Unverified50% confidenceFactExact time
Commonly used embedding models for RAG include Sentence-BERT, BGE (a Chinese vector model introduced by BAAI), and M3E.
1
Sources
50%
Confidence
Long-term
Relevance
8/15/2026
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
UnverifiedKey components of RAG include embedding models (such as OpenAI's text-embedding-3 series or the open-source BGE model), vector databases (Pinecone, Weaviate, Chroma, pgvector, etc.), and retrieval strategies.76% 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).65% similarVerifiedRAG技术栈由向量数据库（如Pinecone、Weaviate、Chroma）、嵌入模型、重排序等技术构成64% similarUnverifiedRAG 架构将官方文档切片后通过嵌入模型转化为高维向量存入向量数据库（如 Chroma、Weaviate、Pinecone），可缓解版本混淆并提升命令版本准确性63% similarUnverifiedRAG (Retrieval-Augmented Generation) is currently the mainstream architectural paradigm for enterprise-level large model deployment.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/751612API
curl https://kongchang.com/api/v1/knowledge/claims/751612MCP
get_claim(id=751612)