v2.1.6+UnO GenAI Service Profile

Use the UnO GenAI Service Profileto configure and manage the connection between HCL UnO Agentic AI Builder and your custom or specific standalone foundation models. This profile allows your agents to interface directly with specialized large language models (LLMs) or small language models (SLMs), enabling targeted reasoning and custom generative capabilities within your automated workflows.

Before you begin

  • Ensure that the targeted model deployment is operational, accessible from your UnO Agentic AI Builder environment, and that you have any necessary connection permissions or routing details.

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

Table 1. Mandatory fields
Option Description
Profile name

A unique, user-defined name for this configuration instance. This name helps identify this specific model profile setup across your agentic workflow logic (for example, unomodel-production-v1).
Models available A dropdown menu containing pre-configured or discovered models supported by the provider interface. Select the appropriate model from the list.
Table 2. Optional fields
Options Description
Other model (overrides mandatory selection above) Type a specific model name if it does not appear in the standard dropdown list. This overrides the "Models available" selection.
Temperature The sampling temperature to use. Higher values mean the model will take more risks and generate more creative or varied output, while lower values make it more deterministic.
Top P Define the nucleus sampling parameter to control the diversity of the response. It controls the cumulative probability threshold for token selection. For example, a value of 0.1 means only the tokens comprising the top 10% of probability distribution are considered.