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

👋 Sign in for the ability to sort posts by relevant, latest, or top.
RAG na Prática: Como Avaliar Retrieval Sem Virar "Achei Que Ficou Bom"
izaaccomze profile

RAG na Prática: Como Avaliar Retrieval Sem Virar "Achei Que Ficou Bom"

#ai #rag #retrieval #llm
Comments
5 min read
Using PixelRAG with Claude Code (August 2026) — Visual RAG for Documents with Tables and Diagrams
_02121fbe984480fd65fc profile

Using PixelRAG with Claude Code (August 2026) — Visual RAG for Documents with Tables and Diagrams

#claude #rag #python #ai
Comments
5 min read
When Everyone Has AI Agents, Who Knows What They’re Doing?
zhan1234 profile
Shan

When Everyone Has AI Agents, Who Knows What They’re Doing?

#ai #agents #rag
5
Comments
2 min read
SWE-bench moved 0 points and the model got dramatically better at my job
superstar0 profile

SWE-bench moved 0 points and the model got dramatically better at my job

#ai #opensource #programming #rag
1
Comments
4 min read
RAG Retrieval Architectures: When Better Embeddings Stop Helping
arvid_andersson_0a598fa45 profile

RAG Retrieval Architectures: When Better Embeddings Stop Helping

#rag #ai #machinelearning #python
Comments 1
7 min read
Agentic AI for Production Support: Moving from Alerts to Intelligent Incident Resolution
dev_hajare_d11ce990734a91 profile

Agentic AI for Production Support: Moving from Alerts to Intelligent Incident Resolution

#ai #llm #rag #agentaichallenge
Comments
2 min read
Rebuilding the Cerebras Knowledge Base: Results Appendix (P1–P4)
faridgnank02 profile

Rebuilding the Cerebras Knowledge Base: Results Appendix (P1–P4)

#ai #rag #vectordatabase #llm
Comments
4 min read
Turning Any Webpage into Clean, LLM-Ready Markdown for RAG Pipelines
josejux profile

Turning Any Webpage into Clean, LLM-Ready Markdown for RAG Pipelines

#ai #rag #llm #python
Comments
4 min read
Rebuilding the Cerebras Knowledge Base: adding hybrid search
faridgnank02 profile

Rebuilding the Cerebras Knowledge Base: adding hybrid search

#rag #vectordatabase #postgres #ai
Comments
6 min read
Rebuilding the Cerebras Knowledge Base: the naive vector baseline
faridgnank02 profile

Rebuilding the Cerebras Knowledge Base: the naive vector baseline

#rag #vectordatabase #postgres #ai
Comments
5 min read
Fine-tuning vs RAG vs prompting: pick the right lever
dev-into-space profile

Fine-tuning vs RAG vs prompting: pick the right lever

#ai #llm #rag #machinelearning
1
Comments
3 min read
Retrieval Is Not Memory
chillpill_ak profile

Retrieval Is Not Memory

#ai #rag #llm #architecture
Comments
1 min read
Quando o RAG erra, quase nunca é o LLM: 4 falhas de recuperação e como logar cada uma
wildrik profile

Quando o RAG erra, quase nunca é o LLM: 4 falhas de recuperação e como logar cada uma

#rag #ai #python #braziliandevs
Comments
3 min read
I built a RAG assistant, then found out my architecture change made it worse
saftyy profile

I built a RAG assistant, then found out my architecture change made it worse

#ai #machinelearning #rag #python
Comments 2
5 min read
Why Your LLM Costs Are Exploding (And the 6 Fixes Every Developer Misses)
nkumar profile

Why Your LLM Costs Are Exploding (And the 6 Fixes Every Developer Misses)

#ai #architecture #agents #rag
Comments
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.