> For the complete documentation index, see [llms.txt](https://interfacing.gitbook.io/interfacing-help-files/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://interfacing.gitbook.io/interfacing-help-files/administration-and-configuration/system-administrators/configuring-ai-in-the-system.md).

# Configuring AI in the System

Configure AI to enhance search, streamline workflows, and deliver trusted insights.

Before using AI capabilities in the platform, the AI engine must be configured for your organization. The system supports integration with Large Language Model (LLM) providers, such as OpenAI or other compatible services.

AI brings smarter search, faster insights, and intelligent assistance directly into your workflow, helping teams save time and make better decisions.

{% hint style="success" %}
The **AI Assistant** generates responses **exclusively from your organization's documentation and content**, ensuring that all outputs are accurate, compliant, and based on trusted internal sources.
{% endhint %}

***

## How to Configure AI in Your System

In **Phase 1**, AI configuration is not yet available directly within the platform. All configuration activities must be performed in EPC.

{% stepper %}
{% step %}

### Get the API key

* Log in to your LLM provider account.
* Navigate to the API or developer section.
* Access the **API Keys** section.
* Generate an API key and copy it.
  {% endstep %}

{% step %}

### Enable the AI

Configure the following fields in [EPC's Advanced settings](/interfacing-help-files/administration-and-configuration/system-administrators/advanced-system-settings.md):

* **`AI_IMS_ENABLED`**\
  Controls whether AI features are enabled globally across the IMS suite. This acts as the master switch for all AI functionality. 
  * Set this setting to `true`
* **`LLM_PROVIDER`**

  Specifies which Large Language Model (LLM) provider the system uses for AI functionality.

  * Required format**:** String (e.g., `openai`)
* **`LLM_API_KEY`**

  API key used to authenticate requests with the selected LLM provider.

  * Paste the API key here
* **`LLM_CHAT_MAX_TOKENS`**\
  Defines the maximum number of tokens generated per AI response.
  * Recommended minimum: `2000` tokens for optimal results

{% hint style="danger" %}
Limited AI token budget will be provided for free each month. \
Contact <sales@interfacing.com> to increase your monthly budget.
{% endhint %}

* **`LLM_CHAT_MODEL`**\
  Specifies the language model used for chat responses.
  * Examples: `gpt-3.5` , `gpt-4` , provider-specific model identifiers
    {% endstep %}

{% step %}

### Advanced Configuration

This section includes optional settings for tuning AI behavior and configuring advanced or enterprise LLM integrations. These settings are not required for standard setup.

<details>

<summary><code>LLM_CHAT_TEMPERATURE</code></summary>

Controls the randomness and creativity of AI-generated responses.

**Format:** Decimal number (e.g., `0.1`, `0.7`, `1.0`)\
**Default:** Provider default (if not specified)

**Behavior:**

* Lower values (e.g., `0.1`) → More deterministic, consistent, and predictable responses
* Higher values (e.g., `1.0`) → More creative, varied, and less deterministic responses

</details>

<details>

<summary><code>LLM_CHAT_TIMEOUT</code></summary>

Defines the maximum time (in seconds) the system waits for a response from the configured LLM provider.

**Format:** Number (seconds)\
**Default:** `30`

If the LLM does not respond within this time window, the request will be terminated and an error will be returned.

</details>

<details>

<summary><code>LLM_CHAT_URL</code></summary>

Defines the API endpoint used for content generation and improvement requests.

This setting is primarily used when connecting to a private or enterprise LLM deployment instead of the default provider endpoint.

**Default:**\
`https://api.openai.com/v1/chat/completions`

</details>

<details>

<summary><code>LLM_EMBEDDINGS_URL</code></summary>

Defines the API endpoint used for the AI Assistant.

This setting is primarily used when connecting to a private LLM deployment instead of the default provider endpoint.

**Default:**\
`https://api.openai.com/v1/embeddings`

</details>
{% endstep %}
{% endstepper %}

***

## OpenAI License Guidance

If you are using your own OpenAI account, note the following:

* **Any OpenAI API subscription works**.\
  Customers may choose pay-as-you-go, enterprise, or any other plan. EPC & IMS do not require a specific license type.
* **No special prerequisites or limitations**.\
  Integration works as long as you have a valid OpenAI API key.
* **Only OpenAI API keys** are supported.\
  Standard user-level ChatGPT accounts are not compatible.

{% hint style="info" %}
For guidance on using the OpenAI API, you can refer to OpenAI’s official documentation, including the [Batch API](https://platform.openai.com/docs/guides/batch) and [Priority Processing](https://openai.com/api-priority-processing/) guides.
{% endhint %}

***

## Explore AI Capabilities

While configuration is not yet supported, you can already begin using the **AI Assistant** in the platform.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="image">Cover image</th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Searching with the AI Assistant</strong></td><td>Leverage the AI Assistant to streamline your workflow and boost productivity with intelligent support.</td><td><a href="https://1488562728-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FTx7AmE0d2Q4ja20EYjF5%2Fuploads%2F9cdChXHzOm83ef10aixi%2FIMS-V16-NAV-Library-Icons-49.png?alt=media&amp;token=e6a515f5-715c-4e19-afc8-39d28b6ff60a">IMS-V16-NAV-Library-Icons-49.png</a></td><td><a href="/interfacing-help-files/end-users/searching-for-content/searching-with-the-ai-assistant.md">Searching with the AI Assistant</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://interfacing.gitbook.io/interfacing-help-files/administration-and-configuration/system-administrators/configuring-ai-in-the-system.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.