Files
nexus/wiki/sources/rag-cong-ru-men-dao-jing-tong.md

43 lines
1.4 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
title: "RAG从入门到精通系列1基础RAG"
type: source
tags: [rag, LLM, retrieval, vector-database]
date: 2025-12-18
---
## Source File
- [[raw/AI/RAG从入门到精通系列1基础RAG.md]]
## Summary
- 核心主题RAG基础概念和实现流程
- 问题域LLM缺乏最新和私有数据
- 方法/机制:索引→检索→生成的三步流程
- 结论/价值RAG是连接LLM与外部数据源的通用方法
## Key Claims
- RAG = Retrieval Augmented Generation检索增强生成
- Indexing将文档切分并转换为Embedding向量存入向量数据库
- Retrieval根据问题语义向量检索相关文档块
- Generation将问题和相关文档输入LLM生成答案
- Embedding Model的Context Window有限512-8192 token需切分文档
## Key Concepts
- [[RAG]]:检索增强生成
- [[Embedding]]:将文本转换为数值向量的技术
- [[向量数据库]]:存储和检索向量表示的数据库
- [[文档切分]]将长文档分割成符合Embedding窗口的块
- [[Context Window]]:模型能接受的上下文长度限制
## Key Entities
- [[LangChain]]RAG实现框架
- [[Qdrant]]:向量数据库
- [[BAAI]]Embedding模型提供商
## Connections
- [[LLM]] ← uses ← [[RAG]]
- [[RAG]] ← includes ← [[索引]]
- [[RAG]] ← includes ← [[检索]]
- [[RAG]] ← includes ← [[生成]]
## Contradictions