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.
PolicyMind AI: Intelligent Insurance Document Assistant using Gemma 4

Gemma 4 Challenge: Build With Gemma 4 Submission

PolicyMind AI: Intelligent Insurance Document Assistant using Gemma 4

1
Comments
4 min read
How to stop your RAG assistant from hallucinating (a practical guide)

How to stop your RAG assistant from hallucinating (a practical guide)

Comments 2
3 min read
RAG vs. Fine-Tuning vs. Prompting: 2026 Strategic Guide

RAG vs. Fine-Tuning vs. Prompting: 2026 Strategic Guide

Comments
4 min read
How to Handle Proprietary Jargon in LLM-as-a-Judge Evaluations

How to Handle Proprietary Jargon in LLM-as-a-Judge Evaluations

Comments
4 min read
I Built a Local-First AI Desktop Knowledge Base — Here's What I Learned

I Built a Local-First AI Desktop Knowledge Base — Here's What I Learned

Comments 2
6 min read
Part 4: Improving Retrieval Quality with Token-Aware Chunking and HyDE

Part 4: Improving Retrieval Quality with Token-Aware Chunking and HyDE

Comments
4 min read
Governance First RAG

Governance First RAG

Comments
2 min read
Applied AI Workflows: Claude Haiku Database, Code Gen Tips, & Data Pipelines

Applied AI Workflows: Claude Haiku Database, Code Gen Tips, & Data Pipelines

Comments
3 min read
Extract Plain Text from Medium Posts for RAG and Search Indexes

Extract Plain Text from Medium Posts for RAG and Search Indexes

1
Comments
2 min read
Plexus: A WiFi Graph RAG for Network Troubleshooting

Plexus: A WiFi Graph RAG for Network Troubleshooting

Comments
9 min read
72% -> 75% -> 92%: a reproducible RAG validation

72% -> 75% -> 92%: a reproducible RAG validation

Comments 3
12 min read
My RAG app confidently told my client the wrong answer. I spent 3 days debugging the wrong thing.

My RAG app confidently told my client the wrong answer. I spent 3 days debugging the wrong thing.

3
Comments
4 min read
Why output-stage PII masking is the wrong protective surface for data exfiltration in RAG

Why output-stage PII masking is the wrong protective surface for data exfiltration in RAG

Comments 2
8 min read
TinySearch: Let Small Local LLMs Search the Web Without Burning Context

TinySearch: Let Small Local LLMs Search the Web Without Burning Context

1
Comments 1
5 min read
Everyone’s Building AI Agents. Here’s the One I Built for Myself

Everyone’s Building AI Agents. Here’s the One I Built for Myself

2
Comments 1
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.