Expired50% confidenceSolutionExact time
The retrieval stage uses a Bi-Encoder dual-tower model (such as text-embedding-ada-002 or the BGE series), with vectors precomputed offline and stored in a vector database (such as FAISS or Milvus).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/20/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/18/2026(expired)
Sources
Related Claims
UnverifiedThe recall stage typically uses Bi-Encoder models (such as text-embedding-ada-002 or the BGE series), while the reranking stage uses Cross-Encoder models (such as Cohere Rerank or BGE-Reranker).78% similarUnverified现代Sentence Embedding模型通常采用双塔（Bi-Encoder）结构，查询和文档分别独立编码为向量73% similarUnverifiedA Bi-Encoder encodes queries and documents independently into vectors and computes relevance via cosine similarity or dot product; document vectors can be pre-computed offline and stored in a vector database.72% similarUnverified嵌入模型采用双塔（Bi-encoder）架构，将查询和文档独立编码成向量，然后通过余弦相似度等方式计算距离69% similarUnverifiedRetrieval BERT uses a Bi-Encoder (dual-tower model), where two sentences each generate a vector and similarity is then computed; vectors can be precomputed offline, enabling fast online matching.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/566483API
curl https://kongchang.com/api/v1/knowledge/claims/566483MCP
get_claim(id=566483)