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.
I made a fast, structured PDF extractor for RAG; 300 pages a second

I made a fast, structured PDF extractor for RAG; 300 pages a second

Comments
3 min read
Building a RAG-Powered Documentation Assistant: Why I Used Bifrost LLM Gateway Instead of Direct API Calls

Building a RAG-Powered Documentation Assistant: Why I Used Bifrost LLM Gateway Instead of Direct API Calls

6
Comments
5 min read
Beyond RAG: Building an Autonomous "Epistemic Engine" to Fight AI Hallucination

Beyond RAG: Building an Autonomous "Epistemic Engine" to Fight AI Hallucination

Comments
2 min read
Humans, Machines, and Ratatouille 🐀

Humans, Machines, and Ratatouille 🐀

Comments 1
3 min read
Stop feeding garbage to your LLM: How to get clean Markdown from Documentation

Stop feeding garbage to your LLM: How to get clean Markdown from Documentation

Comments
1 min read
RAG-Augmented Agile Story Generation: An Architectural Framework for LLM-Powered Backlog Automation

RAG-Augmented Agile Story Generation: An Architectural Framework for LLM-Powered Backlog Automation

Comments
8 min read
Building a Simple RAG System Using FAISS

Building a Simple RAG System Using FAISS

1
Comments
3 min read
Why Memory Architecture Matters More Than Your Model

Why Memory Architecture Matters More Than Your Model

1
Comments
2 min read
Building a Local RAG AI Agent for Airline Reviews with Ollama

Building a Local RAG AI Agent for Airline Reviews with Ollama

2
Comments
3 min read
Reranking and Two-Stage Retrieval: Precision When It Matters Most

Reranking and Two-Stage Retrieval: Precision When It Matters Most

Comments
2 min read
Python] Build a Smart Document Assistant LINE Bot with Python + Gemini File Search: Let AI Help You Read Documents

Python] Build a Smart Document Assistant LINE Bot with Python + Gemini File Search: Let AI Help You Read Documents

7
Comments
9 min read
LLMs Hallucinate. RAG Fixes That — Here’s How We Built a Reliable Healthcare AI

LLMs Hallucinate. RAG Fixes That — Here’s How We Built a Reliable Healthcare AI

Comments
3 min read
Multi-Tenant Design for Bedrock Knowledge Base: Solving the Account Limit with Metadata Filtering

Multi-Tenant Design for Bedrock Knowledge Base: Solving the Account Limit with Metadata Filtering

2
Comments
3 min read
I Built a TUI to Visualize RAG Chunking because chunk_size=1000 is a Lie 📉

I Built a TUI to Visualize RAG Chunking because chunk_size=1000 is a Lie 📉

Comments
3 min read
Introducing Agentic Chart Extraction

Introducing Agentic Chart Extraction

141
Comments 3
6 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.