↑ BACK TO TOP
open sidebar menu
  • AI, it's not that complicated/The Generative AI wave
    Knowledge Bases
    Analyzing Software CompaniesBuilding Software ProductsAI, it's not that complicatedWorking With Data Teams
    Sections
    1: The Basics
    2: The Generative AI wave
    It was never about LLM performanceWhat is RAG?What's a vector database?How do AI models think and reason?How to build apps with AIWhat is MCP?What is Generative AI?The beginner’s guide to AI model architectures
    3: Tools and Products
Sign In

What is RAG?

Retrieval Augmented Generation is a way to make AI models more personalized

ai

Last updated: July 4, 2025

TL;DR

Retrieval Augmented Generation (RAG) is a way to make LLMs like GPT-4 more accurate and personalized to your specific data.

  • LLMs are powerful as hell, but they’re also generic: they’re trained on all data on the internet ever!
  • RAG helps you get more personalized responses tailored to your data by embedding your data in your model prompts
  • RAG relies on the model’s context window, which is how much data in can take in a prompt
  • Today’s RAG pipelines are pretty complex and rely on embedding models and vector databases

Alongside old school fine tuning, RAG is becoming the standard way to get better, more personalized results out of state of the art LLMs.

Terms Mentioned

ChatGPT

Database

Back to the future: training models

The funny thing about RAG is that the basic concept has been around for as long as machine learning has. Long time readers will recall that back in the day, I studied Data Science in undergrad. “Old School” machine learning, before everyone was calling it AI, was entirely predicated on training a new model for every problem.

How old school ML worked: custom models

Imagine you’re a Data Scientist tasked with understanding and predicting customer churn (your employer has a big churn problem). Your goal is to be able to predict a brand new customer’s chances of churning, so your marketing team can give them discounts and winback offers before they leave. Here’s what you might do:

Access the full post in a knowledge base

Knowledge bases give you everything you need – access to the right posts and a learning plan – to get up to speed on whatever your goal is.

Knowledge Base

AI, it's not that complicated

How to understand and work effectively with AI and ML models and products.

$0.00

What's a knowledge base? ↗

Where to next?

Keep learning how to understand and work effectively with AI and ML models and products.

What's a vector database?

A vector database is a place where developers store specially formatted data to use for machine learning and AI.

The Generative AI wave
How do AI models think and reason?

All about "reasoning" language models like OpenAI's o3 and Deepseek's R1.

The Generative AI wave
How to build apps with AI

All about Vercel’s v0

The Generative AI wave
Support
Sponsorships
Twitter
Linkedin
Privacy + ToS