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.
Corrective RAG for billing: the bug is not retrieval, it's the model narrating correct numbers wrong

Corrective RAG for billing: the bug is not retrieval, it's the model narrating correct numbers wrong

1
Comments 2
8 min read
Stop Making Your AI Agent Smarter. Make Its Context Smaller.

Stop Making Your AI Agent Smarter. Make Its Context Smaller.

Comments
3 min read
Building an LLM Gateway Proxy with Security Guardrails and Observability

Building an LLM Gateway Proxy with Security Guardrails and Observability

Comments
5 min read
How I Cut 30% LLM Costs: RAG Context Pruning Cost Reduction

How I Cut 30% LLM Costs: RAG Context Pruning Cost Reduction

Comments
10 min read
Building an AI-native Second Brain with Multi-RAG, Knowledge Graphs, and MCP

Building an AI-native Second Brain with Multi-RAG, Knowledge Graphs, and MCP

16
Comments 14
5 min read
The memory layer that never calls an LLM: what that buys, and what it costs

Raw turns beat LLM cost via auditability

The memory layer that never calls an LLM: what that buys, and what it costs

20
Comments 30
10 min read
Retrieval-Augmented Generation (RAG): Stop Your AI from Hallucinating

Retrieval-Augmented Generation (RAG): Stop Your AI from Hallucinating

1
Comments 2
3 min read
Candidate Compliance Agent: Building a Multilingual RAG System for Tamil Nadu Election Affidavits

Candidate Compliance Agent: Building a Multilingual RAG System for Tamil Nadu Election Affidavits

1
Comments
4 min read
Where Does RAG Actually Cost You Money? (Episode 6)

Where Does RAG Actually Cost You Money? (Episode 6)

7
Comments 1
7 min read
AI Agents Address Hallucinations; New Tools for Code Gen & Enterprise Auth

AI Agents Address Hallucinations; New Tools for Code Gen & Enterprise Auth

Comments
3 min read
RAG Chunking Strategies That Survive Production: Beyond the 512-Token Default

RAG Chunking Strategies That Survive Production: Beyond the 512-Token Default

19
Comments 4
10 min read
Context Compression: Fitting More Useful Information Into Your LLM's Context Window

Context Compression: Fitting More Useful Information Into Your LLM's Context Window

Comments
5 min read
I Deployed a Full RAG Backend for ₹0/Month — Here Are the 3 Walls I Hit

I Deployed a Full RAG Backend for ₹0/Month — Here Are the 3 Walls I Hit

6
Comments 3
10 min read
Reranking in Enterprise RAG: Why It Matters More Than Your Embedding Model Choice

Reranking in Enterprise RAG: Why It Matters More Than Your Embedding Model Choice

Comments
6 min read
Local-First RAG Pipeline in Pure Python

Local-First RAG Pipeline in Pure Python

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