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.
Why Your Embedding Model Choice Matters More Than Your LLM Choice

Why Your Embedding Model Choice Matters More Than Your LLM Choice

Comments
5 min read
From 10% to 57% Accuracy on FinanceBench: What Actually Moved the Needle

From 10% to 57% Accuracy on FinanceBench: What Actually Moved the Needle

Comments
4 min read
Eidetic OS — How I Built a Personal AI Operating System That Never Forgets

Eidetic OS — How I Built a Personal AI Operating System That Never Forgets

1
Comments
9 min read
LLM 파인튜닝 방법 비교: Full vs LoRA vs QLoRA 선택 가이드 2026

LLM 파인튜닝 방법 비교: Full vs LoRA vs QLoRA 선택 가이드 2026

Comments
1 min read
RAG from Scratch with ChromaDB (No LangChain Required)

RAG from Scratch with ChromaDB (No LangChain Required)

2
Comments
4 min read
RAG Evaluation Checklist for AI SaaS: Catch Bad Answers Before Users Do

RAG Evaluation Checklist for AI SaaS: Catch Bad Answers Before Users Do

Comments
10 min read
What Happens When Your Vector Database Reaches 100 Million Chunks

What Happens When Your Vector Database Reaches 100 Million Chunks

Comments
3 min read
How AI agencies can scope automation and RAG projects before build time disappears

How AI agencies can scope automation and RAG projects before build time disappears

Comments
2 min read
The Second Brain They Can’t Subpoena: Local RAG on a Pi 5

Discoverable embeddings and chunking hurdles

The Second Brain They Can’t Subpoena: Local RAG on a Pi 5

7
Comments 4
9 min read
RAG pilots fail when the sources are not ready

RAG pilots fail when the sources are not ready

Comments
2 min read
# Enterprise RAG’s Biggest Risk: Answers That Look Correct but Aren’t

# Enterprise RAG’s Biggest Risk: Answers That Look Correct but Aren’t

Comments
7 min read
RAG reranking for production agents: four approaches, four failure modes

RAG reranking for production agents: four approaches, four failure modes

Comments
11 min read
Building a Four-Tier Parallel RAG Pipeline with Gemini

Building a Four-Tier Parallel RAG Pipeline with Gemini

2
Comments 4
2 min read
I Work in Healthcare Tech. Here's Why I Built a RAG Tool for Clinical Documents.

I Work in Healthcare Tech. Here's Why I Built a RAG Tool for Clinical Documents.

Comments
5 min read
Building a persistent AI business assistant with LangChain, FastAPI, and Redis

Building a persistent AI business assistant with LangChain, FastAPI, and Redis

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