Unverified50% confidenceSolutionExact time
Tool Retrieval uses vector search to first filter out the 3–5 most relevant tools before providing them to the model.
1
Sources
50%
Confidence
Long-term
Relevance
9/8/2026
First Seen
Sources
Related Entities
Related Claims
Unverified系统的五维并行搜索借鉴了信息检索领域的多路召回（Multi-path Retrieval）架构，同时启动产品类型匹配、样式推荐、配色方案、落地页模式、字体配对五个搜索维度71% similarUnverifiedIn 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.64% similarUnverified重排模型会对查询和每个候选文档进行更精细的相关性打分，将最相关的文档排在前列，从而提升检索质量63% similarUnverified语义向量匹配借助FAISS等向量检索库将用户输入映射为高维向量后进行最近邻搜索63% similarUnverified相比通用语义检索，结构化API调用（Tool Use）能返回精确的数据字段，适合处理品牌配色等精确数值查询，而传统向量检索存在召回率和精确率的权衡63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/880164API
curl https://kongchang.com/api/v1/knowledge/claims/880164MCP
get_claim(id=880164)