LLM Judge Presets

.. currentmodule:: opik.evaluation.metrics

These presets wrap common GEval prompt templates so you can instantiate judges with one line of code. Provide an appropriate model (for example, "gpt-4o") and ensure the backing provider is configured via opik.configure.

Agent & Task Presets

.. autoclass:: AgentTaskCompletionJudge :special-members: init :members: score

.. autoclass:: AgentToolCorrectnessJudge :special-members: init :members: score

Conversation Quality Presets

.. autoclass:: DialogueHelpfulnessJudge :special-members: init :members: score

.. autoclass:: QARelevanceJudge :special-members: init :members: score

.. autoclass:: SummarizationCoherenceJudge :special-members: init :members: score

.. autoclass:: SummarizationConsistencyJudge :special-members: init :members: score

.. autoclass:: PromptUncertaintyJudge :special-members: init :members: score

Risk & Bias Presets

.. autoclass:: ComplianceRiskJudge :special-members: init :members: score

.. autoclass:: DemographicBiasJudge :special-members: init :members: score

.. autoclass:: GenderBiasJudge :special-members: init :members: score

.. autoclass:: PoliticalBiasJudge :special-members: init :members: score

.. autoclass:: RegionalBiasJudge :special-members: init :members: score

.. autoclass:: ReligiousBiasJudge :special-members: init :members: score