Unverified50% confidenceFactExact time
The original RAG paper used DPR (Dense Passage Retrieval) as the retriever, with Wikipedia as the knowledge source.
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
UnverifiedRAG原始论文使用DPR（Dense Passage Retrieval）作为检索器、BART作为生成器80% similarUnverifiedRetrieval-Augmented Generation (RAG) anchors facts by retrieving relevant documents from external knowledge bases before generation, but has limitations including inconsistent retrieval quality and limited context windows69% similarUnverifiedThe knowledge base relies on RAG (Retrieval-Augmented Generation) technology at its foundation, slicing private documents and converting them into high-dimensional vectors via an Embedding model for storage in a vector database.64% similarUnverifiedExa搜索工具采用类似RAG的技术，预先将网站内容抓取并存储在向量数据库中，查询时使用模糊语义匹配63% similarVerifiedThis feature uses a Retrieval-Augmented Generation (RAG) technical architecture, retrieving external documents provided by the user in real time as contextual basis when generating content.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/751611API
curl https://kongchang.com/api/v1/knowledge/claims/751611MCP
get_claim(id=751611)