Unverified95% confidenceFactTime unknown
Top-K检索是从向量数据库中取相似度最高的前K个片段作为候选内容
1
Sources
95%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the knowledge retrieval stage, the user's question is converted into a query vector via an embedding model, similarity is computed against the text chunk vectors in the knowledge base (typically using cosine similarity), and the top-K segments are returned by ranking.72% similarUnverified相似度检索通常取Top-K（如Top-3或Top-5）最相似的文本块，相似度计算常用余弦相似度或内积71% similarUnverified向量数据库使用近似最近邻搜索（ANN）算法如HNSW、IVF-PQ，其结果本质上是概率性的，相同查询在索引重建后可能返回不同的Top-K结果66% similarUnverifiedIVF通过K-Means聚类划分向量空间，查询时只在最近的几个簇内搜索，在亿级以上超大规模数据集的内存效率上更具优势65% similarVerified向量数据库的核心操作是近似最近邻搜索（ANN），通过HNSW、IVF等索引算法将相似度计算加速到毫秒级响应64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/11820API
curl https://kongchang.com/api/v1/knowledge/claims/11820MCP
get_claim(id=11820)