RAG
Give the robot your notes before the exam.
▶ the lesson · ~35s · narrated · tap for sound
the intro
Retrieval-augmented generation grounds an LLM in your data: documents are split into chunks, embedded into vectors, and the chunks most similar to the question are handed to the model as context. It answers from your notes instead of its memory.
fun fact ✦
RAG is an open-book exam for AI: retrieval finds the page, the model writes the answer.
the docs
quick hits about RAG
15-second answers · interviews, tips, trivia & hidden gems
🎤 interview
What are embeddings?
📚 tutorial
What does a vector database do?
🔧 useful
Chunk size matters more than you think
🔧 useful
How many chunks should RAG retrieve?
💎 deep
Should RAG answers cite sources?
💎 deep
Vector search alone is not enough