소개
The Document Ranking skill provides a specialized utility for sorting and prioritizing search results within an Adaptive RAG (Retrieval-Augmented Generation) workflow. By processing distance and similarity metrics already computed during vector search, it enables precise control over document relevance without redundant database queries. This skill is essential for developers looking to improve the quality of LLM responses by ensuring only the most contextually relevant information is passed to the generation phase, effectively reducing token costs and noise.
