Unverified50% confidenceFactExact time
At retrieval time, the user's question is likewise encoded into a vector, and the system uses measures such as cosine similarity to find the top-K chunks closest to the question vector.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn 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.80% similarUnverifiedChunks are the basic unit of retrieval; after a user asks a question, the retriever returns the top-K chunks closest to the question embedding.76% similarUnverifiedMulti-query retrieval uses an LLM to automatically generate 3–5 semantically equivalent but differently phrased variant queries for the same question, retrieves results for each separately, and takes the union to improve recall.68% 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67% similarUnverified自注意力通过将输入序列映射为查询Q、键K、值V三组向量，计算Q与K的点积相似度后经Softmax归一化得到注意力权重，再加权汇聚V向量66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1048028API
curl https://kongchang.com/api/v1/knowledge/claims/1048028MCP
get_claim(id=1048028)