Watsonx Profile
Use the Watsonx Profile to configure IBM watsonx.ai foundation models.
Before you begin
-
You must have a valid Watsonx Credential configured in the Credential Library to authenticate this connection.
-
Ensure that all mandatory fields (marked with *) are completed accurately.
| Option | Description |
|---|---|
| Profile name |
A unique identifier for this configuration instance. This name will be used to reference this specific Watsonx model setup in the Agentic AI Builder. |
| Models available | Select a supported model from the dropdown list. |
| 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. |
| Max Tokens | Specify the maximum number of tokens to generate in the model's output. |
| 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. |
| Request Timeout | Enter the duration (in seconds) the system should wait for a response before timing out. |
| Max Retries | Enter the maximum number of times the system should attempt the request if it fails. |