diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_content_safety_multimodal.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_content_safety_multimodal.py index 53518ee02518..31c42d24b4ff 100644 --- a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_content_safety_multimodal.py +++ b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_content_safety_multimodal.py @@ -33,7 +33,6 @@ class ContentSafetyMultimodalEvaluator: :type parallel: bool :return: A function that evaluates multimodal chat messages and generates content safety metrics. - :rtype: Callable **Usage Example** @@ -45,7 +44,7 @@ class ContentSafetyMultimodalEvaluator: "project_name": "", } eval_fn = ContentSafetyMultimodalEvaluator(azure_ai_project) - result = eval_fn( + result = eval_fn(conversation= { "messages": [ { @@ -104,8 +103,9 @@ def __init__(self, credential, azure_ai_project, parallel: bool = False): def __call__(self, *, conversation, **kwargs): """ Evaluates content-safety metrics for list of messages. + :keyword conversation: The conversation contains list of messages to be evaluated. - Each message should have "role" and "content" keys. + Each message should have "role" and "content" keys. It supports single turn only. :paramtype conversation: ~azure.ai.evaluation.Conversation :return: The evaluation score based on the Content Safety Metrics. :rtype: Dict[str, Union[float, str]] diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_hate_unfairness.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_hate_unfairness.py index b1a1ae6898b8..d0ed8b1e642e 100644 --- a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_hate_unfairness.py +++ b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_hate_unfairness.py @@ -28,7 +28,7 @@ class HateUnfairnessMultimodalEvaluator: "project_name": "", } eval_fn = HateUnfairnessMultimodalEvaluator(azure_ai_project) - result = eval_fn( + result = eval_fn(conversation= { "messages": [ { @@ -72,8 +72,9 @@ def __init__(self, credential, azure_ai_project): def __call__(self, *, conversation, **kwargs): """ Evaluates hate unfairness content. + :keyword conversation: The conversation contains list of messages to be evaluated. - Each message should have "role" and "content" keys. + Each message should have "role" and "content" keys. It supports single turn only. :paramtype conversation: ~azure.ai.evaluation.Conversation :return: The hate unfairness score. :rtype: Dict[str, Union[float, str]] diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_protected_material.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_protected_material.py index 6ba03f54dc2a..afece3ce981d 100644 --- a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_protected_material.py +++ b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_protected_material.py @@ -22,7 +22,6 @@ class ProtectedMaterialMultimodalEvaluator: :type azure_ai_project: ~azure.ai.evaluation.AzureAIProject :return: A dictionary containing the evaluation result label and reasoning. - :rtype: Dict[str, str] **Usage Example** @@ -34,7 +33,7 @@ class ProtectedMaterialMultimodalEvaluator: "project_name": "", } eval_fn = ProtectedMaterialMultimodalEvaluator(azure_ai_project) - result = eval_fn( + result = eval_fn(conversation= { "messages": [ { @@ -82,8 +81,9 @@ def __call__(self, *, conversation, **kwargs): """ Evaluates protected materials content. - :keyword messages: The messages to be evaluated. Each message should have "role" and "content" keys. - :paramtype messages: ~azure.ai.evaluation.Conversation + :keyword conversation: The conversation contains list of messages to be evaluated. + Each message should have "role" and "content" keys. It supports single turn only. + :paramtype conversation: ~azure.ai.evaluation.Conversation :return: A dictionary containing a boolean label and reasoning. :rtype: Dict[str, str] """ @@ -101,8 +101,9 @@ def __init__(self, credential, azure_ai_project): async def __call__(self, *, conversation, **kwargs): """ Evaluates content according to this evaluator's metric. + :keyword conversation: The conversation contains list of messages to be evaluated. - Each message should have "role" and "content" keys. + Each message should have "role" and "content" keys. It supports single turn only. :paramtype conversation: ~azure.ai.evaluation.Conversation :return: The evaluation score computation based on the Content Safety metric (self.metric). :rtype: Any diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_self_harm.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_self_harm.py index 17e902f19c2f..757a30a58046 100644 --- a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_self_harm.py +++ b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_self_harm.py @@ -28,7 +28,7 @@ class SelfHarmMultimodalEvaluator: "project_name": "", } eval_fn = SelfHarmMultimodalEvaluator(azure_ai_project) - result = eval_fn( + result = eval_fn(conversation= { "messages": [ { @@ -72,8 +72,9 @@ def __init__(self, credential, azure_ai_project): def __call__(self, *, conversation, **kwargs): """ Evaluates self harm content. + :keyword conversation: The conversation contains list of messages to be evaluated. - Each message should have "role" and "content" keys. + Each message should have "role" and "content" keys. It supports single turn only. :paramtype conversation: ~azure.ai.evaluation.Conversation :return: The self harm score. :rtype: Dict[str, Union[float, str]] diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_sexual.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_sexual.py index 8b571206776b..0c8be5cc2da5 100644 --- a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_sexual.py +++ b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_sexual.py @@ -28,7 +28,7 @@ class SexualMultimodalEvaluator: "project_name": "", } eval_fn = SexualMultimodalEvaluator(azure_ai_project) - result = eval_fn( + result = eval_fn(conversation= { "messages": [ { @@ -72,8 +72,9 @@ def __init__(self, credential, azure_ai_project): def __call__(self, *, conversation, **kwargs): """ Evaluates sexual content. + :keyword conversation: The conversation contains list of messages to be evaluated. - Each message should have "role" and "content" keys. + Each message should have "role" and "content" keys. It supports single turn only. :paramtype conversation: ~azure.ai.evaluation.Conversation :return: The sexual score. :rtype: Dict[str, Union[float, str]] diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_violence.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_violence.py index b86382c86817..cb45cd2edb40 100644 --- a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_violence.py +++ b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_multimodal/_violence.py @@ -28,7 +28,7 @@ class ViolenceMultimodalEvaluator: "project_name": "", } eval_fn = ViolenceMultimodalEvaluator(azure_ai_project) - result = eval_fn( + result = eval_fn(conversation= { "messages": [ { @@ -72,8 +72,9 @@ def __init__(self, credential, azure_ai_project): def __call__(self, *, conversation, **kwargs): """ Evaluates violence content. + :keyword conversation: The conversation contains list of messages to be evaluated. - Each message should have "role" and "content" keys. + Each message should have "role" and "content" keys. It supports single turn only. :paramtype conversation: ~azure.ai.evaluation.Conversation :return: The violence score. :rtype: Dict[str, Union[float, str]]