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 Made Simple: Demonstration and Analysis of Simplicity (Part 3)

RAG Made Simple: Demonstration and Analysis of Simplicity (Part 3)

Comments 3
2 min read
RAG Made Simple: Technical Design and Architecture of Simplicity (Part 2)

RAG Made Simple: Technical Design and Architecture of Simplicity (Part 2)

Comments 2
3 min read
VLM Pipeline with Docling

VLM Pipeline with Docling

Comments
7 min read
Built an AI Assistant to Summarize and Query My Emails – Seeking Feedback

Built an AI Assistant to Summarize and Query My Emails – Seeking Feedback

Comments
1 min read
Cosine Similarity in Vector Databases: Why It Matters for GenAI & RAG Systems

Cosine Similarity in Vector Databases: Why It Matters for GenAI & RAG Systems

Comments
2 min read
Getting Started with LangChain: Build Smarter AI Apps with LLMs

Getting Started with LangChain: Build Smarter AI Apps with LLMs

6
Comments
3 min read
🤖 Retrieval-Augmented Generation (RAG): The Future of AI Search

🤖 Retrieval-Augmented Generation (RAG): The Future of AI Search

3
Comments
2 min read
RAG na prática: transformando PDFs em respostas inteligentes com LLMs

RAG na prática: transformando PDFs em respostas inteligentes com LLMs

2
Comments 2
6 min read
Hallucinations and AI: Scary or Not?

Hallucinations and AI: Scary or Not?

Comments
2 min read
Enhancing AI retrieval with HNSW in RAG applications

Enhancing AI retrieval with HNSW in RAG applications

Comments
2 min read
Taming Complex Codebases with AI: Your Thoughts?

Taming Complex Codebases with AI: Your Thoughts?

Comments
2 min read
Enhancing LLMs with Retrieval-Augmented Generation (RAG): A Practical Guide

Enhancing LLMs with Retrieval-Augmented Generation (RAG): A Practical Guide

Comments
4 min read
All Data and AI Weekly #188 - May 5, 2025

All Data and AI Weekly #188 - May 5, 2025

5
Comments
3 min read
Secrets Sprawl and AI: Why Your Non-Human Identities Need Attention Before You Deploy That LLM

Secrets Sprawl and AI: Why Your Non-Human Identities Need Attention Before You Deploy That LLM

Comments
6 min read
Enhancing RAG Precision Using Bedrock Metadata

Enhancing RAG Precision Using Bedrock Metadata

Comments 1
2 min read
Growing the Tree: Multi-Agent LLMs Meet RAG, Vector Search, and Goal-Oriented Thinking - Part 2

Growing the Tree: Multi-Agent LLMs Meet RAG, Vector Search, and Goal-Oriented Thinking - Part 2

Comments
10 min read
Building a CLI for Multi-Agent Tree-of-Thought: From Idea to Execution - Part 1

Building a CLI for Multi-Agent Tree-of-Thought: From Idea to Execution - Part 1

Comments
5 min read
LimeLight-An Autonomous Assistant for Enterprise Community Platforms Using RAG, LangChain, and LLaMA 3

LimeLight-An Autonomous Assistant for Enterprise Community Platforms Using RAG, LangChain, and LLaMA 3

1
Comments 1
3 min read
Retrieval Technique Series-4.How Search Engines Generate Indexes for Trillions of Websites?

Retrieval Technique Series-4.How Search Engines Generate Indexes for Trillions of Websites?

2
Comments
5 min read
NVIDIA Agentic AI 전략

NVIDIA Agentic AI 전략

Comments
1 min read
How AI Understands Your Documents: The Secret Sauce of RAG

How AI Understands Your Documents: The Secret Sauce of RAG

Comments
2 min read
LangGraph + Graphiti + Long Term Memory = Powerful Agentic Memory

LangGraph + Graphiti + Long Term Memory = Powerful Agentic Memory

2
Comments 1
11 min read
Generative Engine Optimization (GEO): The New Frontier Beyond SEO

Generative Engine Optimization (GEO): The New Frontier Beyond SEO

5
Comments 2
3 min read
VectorRAG is naive, lacks domain awareness, and can’t handle full dataset retrieval

VectorRAG is naive, lacks domain awareness, and can’t handle full dataset retrieval

5
Comments
1 min read
Retrieval Metrics Demystified: From BM25 Baselines to EM@5 & Answer F1

Retrieval Metrics Demystified: From BM25 Baselines to EM@5 & Answer F1

Comments
4 min read
loading...