What an embedding actually encodes
An embedding maps text to a point in space where nearby means related. It captures topic and usage, not truth, and definitely not recency.
- 9m
- Advanced
Video by IBM Technology · YouTube
Check your understanding
3 questions. Unlocks when you finish the video.
Overview
What this lesson covers
- Read an embedding as a position in semantic space
- Know what embeddings fail to capture
- Choose an embedding model for your content
This lesson sits in Embeddings and Vector Search, part of Retrieval-Augmented Generation from Scratch. It assumes what came before it and leads directly into the next lesson in the module.
In this lesson you will:
- Read an embedding as a position in semantic space
- Know what embeddings fail to capture
- Choose an embedding model for your content
Resources
Your notes will live here
Note taking is not available yet. Nothing you type would be saved, so the tab stays read-only for now.