What is the correct order of steps in a RAG pipeline?

Index → Retrieve → Generate. RAG first indexes documents into a vector store, then retrieves relevant chunks at query time, then passes them to the LLM to generate the final answer.

Which of the following is a core benefit of RAG over fine-tuning?

Knowledge can be updated without retraining. RAG stores knowledge externally in a vector database, so you can add, remove, or update documents without expensive model retraining.

What technology does RAG use to find relevant document chunks?

Vector similarity search. RAG converts both documents and queries into vector embeddings, then uses cosine or dot-product similarity to find the most semantically relevant chunks.

AI ArchitectureIntermediate

What is RAG (Retrieval-Augmented Generation)?

RAG combines a language model with a retrieval system, letting the AI search a knowledge base before answering — reducing hallucinations and keeping responses up to date.

TL;DR: RAG combines a language model with a retrieval system, letting the AI search a knowledge base before answering — reducing hallucinations and keeping responses up to date.

The Problem RAG Solves

Standard LLMs have a fixed training cutoff. Ask ChatGPT about last week's news and it either confabulates or says it doesn't know. RAG patches this by retrieving real documents at query time.

training cutoffconfabulationretrieval

How RAG Works (3 Steps)

1. Index: Documents are chunked and converted to vector embeddings stored in a vector database. 2. Retrieve: Your question is also embedded, and the nearest document chunks are fetched. 3. Generate: The LLM receives your question + the retrieved chunks as context and writes the answer.

vector embeddingsvector databasechunkscontext

RAG vs Fine-tuning

Fine-tuning bakes knowledge into model weights — expensive and static. RAG keeps knowledge external and updatable. Use RAG when your data changes frequently; fine-tune when you need a specific style or format the model must produce consistently.

fine-tuningmodel weightsstaticupdatable

Real-World RAG Examples

Perplexity.ai uses RAG to search the web before answering. GitHub Copilot Enterprise uses RAG over your company's private codebase. Notion AI uses RAG on your own workspace documents.

Deep Dive Articles

📖Chatgpt Plus Vs Claude Pro→📖Gemini 2 5 Pro Review→

Related Concepts

LLM Tokenization Explained

Fine-tuning vs Prompting — Which Should You Use?

AI Agent Architecture — How Autonomous AI Works

← Back to all topics