ai21.net
语言

Retrieval-Augmented Generation pipeline

Retrieval-Augmented Generation pipeline — 1

提示词

Landscape 16:9 academic systems diagram of a RAG pipeline, 6-stage left-to-right flow.

(1) "User query" box with placeholder text "What are the side effects of drug X?" and a small user silhouette.
(2) Hexagonal "Embedding encoder (BERT-style)", caption "dense vector d=768".
(3) Stylised database cylinder "Vector store" with "Index: 1.2M chunks"; arrow from (2) labeled "kNN, k=5".
(4) "Retrieved passages" — stack of 5 doc thumbnails; caption "top-k chunks + metadata".
(5) Hexagonal hub "Frozen LLM"; long curved arrow from (1) labeled "original query" also lands here; arrow from (4) labeled "retrieved context".
(6) "Grounded answer" with inline marker "[cite: doc#47]"; caption "with source citations".

Dashed outline around (2)-(3) labeled "OFFLINE — built once". Dashed outline around (4)-(5) labeled "ONLINE — per query".

Title: "Retrieval-Augmented Generation pipeline". Subtitle: "Lewis et al., 2020".

中文译文

横版 16:9 学术风格系统图,展示一条 RAG 流水线,6 个阶段从左到右流动。

(1) "用户查询" 方框,内含占位文本 "药物 X 有哪些副作用?",并配有一个小型用户剪影。
(2) 六边形 "嵌入编码器(BERT 风格)",说明文字 "稠密向量 d=768"。
(3) 风格化数据库圆柱体 "向量库",标注 "索引:120 万条切片";从 (2) 指向它的箭头标注 "kNN, k=5"。
(4) "检索到的段落" —— 5 个文档缩略图堆叠;说明文字 "top-k 切片 + 元数据"。
(5) 六边形中枢 "冻结的 LLM";一条从 (1) 出发的长弧线箭头同样指向此处,标注 "原始查询";从 (4) 出发的箭头标注 "检索到的上下文"。
(6) "有依据的回答",行内标记 "[cite: doc#47]";说明文字 "附带来源引用"。

围绕 (2)-(3) 的虚线框标注 "离线 — 仅构建一次"。围绕 (4)-(5) 的虚线框标注 "在线 — 每次查询"。

标题:"检索增强生成流水线"。副标题:"Lewis et al., 2020"。

溯源

原作者
wuyoscar
收录来源