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

๐Ÿ‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
LLM Wiki: I Set Up Karpathy's Local Knowledge Base โ€” Here's What Actually Works [2026 Guide]

LLM Wiki: I Set Up Karpathy's Local Knowledge Base โ€” Here's What Actually Works [2026 Guide]

1
Comments
7 min read
AI Home Lab โ€” Part 3: Building a RAG Pipeline: Making Your Local AI Actually Know Your Stuff

AI Home Lab โ€” Part 3: Building a RAG Pipeline: Making Your Local AI Actually Know Your Stuff

1
Comments
7 min read
Agent Tools

Agent Tools

2
Comments
86 min read
The 7 AI Agent Failures You'll Never See Coming Until They Hit Production

The 7 AI Agent Failures You'll Never See Coming Until They Hit Production

1
Comments
8 min read
๐Ÿš€ I Built an AI-Powered Fest Assistant with Agents, RAG & Planning (Pragyan @ NITT)

๐Ÿš€ I Built an AI-Powered Fest Assistant with Agents, RAG & Planning (Pragyan @ NITT)

6
Comments 4
3 min read
How to Reduce AI Hallucinations in Production: Grounding, RAG, and Guardrails That Actually Work

How to Reduce AI Hallucinations in Production: Grounding, RAG, and Guardrails That Actually Work

Comments
16 min read
๐Ÿง  From SQL to Intelligence: Why the Future of Data is AI + Graphs + Agents

๐Ÿง  From SQL to Intelligence: Why the Future of Data is AI + Graphs + Agents

Comments
3 min read
Building a RAG Pipeline on Your Existing Django App: A Practical Guide

Building a RAG Pipeline on Your Existing Django App: A Practical Guide

Comments
4 min read
๐ŸŽ™๏ธ Building a Local Voice-Controlled AI Agent

๐ŸŽ™๏ธ Building a Local Voice-Controlled AI Agent

2
Comments
11 min read
I Built a Personal AI That Actually Knows My Projects (RAG + Ollama, Zero Cloud)

I Built a Personal AI That Actually Knows My Projects (RAG + Ollama, Zero Cloud)

1
Comments
5 min read
๐—›๐—ผ๐˜„ ๐—œ ๐—•๐˜‚๐—ถ๐—น๐˜ ๐—ฎ ๐— ๐˜‚๐—น๐˜๐—ถ๐—น๐—ถ๐—ป๐—ด๐˜‚๐—ฎ๐—น ๐—ฅ๐—”๐—š ๐—ฆ๐˜†๐˜€๐˜๐—ฒ๐—บ ๐—ณ๐—ผ๐—ฟ ๐—จ๐—ป๐—ฑ๐—ฒ๐—ฟ $๐Ÿฌ.๐Ÿฌ๐Ÿฌ๐Ÿฌ๐Ÿฑ ๐—ฝ๐—ฒ๐—ฟ ๐—ค๐˜‚๐—ฒ๐˜€๐˜๐—ถ๐—ผ๐—ป

๐—›๐—ผ๐˜„ ๐—œ ๐—•๐˜‚๐—ถ๐—น๐˜ ๐—ฎ ๐— ๐˜‚๐—น๐˜๐—ถ๐—น๐—ถ๐—ป๐—ด๐˜‚๐—ฎ๐—น ๐—ฅ๐—”๐—š ๐—ฆ๐˜†๐˜€๐˜๐—ฒ๐—บ ๐—ณ๐—ผ๐—ฟ ๐—จ๐—ป๐—ฑ๐—ฒ๐—ฟ $๐Ÿฌ.๐Ÿฌ๐Ÿฌ๐Ÿฌ๐Ÿฑ ๐—ฝ๐—ฒ๐—ฟ ๐—ค๐˜‚๐—ฒ๐˜€๐˜๐—ถ๐—ผ๐—ป

1
Comments
1 min read
There Are Too Many RAG Optimization Techniques, So I Organized Them โ€” and the Big Picture Finally Made Sense

There Are Too Many RAG Optimization Techniques, So I Organized Them โ€” and the Big Picture Finally Made Sense

2
Comments
8 min read
Stop Blaming Your LLM: Fix RAG Retrieval Quality With Better Chunking in .NET

Stop Blaming Your LLM: Fix RAG Retrieval Quality With Better Chunking in .NET

1
Comments
7 min read
The Prep Tax: Why Miscommunicated Requirements Create Rework for AI Engineers (and How to Fix It)

The Prep Tax: Why Miscommunicated Requirements Create Rework for AI Engineers (and How to Fix It)

Comments
5 min read
We open-sourced Omega Walls: a stateful runtime defense for RAG and AI agents

We open-sourced Omega Walls: a stateful runtime defense for RAG and AI agents

4
Comments 2
2 min read
๐Ÿ‘‹ Sign in for the ability to sort posts by relevant, latest, or top.