DEV Community

#rag

Retrieval augmented generation, or RAG, is an architectural approach that can improve the efficacy of large language model (LLM) applications by leveraging custom data.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
从 0 到 1 构建企业级 RAG 知识库:pgvector + 文档切片 + 混合检索

从 0 到 1 构建企业级 RAG 知识库:pgvector + 文档切片 + 混合检索

Comments
5 min read
Is Agent Memory Just RAG With Extra Steps? We Opened the Source Code to Find Out

Vendor codebase audit settles the RAG debate

Is Agent Memory Just RAG With Extra Steps? We Opened the Source Code to Find Out

6
Comments 14
6 min read
How AI Answer Engines Decide to Cite Your Pages

How AI Answer Engines Decide to Cite Your Pages

Comments
6 min read
Meet The Builder

Meet The Builder

1
Comments
4 min read
Your RAG system can't answer "why" questions. Here's what you're missing.

Your RAG system can't answer "why" questions. Here's what you're missing.

Comments
4 min read
How AI Stores Millions of Vectors Without Using Tons of Memory

How AI Stores Millions of Vectors Without Using Tons of Memory

12
Comments 2
4 min read
Engineers Don't Want to Push More Slop

Engineers Don't Want to Push More Slop

6
Comments 2
2 min read
AI Is Probabilistic. Enterprise Software Isn’t.

AI Is Probabilistic. Enterprise Software Isn’t.

Comments 2
14 min read
3 Free Tools Every AI Agent Developer Should Bookmark

3 Free Tools Every AI Agent Developer Should Bookmark

Comments
2 min read
I Almost Shipped a RAG Assistant That Lied About APIs That Don't Exist

Adversarial testing reveals RAG failure modes

I Almost Shipped a RAG Assistant That Lied About APIs That Don't Exist

20
Comments 28
8 min read
A local RAG retriever in pure Python — no vector DB, no API key (with Whoosh)

A local RAG retriever in pure Python — no vector DB, no API key (with Whoosh)

Comments 2
3 min read
ur rag can return 200 and still be cooked — how we built Goose on SigNoz

ur rag can return 200 and still be cooked — how we built Goose on SigNoz

Comments
5 min read
Evaluating Amazon Bedrock Knowledge Base RAG using LLM-as-a-Judge

Evaluating Amazon Bedrock Knowledge Base RAG using LLM-as-a-Judge

1
Comments 2
1 min read
Chat history is a second read path into your RAG data — gate the replay like the search

Treating chat history as a security surface

Chat history is a second read path into your RAG data — gate the replay like the search

19
Comments 15
6 min read
AICurt - A Lightweight Python Toolkit for Preparing Text Before AI Processing

AICurt - A Lightweight Python Toolkit for Preparing Text Before AI Processing

Comments
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.