Unverified50% confidenceDecision RuleExact time
In a RAG system, the two steps of building the library and retrieval must use the same Embedding model, otherwise the two models have different definitions of similarity, the vector spaces cannot be aligned, and the retrieval results will deviate severely.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
What Is RAG? Retrieval-Augmented Generation Explained Through an n8n Workflow
youtubeET AI Masterclass10/15/2026
Related Entities
Related Claims
Unverified索引阶段和查询阶段必须使用同一个Embedding模型，否则向量空间不一致会导致检索完全失效72% similarUnverifiedGenerating document vectors and query vectors must use the same embedding model, as the vector spaces of different models are mutually incompatible, and mixing them will cause retrieval to fail.70% similarUnverifiedStandard vector RAG can only find isolated fragments semantically similar to the query and cannot understand the relationships between fragments.70% similarVerifiedTraditional RAG typically uses vector similarity retrieval, but has limited capability to capture structured relationships.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034138API
curl https://kongchang.com/api/v1/knowledge/claims/1034138MCP
get_claim(id=1034138)