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.
GPT-4o API Costs Dropped 50% - How to Recalculate Your AI Budget

GPT-4o API Costs Dropped 50% - How to Recalculate Your AI Budget

Comments
2 min read
RAG Framework with the Infra Lens

RAG Framework with the Infra Lens

Comments
3 min read
A Token Budget is an Architectural Constraint

A Token Budget is an Architectural Constraint

1
Comments 5
6 min read
Your RAG Retrieved the Right Document — So Why Was the Answer Wrong?

Your RAG Retrieved the Right Document — So Why Was the Answer Wrong?

5
Comments 3
11 min read
Agentic RAG Is Powerful Until the Retrieval Loop Eats Your Budget

Agentic RAG Is Powerful Until the Retrieval Loop Eats Your Budget

5
Comments 4
12 min read
Base, Chat and Reasoning Models: How Are They Different?

Base, Chat and Reasoning Models: How Are They Different?

Comments 2
3 min read
RAG Hallucination Diagnosis: Evidence Gating Beats Embeddings for Ask-Your-Docs Chatbot Answers

RAG Hallucination Diagnosis: Evidence Gating Beats Embeddings for Ask-Your-Docs Chatbot Answers

Comments
7 min read
An LLM judge cannot be a build gate, and it is not about the cost

An LLM judge cannot be a build gate, and it is not about the cost

2
Comments 4
3 min read
What nDCG sees that precision and recall miss

What nDCG sees that precision and recall miss

Comments 5
3 min read
Your eval thresholds will not catch the regression, and here is the arithmetic

Your eval thresholds will not catch the regression, and here is the arithmetic

Comments
3 min read
I built a RAG evaluation tool that catches failures RAGAS misses

I built a RAG evaluation tool that catches failures RAGAS misses

Comments
2 min read
Vector Databases for Production RAG (2026): Pinecone vs Qdrant vs Milvus vs pgvector

Vector Databases for Production RAG (2026): Pinecone vs Qdrant vs Milvus vs pgvector

1
Comments 5
11 min read
RAG - Hallucination Detection

RAG - Hallucination Detection

Comments
2 min read
TrustGraph 2.8: Async Infrastructure, Hybrid Retrieval, Structured Output, and a Plugin-Based Workbench

TrustGraph 2.8: Async Infrastructure, Hybrid Retrieval, Structured Output, and a Plugin-Based Workbench

6
Comments
4 min read
Rebuilding the Cerebras Knowledge Base: Results Appendix (P1–P4)

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

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