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.
Tokenizer-Aware Markdown Chunking That Doesn't Shred Tables

Tokenizer-Aware Markdown Chunking That Doesn't Shred Tables

Comments
7 min read
Taming the Colab beast for a RAG pipeline

Taming the Colab beast for a RAG pipeline

Comments
2 min read
RAG’s dirty secret: data prep is the real fight

RAG’s dirty secret: data prep is the real fight

Comments
2 min read
The Reranker Setup That Actually Changes Recall@5

The Reranker Setup That Actually Changes Recall@5

Comments
6 min read
Hybrid Search in 100 Lines: BM25 + pgvector with RRF Merge

Hybrid Search in 100 Lines: BM25 + pgvector with RRF Merge

Comments
6 min read
5 Failure Modes I Found in My Financial RAG (And the One That Actually Mattered)

5 Failure Modes I Found in My Financial RAG (And the One That Actually Mattered)

2
Comments 8
5 min read
RAG Accessibility, AI Agent Security Testing, & Vector Search Optimization

RAG Accessibility, AI Agent Security Testing, & Vector Search Optimization

Comments
3 min read
Building MedAI — An AI-Powered Disease Prediction & Clinical Decision Support System

Building MedAI — An AI-Powered Disease Prediction & Clinical Decision Support System

Comments
9 min read
RAG Explained for Beginners: How AI Assistants Stop Making Things Up

RAG Explained for Beginners: How AI Assistants Stop Making Things Up

2
Comments 4
9 min read
0% vs 50%: Making a RAG Agent Refuse to Hallucinate

0% vs 50%: Making a RAG Agent Refuse to Hallucinate

Comments 1
2 min read
RAG - Hybrid search and RAG pipeline using FAISS DB

RAG - Hybrid search and RAG pipeline using FAISS DB

Comments
2 min read
The Ultimate Generative AI Roadmap (2026 Edition)

The Ultimate Generative AI Roadmap (2026 Edition)

Comments
2 min read
How RAGScope Knows Which Chunks Your LLM Actually Used

How RAGScope Knows Which Chunks Your LLM Actually Used

Comments 2
4 min read
Progressive Distillation

Progressive Distillation

2
Comments
4 min read
AI for Knowledge Management: Real Workflows That Hold Up

AI for Knowledge Management: Real Workflows That Hold Up

Comments
8 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.