Skip to main content
SAICA-KG

Tools

ragas

13,605

Supercharge your LLM application evaluations — RAG- and agent-centric metrics.

DetectionPost-generationFull HITLStableTier 2BEnvironment
Maturity tier details

Computed tier: 2B(raw score 4.15). Effective tier: 2B.

Facets:documented_in=0evaluated_on=0integration_surfaces=0.5paper_citations=0recent_commit=2stars=1.65

Source of truth:pipeline/maturity/score.py

Description

Ragas is an open-source evaluation framework for LLM applications with specialized metrics for RAG systems (faithfulness, context precision/recall, answer relevancy) and agent trajectories. Pytest-compatible, widely adopted in the RAG community, and frequently paired with tracing backends.

Why it's included

Canonical RAG-eval library. Complements deepeval (broad LLM eval) and autorag (pipeline search) by owning the faithfulness / context-precision metric family.

Addresses failure modes

  • Fabrication — Generating reference to non-existent APIs, packages, or symbols.
  • Logic error — Correct API use, incorrect logic.
  • Context pollution — Trajectory drift, hallucination spirals, overlong or off-task context.

Techniques

rag-metricsfaithfulnesscontext-recallcontext-precision

View raw YAML on GitHub →