RAG & Search
Embedding model
A model that converts text, images, or other data into embeddings.
Example
One model converts every handbook passage and each new question into comparable vectors.
Why it matters
It supplies the comparisons needed to organize or search large collections by similarity.
You'll hear it
“We changed the embedding model, so the stored documents need updating.”
Can you control it?
Set by the team
The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.
Common questions
- Does the best model for one language suit every language?
- No. Teaching material and design can make performance uneven across languages and subjects.
- Can a writing model automatically substitute for it?
- Not necessarily. Producing text and producing useful numerical descriptions are different capabilities.
- Can switching versions change search results?
- Yes. Different descriptions can alter which items appear closest to a question.