Ragas

Ragas evaluates RAG pipelines with referenceless and reference-based metrics (faithfulness, context relevance, answer accuracy).

ragas_example.py
from rhesis.sdk.metrics import RagasFaithfulness

metric = RagasFaithfulness(threshold=0.8)
result = metric.evaluate(
    input="What causes ocean tides?",
    output="The gravitational pull of the moon causes ocean tides.",
    contexts=["The moon's gravity pulls on Earth's oceans, causing tides."],
)

See the full metric list: SDK — Ragas metrics