Verified65% confidenceFactExact time
RAG (Retrieval-Augmented Generation) is an architectural paradigm proposed by Facebook AI Research in 2020, whose core idea is to retrieve relevant document snippets from an external knowledge base before the large language model generates a response and inject them into the prompt as context.
3
Sources
65%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRAG was first proposed in a 2020 paper by Patrick Lewis and others from Facebook AI Research.74% similarUnverifiedGraph RAG是微软研究院于2024年提出并开源的检索增强范式，先用LLM抽取实体与关系构建知识图谱，检索时沿图结构进行社区摘要68% similarUnverifiedONNX（Open Neural Network Exchange）由微软和Facebook于2017年联合推出，现已成为业界事实标准的跨框架模型交换格式60% similarUnverified谷歌AI Overviews采用检索增强生成（RAG）技术，先检索多个权威网页再由大模型综合生成结构化答案并保留来源引用59% similarVerifiedAI Overview is a search feature that Google fully launched in 2024, based on its Gemini large language model, capable of automatically generating comprehensive summary answers after a user enters a query.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/802094API
curl https://kongchang.com/api/v1/knowledge/claims/802094MCP
get_claim(id=802094)