The Excellence
Directory Platform Template

RAG evaluation metric assessing retriever's ability to rank relevant chunks higher than irrelevant ones, measuring context relevance and ranking quality for optimal retrieval.

Widely-used similarity metric measuring the cosine of the angle between two vectors, preferred for semantic search where direction matters more than magnitude, with values from -1 to +1.

Straight-line distance metric between vectors in multidimensional space, sensitive to both magnitude and direction, ideal when embedding magnitude carries important information.

Vector similarity metric combining both angle and magnitude information for comprehensive similarity measurement, equivalent to cosine similarity when vectors are normalized.