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.
A Cognitive Benchmark for Code-RAG Retrieval: Part 2 — Why Model Rankings Depend on the Pipeline

A Cognitive Benchmark for Code-RAG Retrieval: Part 2 — Why Model Rankings Depend on the Pipeline

Comments
15 min read
The most underrated feature in a website AI assistant: saying "I don't know"

The most underrated feature in a website AI assistant: saying "I don't know"

Comments
2 min read
Portfolio de IA open source: 20+ proyectos con LLMs self-hosted en producción

Portfolio de IA open source: 20+ proyectos con LLMs self-hosted en producción

Comments
3 min read
Book Library: A Local RAG That Answers From My Own PDFs

Book Library: A Local RAG That Answers From My Own PDFs

Comments
5 min read
Build a Local RAG AI App with Ollama, Mistral, and Node.js

Build a Local RAG AI App with Ollama, Mistral, and Node.js

Comments
7 min read
Your AI Agent's Memory Has No Expiry Date: I Scored Freshness on a Real Corpus

Your AI Agent's Memory Has No Expiry Date: I Scored Freshness on a Real Corpus

Comments
14 min read
I Built 'Chat With Your Docs' From Scratch — Supabase + pgvector + a Free Local Embedder

I Built 'Chat With Your Docs' From Scratch — Supabase + pgvector + a Free Local Embedder

Comments
2 min read
Optimizing RAG Pipelines, Migrating AI Agents, and LLM-Powered Troubleshooting

Optimizing RAG Pipelines, Migrating AI Agents, and LLM-Powered Troubleshooting

Comments
3 min read
Two Pre-Registered Benchmarks for Audit-Native RAG: RAB (EU AI Act 10/12/19) + LRB (Time-Travel Retrieval)

Two Pre-Registered Benchmarks for Audit-Native RAG: RAB (EU AI Act 10/12/19) + LRB (Time-Travel Retrieval)

Comments
3 min read
Most RAG Problems Are Retrieval Problems. Here Are 8 Fixes That Worked for Me

Most RAG Problems Are Retrieval Problems. Here Are 8 Fixes That Worked for Me

Comments
4 min read
Building Modular AI Agent Features with Pydantic AI Capabilities

Building Modular AI Agent Features with Pydantic AI Capabilities

Comments
2 min read
A Chinese 8B model beat the Western 8B models at Japanese RAG. I still wouldn't put it in the default deployment — and that distinction is the point.

A Chinese 8B model beat the Western 8B models at Japanese RAG. I still wouldn't put it in the default deployment — and that distinction is the point.

Comments
4 min read
RAG should never be your default

RAG should never be your default

Comments
3 min read
Define the state of our agent

Define the state of our agent

Comments 1
6 min read
Query Rewriting Before Retrieval: The Cheap Recall Win Most Skip

Query Rewriting Before Retrieval: The Cheap Recall Win Most Skip

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