Azure Profile

Use the Azure Profile to configure and manage the connection between HCL UnO Agentic AI Builder and Azure OpenAI Service. This integration enables your agents to leverage enterprise-grade OpenAI models (such as GPT-4, GPT-3.5-Turbo) hosted securely within your Azure environment.

Before you begin

  • You must have an active Azure OpenAI Resource deployed in your Azure portal.

  • You must have specific Model Deployments created within that resource (for example, a deployment named gpt-4 or my-custom-model).

  • You must have a valid Azure Credential configured in the Credential Library to authenticate the connection.

  • Ensure that all mandatory fields (marked with *) are completed accurately.

Table 1. Mandatory fields
Option Description
Name

A unique identifier for this configuration instance. This name will be used within the Agentic AI Builder to reference this specific Azure model setup.
LLM Name

The specific authentication credential (previously created in the Credential Library) used to authorize the connection to your Azure OpenAI resource.
Table 2. Optional fields
Options Description
Model Name
The name of the specific deployment in your Azure portal (for example, gpt-35-turbo or gpt-4-deployment).
Note:

The Model Name field is where you specify the exact technical identifier for the Large Language Model (LLM) or Small Language Model (SLM) to be used.

If Discover Models is checked in the corresponding Credentials account, available LLM models will populate a dropdown menu for selection in the LLM Name field.
Temperature Controls randomness in the output. Higher values (for example, 0.8) result in more creative responses; lower values result in more deterministic output.
Top P Works with top-k to control nucleus sampling (for example, 0.9). It constrains the token pool to the top P probability mass.
Presence Penalty A value that penalizes new tokens based on whether they have already appeared in the text so far. Increases the model's likelihood to talk about new topics.
Frequency Penalty A value that penalizes new tokens based on their existing frequency in the text so far. Decreases the model's likelihood to repeat the same line verbatim.
Max Tokens The maximum number of tokens the model is allowed to generate in the response (default: 1000).
Max Retries The number of times the system should attempt to reconnect or resend the request in case of a transient failure (default: 3).
Streaming A checkbox to enable or disable streaming responses. If checked, the model returns tokens progressively as they are generated rather than waiting for the full completion.