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

# How to set up and configure OpenAI

> How to add OpenAI as the LLM provider for Atoti Intelligence via Spring AI, including the `spring-ai-starter-model-openai` Maven dependency, `application.yaml` API key and model configuration, and support for OpenAI-compatible APIs.

This guide explains how to configure OpenAI as the Large Language Model (LLM) provider for Atoti Intelligence.

## What is OpenAI?

<Info>
  ### Compatible APIs

  Many LLMs now support the OpenAI API format. There is a high chance that a chosen model is compatible with this API.
</Info>

## Prerequisites

Before configuring OpenAI, ensure the following requirements are met:

* An OpenAI account with API access (or compatible provider)
* OpenAI API key

## Add the dependency

Add the Spring AI OpenAI dependency to the project.

Add the following to `pom.xml`:

```xml theme={"languages":{"custom":["/engine/python-sdk/0.9/languages/pycon.tmLanguage.json"]}}
<dependency>
  <groupId>org.springframework.ai</groupId>
  <artifactId>spring-ai-starter-model-openai</artifactId>
</dependency>
```

## Configure the model

Configure the OpenAI model in the application configuration file. This example assumes that `LLM_API_KEY` is passed as an environment variable or JVM argument.

Add the following to `application.yaml`:

```yaml theme={"languages":{"custom":["/engine/python-sdk/0.9/languages/pycon.tmLanguage.json"]}}
spring:
  ai:
    openai:
      api-key: ${LLM_API_KEY}
      chat:
        options:
          model: gpt-3.5-turbo
          temperature: 0.
          maxTokens: 5000
```

Replace the following placeholders:

* Model name: Choose an available OpenAI model

Please refer to the [Spring AI documentation](https://docs.spring.io/spring-ai/reference/api/chat/comparison.html) for any additional configuration options.

## Verify the configuration

After completing the configuration, verify that the LLM connection works:

1. Start the Atoti application
2. Check the application logs for successful LLM initialization
3. Test an AI feature such as Visualize This or Auto-Explain

## Related reading

After configuring OpenAI, proceed to set up AI features:

* [Auto-Explain setup](../auto-explain/setup)
* [Visualize This setup](../chat/setup)