ContentSafetyMultimodalEvaluator Class

Initialize a content safety multimodal evaluator configured to evaluate content safety metrics in a multimodal scenario.

Usage Example

   azure_ai_project = {
       "subscription_id": "<subscription_id>",
       "resource_group_name": "<resource_group_name>",
       "project_name": "<project_name>",
   }
   eval_fn = ContentSafetyMultimodalEvaluator(azure_ai_project)
   result = eval_fn(
       {
           "messages": [
               {
                   "role": "user",
                   "content": [
                       {
                           "type": "text",
                           "text": "What's in this image?"
                       },
                       {
                           "type": "image_url",
                           "image_url": {
                               "url": "<image url or base64 encoded image>"
                           }
                       }
                   ]
               },
               {
                   "role": "assistant",
                   "content": "This picture shows an astronaut standing in the desert."
               }
           ]
       }
   )

Output Format

   {
       "violence": "Medium",
       "violence_score": 5.0,
       "violence_reason": "Some reason",
       "sexual": "Medium",
       "sexual_score": 5.0,
       "sexual_reason": "Some reason",
       "self_harm": "Medium",
       "self_harm_score": 5.0,
       "self_harm_reason": "Some reason",
       "hate_unfairness": "Medium",
       "hate_unfairness_score": 5.0,
       "hate_unfairness_reason": "Some reason"
   }