Vertex AI V1 API - Module Google::Cloud::AIPlatform::V1::SafetySetting::HarmBlockThreshold (v0.55.0)

Reference documentation and code samples for the Vertex AI V1 API module Google::Cloud::AIPlatform::V1::SafetySetting::HarmBlockThreshold.

Probability based thresholds levels for blocking.

Constants

HARM_BLOCK_THRESHOLD_UNSPECIFIED

value: 0
Unspecified harm block threshold.

BLOCK_LOW_AND_ABOVE

value: 1
Block low threshold and above (i.e. block more).

BLOCK_MEDIUM_AND_ABOVE

value: 2
Block medium threshold and above.

BLOCK_ONLY_HIGH

value: 3
Block only high threshold (i.e. block less).

BLOCK_NONE

value: 4
Block none.

OFF

value: 5
Turn off the safety filter.