Model Armor v1beta API - Namespace Google.Cloud.ModelArmor.V1Beta (1.0.0-beta04)

message describing AiPlatformFloorSetting

Represents Byte Data item.

Container for nested types declared in the ByteDataItem message type.

Message for creating a Template

CSAM (Child Safety Abuse Material) Filter Result

Represents Data item

Message for deleting a Template

Filters configuration.

Filter Result obtained after Sanitization operations.

Message describing FloorSetting resource

Container for nested types declared in the FloorSetting message type.

message describing FloorSetting Metadata

Container for nested types declared in the FloorSettingMetadata message type.

Metadata to enable multi language detection via floor setting.

Resource name for the FloorSetting resource.

Message for getting a Floor Setting

Message for getting a Template

Message for requesting list of Templates

Message for response to listing Templates

Malicious URI Filter Result.

Container for nested types declared in the MaliciousUriFilterResult message type.

Information regarding malicious URI and its location within the input content.

Malicious URI filter settings.

Container for nested types declared in the MaliciousUriFilterSettings message type.

Message item to report information, warning or error messages.

Container for nested types declared in the MessageItem message type.

Service describing handlers for resources

Base class for server-side implementations of ModelArmor

Client for ModelArmor

ModelArmor client wrapper, for convenient use.

Builder class for ModelArmorClient to provide simple configuration of credentials, endpoint etc.

ModelArmor client wrapper implementation, for convenient use.

Settings for ModelArmorClient instances.

Message for Enabling Multi Language Detection.

Prompt injection and Jailbreak Filter Result.

Prompt injection and Jailbreak Filter settings.

Container for nested types declared in the PiAndJailbreakFilterSettings message type.

Responsible AI Result.

Container for nested types declared in the RaiFilterResult message type.

Detailed Filter result for each of the responsible AI Filter Types.

Responsible AI Filter settings.

Container for nested types declared in the RaiFilterSettings message type.

Responsible AI filter.

Half-open range interval [start, end)

Sanitization result after applying all the filters on input content.

Container for nested types declared in the SanitizationResult message type.

Message describing Sanitization metadata.

Sanitize Model Response request.

Sanitized Model Response Response.

Sanitize User Prompt request.

Sanitized User Prompt Response.

Sensitive Data Protection Advanced configuration.

Sensitive Data Protection basic configuration.

Container for nested types declared in the SdpBasicConfig message type.

Sensitive Data Protection Deidentification Result.

Sensitive Data Protection filter result.

Sensitive Data Protection settings.

Finding corresponding to Sensitive Data Protection filter.

Container for nested types declared in the SdpFinding message type.

Location of this Sensitive Data Protection Finding within input content.

Sensitive Data Protection Inspection Result.

Message describing Template resource

Container for nested types declared in the Template message type.

Message describing TemplateMetadata

Container for nested types declared in the TemplateMetadata message type.

Metadata to enable multi language detection via template.

Resource name for the Template resource.

Message for Updating a Floor Setting

Message for updating a Template

Details of an identified virus

Container for nested types declared in the VirusDetail message type.

Virus scan results.

Container for nested types declared in the VirusScanFilterResult message type.

Enum of possible cases for the "enforcement_type" oneof.

Option to specify the type of byte data.

Enum of possible cases for the "data_item" oneof.

Confidence levels for detectors. Higher value maps to a greater confidence level. To enforce stricter level a lower value should be used.

Enum which reports whether a specific filter executed successfully or not.

Option to specify filter match state.

Enum of possible cases for the "filter_result" oneof.

Integrated service for which the floor setting is applicable.

The possible contents of FloorSettingName.

A field indicating the outcome of the invocation, irrespective of match status.

Option to specify the state of Malicious URI filter (ENABLED/DISABLED).

Option to specify the type of message.

Option to specify the state of Prompt Injection and Jailbreak filter (ENABLED/DISABLED).

Options for responsible AI Filter Types.

Option to specify the state of Sensitive Data Protection basic config (ENABLED/DISABLED).

Enum of possible cases for the "result" oneof.

Enum of possible cases for the "sdp_configuration" oneof.

For more information about each Sensitive Data Protection likelihood level, see https://cloud.google.com/sensitive-data-protection/docs/likelihood.

Enforcement type for Model Armor filters.

The possible contents of TemplateName.

Defines all the threat types of a virus

Type of content scanned.