Skip to main content

​
Atoti Intelligence Essentials

This is part of the Atoti Intelligence Essentials offer.
This guide explains how to configure OpenAI as the LLM provider for Atoti Intelligence in an Atoti Python project.

​
Compatible APIs

Many LLMs support the OpenAI API format. A model from another provider may be compatible with this configuration.

​
Prerequisites

Before configuring OpenAI, ensure the following requirements are met:
  • An Atoti Python project
  • An OpenAI account with API access, or a compatible provider
  • An OpenAI API key

​
Install the package

uv add "atoti[ai-openai]"

​
Configure the LLM

Use ConnectionConfig and ChatConfig from atoti_ai_openai to configure the LLM connection, then pass them to AiConfig. The following example uses Azure OpenAI, an OpenAI-compatible provider. Adapt the base_url and environment variable names for other providers. Then pass the config to the session through SessionConfig: 
session = tt.Session.start(tt.SessionConfig(ai=ai_config))

​
ConnectionConfig parameters

​
ChatConfig parameters

​
Verify the configuration

After completing the configuration, verify that the LLM connection works:
  1. Start the Atoti session.
  2. Open the Atoti UI.
  3. Test an AI feature such as Visualize This or Auto-Explain.
After configuring OpenAI, proceed to set up AI features: