Agent - Model Configuration

This documentation provides instructions on deploying Agent models. An Agent model is a configuration of a Large Language Model (LLM) that outlines the specific features and functionalities to be included in the deployment and determines which capabilities of the LLM that are to be utilized.

Agent models come in two variants:

• Agent System Models - these are recommended and automatically maintained built-in models. An admin only needs to provide the LLM’s API token and API address. Currently, all system models are GDPR compliant configurations for Azure OpenAI LLMs.

• Agent Custom Models - these models require manual configuration and maintenance by an admin and can be configured for any supported LLM.

These are the instructions on how to create the two types of models:

• Agent - System Models ConfigurationPreview

• Agent - Custom Model ConfigurationPreview