Updating configuration parameters of a model

To update configuration parameters for a model

1. Log in to BMC Helix Innovation Studio.
2. Select Workspace > HelixGPT Agent Studio.
3. Select the Model record definition, and click Edit data.
   The Data editor (Model) as shown in the following screenshot, is displayed:
   
4. Select the model that you want to update.
   The Edit record dialog box, as shown in the following screenshot, is displayed:
   
5. Update the configuration parameters as per your requirements.

   Configuration parameter	Description
   Auth key	A unique authorization key to validate secure communication between BMC HelixGPT and the model.
   Created by	The username or ID of the individual who created this model record
   Name	The display name of the model
   Vendor	The name of the organization or provider offering the model.
   Company	The name of the customer company or business unit associated with this model configuration.
   Description	A brief overview of the model, its purpose, and usage within BMC HelixGPT.
   Status	Indicates the current operational state of the model. The following options are available: New Assigned Fixed Rejected  Closed
   API End Point URL	The specific URL to access the model.
   API Key	A unique key provided by the model vendor to authenticate API requests.
   Assignee	An individual responsible for managing or maintaining this model record.
   Auth Client ID	A unique identifier for the client application used during authentication
   Auth Grant Type	The authentication method used to obtain access tokens.
   Auth Scopes	The permissions or access levels requested for the authentication.
   Auth Secret	Password used for authentication.
   Auth URL	The endpoint URL used to initiate the authentication process.
   Auth User Name	The username required for authentication.
   Default configuration	The predefined settings or parameters applied to the model.  An administrator can modify the default configuration.
   	Audio & screenshare configuration: This configuration controls the behavior of audio input and screensharing features during live interactions, particularly in scenarios involving voice activity detection and speech segmentation. It includes the following sub-parameters: ​​​​​ liveModelName: gemini-live-2.5-flash disabled: Set to True to manually disable automatic voice activity detection and requires client-side signaling for start or end of speech. The default value is False.​​​ startOfSpeechSensitivity: Sets the sensitivity of the system for detecting a speech. Lower sensitivity means the system needs louder or longer sounds to recognize the speech. The default value is "START_SENSITIVITY_LOW". endOfSpeechSensitivity: Sets the sensitivity of the system to detect the end of speech. Lower sensitivity means even short pauses might be seen as the end of speech. The default value is "END_SENSITIVITY_LOW". prefixPaddingMs: Adds a bit of audio (in milliseconds) before the speech starts so the beginning of the speech is not cut off. The default value is 20. silenceDurationMs: Sets how long the silence lasts before the system decides speech has ended. The default value is 200.
   Max Prompt Tokens	The maximum number of tokens allowed in a single prompt.
   Versions	The specific version or release number of the model.

6. Click Save.