Phase 1 · Building with LLMs · Context & retrieval
Embeddings
Meaning as a list of numbers, so text can be compared.
Open this lesson Create a free account
Why it matters
Embeddings are how AI systems search by meaning instead of by keyword. They power "find similar products", grouping thousands of survey answers by theme, detecting duplicate leads, and, most importantly, retrieval-augmented generation (RAG): giving a model the right page of your own documents before it answers. Every lesson in the next part of this phase builds on them.
What you'll be able to do
- Explain what an embedding is and why similar meanings get similar vectors
- Request embeddings from an API and read the response
- Measure how similar two texts are with cosine similarity
- Name real embedding models and how they differ from chat models
Before this lesson
Next in this phase: Similarity search