Unverified50% confidenceFactExact time
双塔架构允许文档端向量在离线阶段预先计算并存储在向量数据库中，在线查询时只需编码查询文本
1
Sources
50%
Confidence
Long-term
Relevance
8/6/2026
First Seen
Sources
Related Claims
Unverified知识库检索中，文档分段后每个文本块通过嵌入模型（如text-embedding-ada-002或BGE系列）转换为高维向量存储在向量数据库中76% similarVerifiedVector databases such as FAISS, Chroma, and Weaviate build indexes by encoding text as high-dimensional vectors, enabling semantic similarity retrieval in milliseconds.74% similarVerifiedVector databases convert code snippets into high-dimensional embedding vectors and perform Approximate Nearest Neighbor (ANN) searches, enabling on-demand memory without expanding the context window.74% similarVerifiedThe RAG workflow is divided into offline and online phases: offline, documents are chunked and converted into vectors stored in a vector database; online, questions are converted into vectors and the most similar text segments are retrieved via ANN algorithms and concatenated into the context.71% similarUnverifiedThe WeChat Cloud Development free tier provides a certain number of database read/write operations and storage space.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/692779API
curl https://kongchang.com/api/v1/knowledge/claims/692779MCP
get_claim(id=692779)