. This trigger will not be executed if the "Auto-Generate Content" flag is enabled.

### Variables

This action produces the following variables after being triggered:

| Variable                              | Description                                              |
| ------------------------------------- | -------------------------------------------------------- |
| openai\_assistant\_thread             | The thread id of the current conversation                |
| openai\_assistant\_model              | The LLM model used by the assitant                       |
| openai\_assistant\_raw\_reply         | The raw JSON reply of the last assistant request         |
| openai\_assistant\_prompt\_tokens     | The number of prompt tokens used by the last request     |
| openai\_assistant\_completion\_tokens | The number of completion tokens used by the last request |
|                                       |                                                          |

### Availability

Channel specific availability follows the table below:

| Channel          | Availability                                                           |
| ---------------- | ---------------------------------------------------------------------- |
| Facebook         | Fully Available.                                                       |
| WhatsApp         | Fully Available.                                                       |
| Telegram         | Fully Available.                                                       |
| Web              | Fully Available.                                                       |
| Alexa            | **Not Available. Out of AI Detection is not supported inside skills.** |
| Google Assistant | Fully Available.                                                       |
| Slack            | Fully Available.                                                       |
| API              | Fully Available.                                                       |

This action can be used only at [Bot Global level](https://docs.xenioo.com/execution#global-and-local-actions) or [Behavior level.](https://docs.xenioo.com/execution#global-and-local-actions)&#x20;