Zenaique
Concepts · RAG

Retrieval-Augmented Generation (RAG)

Also known as: Retrieval-Augmented Generation, Retrieval Augmented Generation

Fetch relevant docs at inference time and stuff them into the prompt so the model can answer from real data.

A pattern that augments an LLM with an external retrieval step: relevant documents are fetched from a knowledge base and injected into the prompt context, reducing hallucination and grounding responses in real data.

In practice

Default architecture for LLM apps that need fresh or domain-specific knowledge. Expect deep questions on chunking, retrieval quality, and the read-vs-write trade-off versus fine-tuning.

How it compares

vs. Fine-tuning →Deep comparison →

RAG injects context at inference time without changing weights; fine-tuning bakes knowledge into the weights.

Comparisons that include Retrieval-Augmented Generation (RAG)

Long context vs RAGLong context lets the model see everything; RAG selects what it should see. Long context is convenient but not free: cost scales, and quality falls off past the middle of the window.RAG vs Fine-tuningReach for RAG when knowledge changes or must be cited; fine-tune when you need the model to change how it behaves, not what it knows.

Related topics

Retrieval-Augmented Generation

151 questions

Context Engineering

104 questions

Vector Databases

83 questions

Practice questions

Related terms

AI System Design

End-to-end design of production LLM systems: ingestion, retrieval, serving, eval, monitoring.

BM25

Classical TF-IDF-style lexical scoring: a surprisingly strong baseline, still the first stage of many hybrid RAG pipelines.

Chunking

Cutting documents into retrievable pieces before embedding them.

Context Engineering

Deciding what makes it into the model's context window (prompt + RAG + history + memory), and why.

Context Rot

Long-running chats degrade: early instructions get forgotten, and tool calls become less reliable.

Context Window

The max number of tokens a model can attend to at once.