Firebase.AI.SafetyRating

A type defining potentially harmful media categories and their model-assigned ratings.

Summary

A value of this type may be assigned to a category for every model-generated response, not just responses that exceed a certain threshold.

Public types
`HarmProbability{ Unknown = 0, Negligible, Low, Medium, High }`	enum The probability that a given model output falls under a harmful content category.
`HarmSeverity{ Unknown = 0, Negligible, Low, Medium, High }`	enum The magnitude of how harmful a model response might be for the respective `HarmCategory`.

Properties
`Blocked`	`bool` If true, the response was blocked.
`Category`	`HarmCategory` The category describing the potential harm a piece of content may pose.
`Probability`	`HarmProbability` The model-generated probability that the content falls under the specified HarmCategory.
`ProbabilityScore`	`float` The confidence score that the response is associated with the corresponding HarmCategory.
`Severity`	`HarmSeverity` The severity reflects the magnitude of how harmful a model response might be.
`SeverityScore`	`float` The severity score is the magnitude of how harmful a model response might be.

Public types

HarmProbability

 Firebase::AI::SafetyRating::HarmProbability

The probability that a given model output falls under a harmful content category.

Note: This does not indicate the severity of harm for a piece of content.

Properties
`High`	The probability is high. The content described is very likely harmful.
`Low`	The probability is small but non-zero.
`Medium`	The probability is moderate.
`Negligible`	The probability is zero or close to zero. For benign content, the probability across all categories will be this value.
`Unknown`	A new and not yet supported value.

HarmSeverity

 Firebase::AI::SafetyRating::HarmSeverity

The magnitude of how harmful a model response might be for the respective HarmCategory.

Properties
`High`	High level of harm severity.
`Low`	Low level of harm severity.
`Medium`	Medium level of harm severity.
`Negligible`	Negligible level of harm severity.
`Unknown`	A new and not yet supported value.

Properties

Blocked

bool Firebase::AI::SafetyRating::Blocked

If true, the response was blocked.

Probability

HarmProbability Firebase::AI::SafetyRating::Probability

The model-generated probability that the content falls under the specified HarmCategory.

This is a discretized representation of the ProbabilityScore.

Important: This does not indicate the severity of harm for a piece of content.

ProbabilityScore

float Firebase::AI::SafetyRating::ProbabilityScore

The confidence score that the response is associated with the corresponding HarmCategory.

The probability safety score is a confidence score between 0.0 and 1.0, rounded to one decimal place; it is discretized into a HarmProbability in Probability. See probability scores in the Google Cloud documentation for more details.

Severity

HarmSeverity Firebase::AI::SafetyRating::Severity

The severity reflects the magnitude of how harmful a model response might be.

This is a discretized representation of the SeverityScore.

SeverityScore

float Firebase::AI::SafetyRating::SeverityScore

The severity score is the magnitude of how harmful a model response might be.

The severity score ranges from 0.0 to 1.0, rounded to one decimal place; it is discretized into a HarmSeverity in Severity. See severity scores in the Google Cloud documentation for more details.