Unverified50% confidenceSolutionExact time
In RAG, the question and the knowledge base must be vectorized using the same embedding model for vector similarity to effectively represent text similarity.
1
Sources
50%
Confidence
Long-term
Relevance
8/14/2026
First Seen
Sources
RAG实战：用检索增强生成打造百万级医疗问诊AI系统
Related Claims
UnverifiedEmbeddingModel converts text into vectors and uses vector similarity matching to find text segments most relevant to a query, forming the foundation of RAG.76% similarUnverifiedThe RAG strategy encodes code snippets as high-dimensional semantic vectors through vector embeddings, and during retrieval computes the semantic similarity between query intent and code snippets to recall relevant code.74% similarVerified向量数据库将文本内容通过嵌入模型（Embedding Model）转化为高维数值向量，检索时通过余弦相似度等算法找出语义最接近的内容70% similarUnverifiedSynonym normalization can be achieved by using sentence embedding models such as Sentence-BERT to map words into dense vectors, and then computing semantic proximity via cosine similarity.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/748207API
curl https://kongchang.com/api/v1/knowledge/claims/748207MCP
get_claim(id=748207)