DeepEval

DeepEval provides single-turn and conversational metrics for RAG, agents, toxicity, bias, and PII checks. Rhesis exposes them in the platform and SDK — no separate CLI.

deepeval_example.py
from rhesis.sdk.metrics import DeepEvalAnswerRelevancy

metric = DeepEvalAnswerRelevancy(threshold=0.7)
result = metric.evaluate(
    input="What is photosynthesis?",
    output="Photosynthesis is how plants convert light into energy.",
)

See the full metric list: SDK — DeepEval metrics · Conversational metrics