Function run_redteaming

evals/safety_evaluation.py:50–84

(target_url: str, questions_per_category: int = 1, scan_name: Optional[str] = None)

async def run_redteaming(target_url: str, questions_per_category: int = 1, scan_name: Optional[str] = None):
    AZURE_AI_FOUNDRY = os.getenv("AZURE_AI_FOUNDRY")
    AZURE_AI_PROJECT = os.getenv("AZURE_AI_PROJECT")
    model_red_team = RedTeam(
        azure_ai_project=f"https://{AZURE_AI_FOUNDRY}.services.ai.azure.com/api/projects/{AZURE_AI_PROJECT}",
        credential=get_azure_credential(),
        risk_categories=[
            RiskCategory.Violence,
            RiskCategory.HateUnfairness,
            RiskCategory.Sexual,
            RiskCategory.SelfHarm,
        ],
        num_objectives=questions_per_category,
    )

    if scan_name is None:
        timestamp = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
        scan_name = f"Safety evaluation {timestamp}"

    await model_red_team.scan(
        scan_name=scan_name,
        output_path=f"{root_dir}/redteams/{scan_name}.json",
        attack_strategies=[
            AttackStrategy.Baseline,
            # Easy Complexity:
            AttackStrategy.Morse,
            AttackStrategy.UnicodeConfusable,
            AttackStrategy.Url,
            # Moderate Complexity:
            AttackStrategy.Tense,
            # Difficult Complexity:
            AttackStrategy.Compose([AttackStrategy.Tense, AttackStrategy.Url]),
        ],
        target=lambda query: callback(query, target_url),
    )


if __name__ == "__main__":