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.
Why we stopped stitching SQL + vector databases for AI apps - Answer is sochDB

Why we stopped stitching SQL + vector databases for AI apps - Answer is sochDB

1
Comments 1
3 min read
An Introduction to Retrieval Augmented Generation (RAG)

An Introduction to Retrieval Augmented Generation (RAG)

Comments
2 min read
I Built a RAG-Powered “Second Brain” and Accidentally Created My Personal Research Assistant

I Built a RAG-Powered “Second Brain” and Accidentally Created My Personal Research Assistant

Comments
13 min read
How RAG Changed the Way We Use Large Language Models

How RAG Changed the Way We Use Large Language Models

8
Comments 2
5 min read
RAG Doesn’t Make LLMs Smarter, This Architecture Does

RAG Doesn’t Make LLMs Smarter, This Architecture Does

Comments
4 min read
We won a Hackathon at Brown University 🏆

We won a Hackathon at Brown University 🏆

2
Comments
5 min read
How to Build a Text-to-SQL Agent With RAG, LLMs, and SQL Guards

How to Build a Text-to-SQL Agent With RAG, LLMs, and SQL Guards

Comments
7 min read
Converting Text Documents into Enterprise Ready Knowledge Graphs

Converting Text Documents into Enterprise Ready Knowledge Graphs

Comments
5 min read
Key Benefits of RAG as a Service for Enterprise AI Applications

Key Benefits of RAG as a Service for Enterprise AI Applications

Comments
6 min read
The Thinking Machines: How AI Learned to Reason Step-by-Step

The Thinking Machines: How AI Learned to Reason Step-by-Step

Comments 2
8 min read
RAG Is Easy. Your Data Isn't. Why AI Projects Fail

RAG Is Easy. Your Data Isn't. Why AI Projects Fail

Comments 1
5 min read
Stop Tuning Embeddings: Package Your Knowledge for Retrieval

Stop Tuning Embeddings: Package Your Knowledge for Retrieval

Comments
4 min read
Designing RAG Pipelines That Survive Production Traffic

Designing RAG Pipelines That Survive Production Traffic

Comments
3 min read
Vectors vs. Keywords: Why "Close Enough" is Dangerous in MedTech RAG

Vectors vs. Keywords: Why "Close Enough" is Dangerous in MedTech RAG

Comments
3 min read
You Don’t Need a Vector Database to Build RAG (Yet): A ~$1/Month DynamoDB Pipeline

You Don’t Need a Vector Database to Build RAG (Yet): A ~$1/Month DynamoDB Pipeline

1
Comments
10 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.