Plus

This lesson is part of Plus

How to Implement Contextual Embeddings for RAG · RAG for Real-World AI Applications

Lesson 28 of 30 in RAG for Real-World AI Applications. Plus opens every course and every lesson, and new ones as they ship.

Price
$219/year
Refund
30 days

How to Implement Contextual Embeddings for RAG

In this lesson, learn how to generate contextual embeddings for improved retrieval in RAG pipelines. Contextual retrieval situates document chunks within their documents context by using an LLM before the embedding step to generate a document summary prefix to the chunk.

The full notes, transcript and prompts open with Plus.

Keyboard shortcuts

SpaceK
Play or pause
JL
Back or forward 10 seconds
O
Outline
F
Fullscreen
ShiftN
Next lesson
?
This list

Shortcuts work while the video area has focus (click beside the video or tab to it), so they never clash with screen reader or speech input keys.

Single-key shortcuts