Aident Loadout के माध्यम से Metatextai Tools के साथ Metatextai Evaluate का उपयोग करें। चलाने से पहले इनपुट, आउटपुट, सेटअप, मूल्य और जोखिम देखें।
Tool to evaluate LLM messages against policies/guardrails. Use after generating model output to get violation details or corrections.
messagesआवश्यकarrayConversation messages to evaluate. Must include 'user' and 'assistant' messages; 'system' optional.
policiesarrayInline policies to evaluate; overrides console defaults when provided.
fail_fastbooleanIf true, stops evaluation on first violation.
policy_idsarrayList of policy IDs to override default console policies.
applicationstringApplication identifier; defaults to your configured application ID.
override_responsestringTop-level override response message on violation. Overrides correction.
correction_enabledbooleanIf true, returns corrected output when violations occur (unless override_response is set).
dataआवश्यकData from the action execution
errorstringError if any occurred during the execution of the action
successfulआवश्यकbooleanWhether or not the action execution was successful or not
API कुंजी कनेक्शन। जोखिम स्तर 2/5।
मुफ़्त Action
अभी कोई प्रकाशित Skills इस Action को स्पष्ट रूप से संदर्भित नहीं करती है।