Partially Verified65% confidenceFactTime unknown
RAG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
3
Sources
65%
Confidence
Long-term
Relevance
6/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRAG工程实现包含离线索引与在线检索两个阶段，在线阶段通过余弦相似度或点积相似度检索Top-K相关片段拼接进Prompt79% similarUnverifiedThe evolution of RAG technology has progressed from naive vector similarity retrieval to more advanced approaches such as Hybrid Search, Reranking, and graph-augmented retrieval.78% similarVerifiedRAG (Retrieval-Augmented Generation) relies on vector databases such as Pinecone and Weaviate, and embedding models to achieve semantic-level similarity matching78% similarUnverifiedMainstream RAG systems typically employ a hybrid retrieval strategy that combines keyword retrieval with vector retrieval and applies a reranking model for secondary filtering.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/38316API
curl https://kongchang.com/api/v1/knowledge/claims/38316MCP
get_claim(id=38316)