Class ApplyGuardrailsDetails
Details for applying guardrails to the input content.
Case 1: Use input for simple single-text moderation. Existing customers can continue to
use this field for the current text-only flow.
Case 2: Use multimodalInput for moderation over text, image, or a combination of both.
multimodalInput supports a single text item, an array of text items only, an array of
images only, or a mixed ordered combination of text and image items.
Clients may provide input, multimodalInput, or both. At least one of these fields must
be provided. If both input and multimodalInput are provided, the service will process
input and discard multimodalInput.
Inherited Members
Namespace: Oci.GenerativeaiinferenceService.Models
Assembly: OCI.DotNetSDK.Generativeaiinference.dll
Syntax
public class ApplyGuardrailsDetails
Properties
CompartmentId
Declaration
[Required(ErrorMessage = "CompartmentId is required.")]
[JsonProperty(PropertyName = "compartmentId")]
public string CompartmentId { get; set; }
Property Value
| Type | Description |
|---|---|
| string | The OCID of the compartment to apply guardrails. |
Remarks
Required
GuardrailConfigs
Declaration
[Required(ErrorMessage = "GuardrailConfigs is required.")]
[JsonProperty(PropertyName = "guardrailConfigs")]
public GuardrailConfigs GuardrailConfigs { get; set; }
Property Value
| Type | Description |
|---|---|
| GuardrailConfigs |
Remarks
Required
GuardrailVersionConfig
Declaration
[JsonProperty(PropertyName = "guardrailVersionConfig")]
public GuardrailVersionConfig GuardrailVersionConfig { get; set; }
Property Value
| Type | Description |
|---|---|
| GuardrailVersionConfig |
Input
Declaration
[JsonProperty(PropertyName = "input")]
public GuardrailsInput Input { get; set; }
Property Value
| Type | Description |
|---|---|
| GuardrailsInput |
MultimodalInput
Declaration
[JsonProperty(PropertyName = "multimodalInput")]
public List<GuardrailsInput> MultimodalInput { get; set; }
Property Value
| Type | Description |
|---|---|
| List<GuardrailsInput> | An ordered list of text and image inputs for multimodal guardrail evaluation. This field supports a single text item, an array of text items only, an array of images only, or a mixed ordered combination of text and image items. If both |