Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

Unverified70% confidenceOpinionExact time

CLAUDE.md 的 @ 引用语法类似于 RAG（检索增强生成）技术的核心理念，在正确的时机提供正确的信息以控制 Token 消耗

1

Sources

70%

Confidence

Long-term

Relevance

5/30/2026

First Seen

Sources

CLAUDE.md配置指南：六段式结构写好项目说明书

bilibili路过的阿诚5/30/2026

Related Entities

CLAUDE.mdproduct RAGconcept

Related Claims

VerifiedRAG的核心逻辑是将文档切片后向量化存储，查询时通过语义相似度检索相关片段注入上下文68% similar UnverifiedRAG 是按需动态检索，references 是预置精选文档库，后者在专有领域场景下往往能提供更高的执行稳定性68% similar UnverifiedRAG（检索增强生成）由Lewis等人于2020年提出，核心思想是将参数化知识与非参数化知识解耦，推理时动态召回相关文档拼接进提示词68% similar UnverifiedRAG通过在生成前用语义检索召回相关评论作为上下文，可对安全关键语义设置更高召回权重68% similar Unverifiedreferences 文件夹本质上是 RAG（检索增强生成）思想的一种静态化实现67% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/493

API

curl https://kongchang.com/api/v1/knowledge/claims/493

MCP

get_claim(id=493)