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.
What we learned from 100+ production RAG deployments (free 118-page handbook)

What we learned from 100+ production RAG deployments (free 118-page handbook)

Comments
1 min read
Building a Cloud-Native Agentic AI Research App: A Comprehensive Deep Dive into pgvector, Remix, and Multimodal LLMs

Building a Cloud-Native Agentic AI Research App: A Comprehensive Deep Dive into pgvector, Remix, and Multimodal LLMs

Comments
8 min read
Building an Enterprise RAG System: Lessons from Production with Turkish Documents

Building an Enterprise RAG System: Lessons from Production with Turkish Documents

Comments
3 min read
Monitor RAG Data Source Quality

Monitor RAG Data Source Quality

Comments
9 min read
Context Retrieval vs Context Demand: A Design Question in LLM System

Context Retrieval vs Context Demand: A Design Question in LLM System

Comments
3 min read
AI Agents Don’t Scale Like Chatbots

AI Agents Don’t Scale Like Chatbots

4
Comments 6
2 min read
I built a memory system that outperforms standard RAG on temporal queries -- try the live playground

I built a memory system that outperforms standard RAG on temporal queries -- try the live playground

Comments
1 min read
LLM Audit for Developers: A 30-Minute Self-Check Before You Tune That Prompt Again

LLM Audit for Developers: A 30-Minute Self-Check Before You Tune That Prompt Again

5
Comments
4 min read
How I ran LLM + RAG fully offline on Android using MNN

How I ran LLM + RAG fully offline on Android using MNN

Comments
3 min read
Build a RAG System from Scratch: Create an AI That Answers Questions About Your Codebase

Build a RAG System from Scratch: Create an AI That Answers Questions About Your Codebase

Comments
5 min read
Building a Production-Ready AI Customer Service Agent with HazelJS

Building a Production-Ready AI Customer Service Agent with HazelJS

1
Comments
7 min read
Docling Speaks LaTeX: Unlocking Academic and Scientific Documents

Docling Speaks LaTeX: Unlocking Academic and Scientific Documents

Comments
23 min read
Show DEV: PardusDB – The "SQLite of Vector DBs" written in Rust

Show DEV: PardusDB – The "SQLite of Vector DBs" written in Rust

5
Comments
1 min read
Chatting with 3 Billion Base Pairs: Building a RAG Index for Your Personal Genome (WGS)

Chatting with 3 Billion Base Pairs: Building a RAG Index for Your Personal Genome (WGS)

Comments
4 min read
Scaling RAG : Demo to Production Ready

Scaling RAG : Demo to Production Ready

Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.