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.
Demystifying the AI Jungle: Connecting the Dots

Demystifying the AI Jungle: Connecting the Dots

Comments
5 min read
Building QuantTrade AI: Where Wall Street Meets Machine Learning📈

Building QuantTrade AI: Where Wall Street Meets Machine Learning📈

1
Comments
4 min read
How a RAG Agent Helped My Father's Shoulder Treatment (And Saved ₹30,000).

How a RAG Agent Helped My Father's Shoulder Treatment (And Saved ₹30,000).

4
Comments
5 min read
Build a Scalable Multi-Agent RAG System with A2A Protocol, Oracle AI Database and LangChain

Build a Scalable Multi-Agent RAG System with A2A Protocol, Oracle AI Database and LangChain

Comments
7 min read
Designing RAG Pipelines That Survive Production Traffic

Designing RAG Pipelines That Survive Production Traffic

Comments
3 min read
The RAG System That Retrieved Perfect Chunks (But Answered Wrong Anyway)

The RAG System That Retrieved Perfect Chunks (But Answered Wrong Anyway)

Comments
4 min read
The RAG System That Mixed Documentation From Different Products (And Created Frankenstein Instructions)

The RAG System That Mixed Documentation From Different Products (And Created Frankenstein Instructions)

Comments
5 min read
Self-RAG vs Adaptive RAG vs Corrective RAG

Self-RAG vs Adaptive RAG vs Corrective RAG

Comments
3 min read
The RAG System That Found Contradicting Answers (And Confidently Picked The Wrong One)

The RAG System That Found Contradicting Answers (And Confidently Picked The Wrong One)

Comments
4 min read
Building an Autonomous RFP Response Engine with Python

Building an Autonomous RFP Response Engine with Python

Comments
5 min read
The Context Window Paradox: Why Bigger Isn't Always Better in AI

The Context Window Paradox: Why Bigger Isn't Always Better in AI

1
Comments
19 min read
OpenCode as a txtai LLM

OpenCode as a txtai LLM

1
Comments
3 min read
Safety boundaries for AI agents: stop sensitive actions + data leaks at the prompt layer

Safety boundaries for AI agents: stop sensitive actions + data leaks at the prompt layer

Comments
7 min read
The FAQ Bot That Made Up Answers When It Couldn’t Find Real Ones

The FAQ Bot That Made Up Answers When It Couldn’t Find Real Ones

Comments
4 min read
RAG Pipeline Deep Dive: Ingestion, Chunking, Embedding, and Vector Search

RAG Pipeline Deep Dive: Ingestion, Chunking, Embedding, and Vector Search

1
Comments
10 min read
Building a RAG Inside Discord? Clyde Meets Claude!

Building a RAG Inside Discord? Clyde Meets Claude!

Comments 1
3 min read
LangChain vs LangGraph vs Semantic Kernel vs Google AI ADK vs CrewAI

LangChain vs LangGraph vs Semantic Kernel vs Google AI ADK vs CrewAI

1
Comments
3 min read
Why Feature Stores Didn't Fix Training–Serving Skew

Why Feature Stores Didn't Fix Training–Serving Skew

1
Comments
4 min read
站內搜尋加上 AI:使用 Google Vertex AI Search(RAG)打造智慧問答型搜尋

站內搜尋加上 AI:使用 Google Vertex AI Search(RAG)打造智慧問答型搜尋

Comments
4 min read
The Quiet Rebellion: Waking Up Your AI

The Quiet Rebellion: Waking Up Your AI

Comments
3 min read
OCI Generative AI and LangChain: Building Enterprise AI Applications with Oracle

OCI Generative AI and LangChain: Building Enterprise AI Applications with Oracle

Comments
9 min read
TalentArch-AI: Building an Architectural Talent Matching Agent

TalentArch-AI: Building an Architectural Talent Matching Agent

Comments
5 min read
Running a RAG Pipeline in a Production Full-Stack Application (Without a Vector Database)

Running a RAG Pipeline in a Production Full-Stack Application (Without a Vector Database)

Comments
6 min read
VaultGuard-AI: Building a Local-First Hybrid Search RAG for Private Equity Intelligence

VaultGuard-AI: Building a Local-First Hybrid Search RAG for Private Equity Intelligence

Comments
5 min read
The Knowledge Base That Lied to 10,000 Customers (And How We Caught It)

The Knowledge Base That Lied to 10,000 Customers (And How We Caught It)

Comments
6 min read
loading...