> For the complete documentation index, see [llms.txt](https://piara-docs.gitbook.io/piara-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://piara-docs.gitbook.io/piara-documentation/admin-guide/enable-ai.md).

# Enable AI

This guide explains how to enable and configure AI functionality in **PIARA Lite** using the **OpenAI API**. Once connected, PIARA can use AI models to analyze and enrich both text and image data in your instance.

{% embed url="<https://www.youtube.com/watch?v=nfq1aNFhgPc>" %}

> ℹ️ **PIARA Premium** also supports **Google Gemini** and **Ollama**, using the same configuration flow.

***

## 🤖 What Is an AI Model in PIARA?

In PIARA, an **AI Model** is a combination of:

* A provider (e.g., OpenAI, Google, Ollama)
* A billing account (via API key)
* A specific model from that provider (e.g., `gpt-4.1`, `gpt-4.1-nano`)

This modular design provides flexibility and encourages experimentation with AI.

> 🛠️ **AI Models** are system-wide configurations available to all users in the instance.

### 💡 Notes

* **PIARA Lite** supports **OpenAI** models only.
* **PIARA Premium** adds support for **Google Gemini** and **Ollama**.

***

## 📋 Prerequisites

Make sure the following requirements are met before you proceed:

* ✅ A fully deployed instance of **PIARA Lite**
* 🔑 A valid **OpenAI API key**
* 🧪 (Optional) Some data already present in PIARA
* 📄 Required configuration parameters (listed below)

***

## ⚙️ Required Configuration Parameters

| Parameter      | Value / Source                                                       |
| -------------- | -------------------------------------------------------------------- |
| **URL**        | `https://api.openai.com`                                             |
| **API Key**    | [Get your API key from OpenAI](https://platform.openai.com/api-keys) |
| **Model Type** | [Browse available models](https://platform.openai.com/docs/models)   |

***

## 🛠️ Setup Instructions

### 1. Open the AI Model Management Page

Navigate to:\
**`System > AI Models Management`**

> 📂 If no models are configured, the list will be empty.

### 2. Add a New AI Model

Click **“Add Model”** and fill in the fields:

|                 |                                                                                                   |
| --------------- | ------------------------------------------------------------------------------------------------- |
| **Title**       | A unique name for the model (e.g., `GPT-4.1-nano`)                                                |
| **Description** | *(Optional)* Notes for internal use                                                               |
| **URL**         | `https://api.openai.com`                                                                          |
| **API Key**     | Your key from [OpenAI API Keys](https://platform.openai.com/api-keys)                             |
| **Model Type**  | e.g., `gpt-4.1-nano`, `gpt-4.1`, etc. ([See model list](https://platform.openai.com/docs/models)) |
| **Connector**   | Select `OpenAI` (PIARA Lite only supports OpenAI)                                                 |
| **Inputs**      | Select **Text**, **Image**, or both (depends on model capabilities)                               |
| **Options**     | *(Optional)* JSON config for advanced use (not covered in this guide)                             |

### 3. Test the Connection

After saving the model:

1. Click **“Save and Test”**
2. Enter a sample input (e.g., `Hello AI!`)
3. Click **Submit**
4. ✅ Confirm successful connection

### 4. (Optional) Add More Models

You can configure multiple models to support various use cases:

* Use unique names for each model
* Select different model types (e.g., lightweight vs full-scale)

***

## ✅ Result

Once set up, your models will appear in the list and can be used in enrichment and automation features throughout PIARA.