Embeddings and similarity
Comes up in: AI engineering
This concept is being written. It gets the full five steps — explanation, predict, interview angle, practice with tests, and review cards. Here is exactly what it will cover, so you can study it elsewhere in the meantime.
What it covers
- what an embedding vector is
- cosine similarity
- semantic search
- embedding models are separate from chat models
- dimensions and cost
- limits (negation, numbers)
Words you will know
What you will practise
- semantic search over 200 FAQs in the browser
Interview questions this answers
- What is an embedding and how is it used in search?