Unverified90% confidenceFactTime unknown
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
1
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedMainstream vector database products include Pinecone, Chroma, and Weaviate, where text is converted into high-dimensional vectors via embedding models and stored within them.78% similarUnverifiedIn the RAG offline construction phase, embedding models (such as OpenAI's text-embedding-ada-002 or open-source BGE and M3E) convert text chunks into vectors and store them in vector databases (such as Faiss, Chroma, Milvus, and Weaviate).78% similarUnverifiedDuring the RAG indexing phase, documents are chunked and converted into vectors via an embedding model, then stored in vector databases such as Faiss, Pinecone, and Weaviate.77% similarUnverified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76% similarVerifiedRAG addresses the limitation of large models' knowledge cutoff dates by splitting private documents into text chunks, converting them into vector representations stored in a vector database, and injecting retrieved relevant content into the Prompt.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/18896API
curl https://kongchang.com/api/v1/knowledge/claims/18896MCP
get_claim(id=18896)