05
Embeddings
How text becomes numbers, what that misses, and how to choose and change a model.
Concept 5.1
Embeddings and similarity from first principles
How a model turns text into a list of numbers, why close numbers mean close meaning, and how cosine similarity ranks chunks, measured on our 34 chunks.
Concept 5.2
What embeddings cannot do
Embeddings blur negation, numbers and codes, and an English model barely links Dutch to English. Measured sentence pairs show where, and what to add.
Concept 5.3
Choosing an embedding model: size, cost, language
Four open models scored on our own 47 questions and 8 Dutch translations. The largest came last, the multilingual one came first, and the leaderboard would not have told us.
Concept 5.4
Embedding model migration and index rebuilds
Changing the embedding model means re-embedding everything. We mixed an old index with a new query model of the same size; recall fell from 44 to 28 of 47 without a single error.
Chapter 5 recap