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.
All Data and AI Weekly #184 - April 07, 2025

All Data and AI Weekly #184 - April 07, 2025

5
Comments
2 min read
Processing data with “Data Prep Kit” (part 2)

Processing data with “Data Prep Kit” (part 2)

Comments
8 min read
🚀 How I Boosted Slack RAG Accuracy by 5–6% with Smarter Chunking

🚀 How I Boosted Slack RAG Accuracy by 5–6% with Smarter Chunking

Comments
3 min read
Part 2: AI Agent Truly Intelligent?

Part 2: AI Agent Truly Intelligent?

Comments
2 min read
Crawling web sites using “Data Prep Kit”

Crawling web sites using “Data Prep Kit”

Comments
4 min read
Embeddings Demystified: Math, Meaning & Machines

Embeddings Demystified: Math, Meaning & Machines

Comments
3 min read
[Feedback wanted] Connect user data to AI with PersonalAgentKit for LangGraph

[Feedback wanted] Connect user data to AI with PersonalAgentKit for LangGraph

Comments
1 min read
Vector Database Indexing: A Comprehensive Guide

Vector Database Indexing: A Comprehensive Guide

Comments
7 min read
Building Custom Kendra Connectors and Managing Data Sources with IaC

Building Custom Kendra Connectors and Managing Data Sources with IaC

Comments
15 min read
Relevance Feedback in Informational Retrieval

Relevance Feedback in Informational Retrieval

6
Comments
11 min read
RAG Search with AWS Lambda and Bedrock

RAG Search with AWS Lambda and Bedrock

9
Comments 1
4 min read
Beyond the Black Box: Unpacking CoT, RAG, and RAT for Smarter AI

Beyond the Black Box: Unpacking CoT, RAG, and RAT for Smarter AI

Comments
3 min read
I Built an LLM Framework in just 100 Lines — Here is Why

I Built an LLM Framework in just 100 Lines — Here is Why

5
Comments
8 min read
Figure Export from Docling — Exporting PDF to image

Figure Export from Docling — Exporting PDF to image

1
Comments
3 min read
Vector Recall Reasoning

Vector Recall Reasoning

5
Comments
1 min read
🧭 Part 3: Implementing Vector Search with Pinecone

🧭 Part 3: Implementing Vector Search with Pinecone

Comments
2 min read
Building an E-Commerce Support Chatbot: Part 2 - Building the Knowledge Base

Building an E-Commerce Support Chatbot: Part 2 - Building the Knowledge Base

Comments
2 min read
An overview of rules based ingestion in DataBridge

An overview of rules based ingestion in DataBridge

1
Comments
6 min read
Integrating LlamaIndex and DeepSeek-R1 for reasoning_content and Function Call Features

Integrating LlamaIndex and DeepSeek-R1 for reasoning_content and Function Call Features

Comments
10 min read
Building a RAG System With Claude, PostgreSQL & Python on AWS

Building a RAG System With Claude, PostgreSQL & Python on AWS

Comments
9 min read
Google Vertex RAG Engine with C# .Net

Google Vertex RAG Engine with C# .Net

Comments
6 min read
Introduction to branched RAG

Introduction to branched RAG

2
Comments
3 min read
AI’s Hidden Superpower: Why Retrieval-Augmented Generation (RAG) is Game-Changing

AI’s Hidden Superpower: Why Retrieval-Augmented Generation (RAG) is Game-Changing

Comments
3 min read
Generic RAG Frameworks: Why They Can’t Catch On

Generic RAG Frameworks: Why They Can’t Catch On

17
Comments
5 min read
Nexus Search: RAG-Powered Semantic Search for HPKV

Nexus Search: RAG-Powered Semantic Search for HPKV

Comments
8 min read
loading...