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.
Day 8 - Sparse embedding - RAG

Day 8 - Sparse embedding - RAG

Comments
2 min read
RAG Is Not Always the Answer Anymore: How AI Agents Search Code in 2026

RAG Is Not Always the Answer Anymore: How AI Agents Search Code in 2026

5
Comments
6 min read
I built a local-first movie recommender with Corrective-RAG (cited explanations, hybrid retrieval, runs entirely on Ollama)

I built a local-first movie recommender with Corrective-RAG (cited explanations, hybrid retrieval, runs entirely on Ollama)

Comments
1 min read
My RAG system slowly got worse for three months and nobody noticed.

My RAG system slowly got worse for three months and nobody noticed.

Comments
4 min read
Scaling RAG for 10M+ Docs, .md Agent Memory, & Claude Code for Motion Graphics

Scaling RAG for 10M+ Docs, .md Agent Memory, & Claude Code for Motion Graphics

Comments
3 min read
I built a token-level debugger for comparing two LLMs

I built a token-level debugger for comparing two LLMs

Comments
1 min read
NyayAI: Building an AI Legal Assistant for 1.4 Billion People — A Technical Deep Dive

NyayAI: Building an AI Legal Assistant for 1.4 Billion People — A Technical Deep Dive

1
Comments
21 min read
The Hidden Problem With Long-Running AI Agents Nobody Talks About

The Hidden Problem With Long-Running AI Agents Nobody Talks About

Comments
3 min read
What I Learned About Memory-Augmented AI Agents

What I Learned About Memory-Augmented AI Agents

2
Comments
4 min read
# Arquitetando RAG Multi-Agente em Produção na AWS — Do Conceito à Operação

# Arquitetando RAG Multi-Agente em Produção na AWS — Do Conceito à Operação

Comments
13 min read
What Actually Helped Our Talk-to-DB Agent Stop Relearning the Same SQL

What Actually Helped Our Talk-to-DB Agent Stop Relearning the Same SQL

Comments
1 min read
Revisiting My Phone AI After Gemma 4: The Upgrade I Didn't Know I Needed

Revisiting My Phone AI After Gemma 4: The Upgrade I Didn't Know I Needed

Comments
4 min read
NyayAI: AI-Powered Legal Intelligence for India

NyayAI: AI-Powered Legal Intelligence for India

Comments
13 min read
Hybrid Search in RAG: Why Neither Keyword Search Nor Semantic Search Alone Is Good Enough

Hybrid Search in RAG: Why Neither Keyword Search Nor Semantic Search Alone Is Good Enough

Comments
13 min read
Building a RAG Document Q&A System with Hybrid Retrieval (No Embeddings API Needed)

Building a RAG Document Q&A System with Hybrid Retrieval (No Embeddings API Needed)

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