Unverified50% confidenceFactExact time
Commonly used metrics for RAG retrieval quality include Recall@k and MRR (Mean Reciprocal Rank).
1
Sources
50%
Confidence
Long-term
Relevance
10/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRAG知识库质量的关键指标包括文本切片策略（Chunk Size与Overlap）、Embedding模型选型、检索Top-K设置以及重排序（Reranking）策略67% similarPartially VerifiedRAG系统的召回主要有两种方式：向量相似度计算和关键词匹配62% similarUnverifiedThe selection of vector databases and chunking strategies (chunk size, overlap) have a significant impact on RAG retrieval quality.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/970555API
curl https://kongchang.com/api/v1/knowledge/claims/970555MCP
get_claim(id=970555)