# Test

This endpoint will test the configured model.

### Request

Use the following request to set up the LLM:

```bash
curl --location --request POST 'https://publicapi.xenioo.com/llm/test' \
--header 'Authorization: Bearer <BOT_AUTH_TOKEN>' \
--header 'Content-Type: application/json'
--data-raw '{
	"Text":"<USER PROMPT>"	,
	"SplitParagraphs": <BOOLEAN>	,
	"ThreadId": "<THREAD ID>"	,		
}'
```

The "ThreadId" can be blank with the first message.

### Response

If successful, the request will return the reply in the response with the following format:

````json
{
    "ThreadId": "acd0c03a-f91b-4189-a5b6-39e95cd794d2",
    "Usage": {
        "PromptTokens": 1149,
        "CompletionTokens": 24,
        "Total": 1173
    },
    "Paragraphs": [
        "I am an AI assistant designed to help and provide information to users. How can I assist you today?"
    ],
    "Elapsed": 0.7142745,
    "Failed": false
}
```
````

{% hint style="warning" %}
Write the "ThreadId" that the reply will provide to you into your next call in order to continue with the conversation (making the LLM aware of the previous messages)
{% endhint %}

### Response Codes

This endpoint will reply with the following standard HTTP codes.

| Code | Meaning                                                                         |
| ---- | ------------------------------------------------------------------------------- |
| 200  | Ok. The request has been successfully fulfilled.                                |
| 400  | Bad Request. The supplied token is invalid or does not have enough permissions. |
| 404  | Not Found. The account specified by the token could not be found.               |


---

# 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.xenioo.com/xenioo-api/globa-platform-api/large-language-models/test.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.