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

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Our attempt to reduce the boring 40–60% of AI engineering

Our attempt to reduce the boring 40–60% of AI engineering

2
Comments 3
2 min read
Engineers who explore build better AI products

Engineers who explore build better AI products

2
Comments
2 min read
A Complete Architecture Guide for RAG + Agent Systems

A Complete Architecture Guide for RAG + Agent Systems

2
Comments 2
2 min read
Building an AI-Powered Log Analyser with RAG

Building an AI-Powered Log Analyser with RAG

Comments
6 min read
How to Evaluate Your RAG System: A Complete Guide to Metrics, Methods, and Best Practices

How to Evaluate Your RAG System: A Complete Guide to Metrics, Methods, and Best Practices

2
Comments
18 min read
Gemini 3 is Now Available as an OCR Model in Tensorlake

Gemini 3 is Now Available as an OCR Model in Tensorlake

78
Comments 3
4 min read
Verification Nodes: The Difference Between Playable and Production Agents

Verification Nodes: The Difference Between Playable and Production Agents

1
Comments 4
2 min read
đź§ Maybe I Just Do Not Get It!

đź§ Maybe I Just Do Not Get It!

50
Comments 19
12 min read
Prompt Systems > Prompt Engineering: The Enterprise Shift in 2026

Prompt Systems > Prompt Engineering: The Enterprise Shift in 2026

Comments 1
4 min read
[Update] VAC: A Memory Layer That Makes LLMs Remember You

[Update] VAC: A Memory Layer That Makes LLMs Remember You

Comments 1
3 min read
Por Qué el 83% de Herramientas de Detección de Alucinaciones RAG Fallan en Producción

Por Qué el 83% de Herramientas de Detección de Alucinaciones RAG Fallan en Producción

Comments
3 min read
AWS Knowledge Bases: Building Intelligent, Context-Aware Applications at Scale

AWS Knowledge Bases: Building Intelligent, Context-Aware Applications at Scale

Comments
3 min read
How S3 Vectors Work: A Friendly Guide to AWS’s New Vector Store

How S3 Vectors Work: A Friendly Guide to AWS’s New Vector Store

5
Comments 1
5 min read
Choosing the Right Chunking Strategy: A Comprehensive Guide to RAG Optimization

Choosing the Right Chunking Strategy: A Comprehensive Guide to RAG Optimization

9
Comments
10 min read
Kreuzberg v4.0.0-RC.8 is Available

Kreuzberg v4.0.0-RC.8 is Available

1
Comments
8 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.