Connections > Large Language Model connection properties > Connect to Large Language Model
  

Connect to Large Language Model

Let's configure a Large Language Model connection to connect to Azure OpenAI and use the chat model to process and interpret unstructured data within an intelligent structure model.
Before you use Azure OpenAI to generate an intelligent structure model, you must enable Python integration to interact with the APIs and pre-process data.
For more information about how to enable Python integration, see Creating an intelligent structure model using custom AI engine.
Note: Large Language Model connection is specifically designed to interface with large language models. You can use this connection only within an intelligent structure model. You cannot use this connection to directly read from or write to models in the way other connectors handle databases or files.

Before you begin

Before you create a Large Language Model connection, you'll need to get the the API key and endpoint URL of your Azure OpenAI account.
Check out Prepare for authentication to learn about the authentication requirements before you configure a connection.

Connection details

The following table describes the connection properties:
Property
Description
Connection Name
Name of the connection.
Each connection name must be unique within the organization. Connection names can contain alphanumeric characters, spaces, and the following special characters: _ . + -,
Maximum length is 255 characters.
Description
Description of the connection. Maximum length is 4000 characters.
Type
Large Language Model
Use Secret Vault
Stores sensitive credentials for this connection in the secrets manager that is configured for your organization.
This property appears only if secrets manager is set up for your organization.
This property is not supported by Data Ingestion and Replication.
When you enable the secret vault in the connection, you can select which credentials that the Secure Agent retrieves from the secrets manager. If you don't enable this option, the credentials are stored in the repository or on a local Secure Agent, depending on how your organization is configured.
For information about how to configure and use a secrets manager, see Secrets manager configuration.
Runtime Environment
The name of the runtime environment where you want to run tasks.
Select a Secure Agent.
Hosted Agent is not applicable.
Model Category
The type of large language model.
Select Chat to use conversation APIs to process and interpret unstructured data.
Embedding model is not applicable.
Model Provider
The provider of the large language model.
Select Azure OpenAI.
Authentication
The authentication type to connect to the selected model provider.
Select API Key.
Endpoint
The endpoint URL of the large language model API provided by the model provider.
Example for Chat model:
https://<RESOURCE_NAME>/openai/deployments/<DEPLOYMENT_NAME>/chat/completions?api-version=<API_VERSION>
API Key
The API key of your account used to authenticate access to the large language model APIs.