ragas

What problem does it solve?

This Skill addresses the challenge of objectively evaluating the performance and quality of Retrieval Augmented Generation (RAG) pipelines, ensuring they are faithful, relevant, and accurate.

Core Features & Use Cases

• RAGAS Evaluation: Measures faithfulness, answer relevancy, context precision, and context recall.
• Compliance Assessment: Helps evaluate AI systems against EU AI Act Art. 15 requirements related to performance and risk.
• Risk Mitigation: Implements controls for performance risks by identifying weaknesses in RAG systems.
• Use Case: A developer building a customer support chatbot powered by RAG can use this skill to test if the chatbot's answers are factually correct based on the provided context and if the context used is relevant to the user's query.

Quick Start

Use the ragas skill to evaluate the faithfulness of generated answers against the provided context.