What embeddings are
On This Lesson 4 topics
This lesson is planned. The outline below lists the topics it will cover. The full lesson has not been published yet.
In this lesson
explain that an embedding is a list of numbers that places a text at a point where similar meanings are close.
Planned topics
- An embedding model turns text into a vector: a fixed-length list of numbers (for example 768 or 1536 values; verify per model).
- Texts with similar meaning land near each other: "Where is my parcel?" is close to "Track an order".
- The vector has no readable parts; only distances between vectors carry meaning.
- Vectors from different models live in different spaces: never compare or mix them in one column.
- Embeddings capture meaning, not exact words: product codes and rare names can be missed.
Draft outline details
Demonstration
three phrases drawn as points on a 2D map: "return policy" and "refund a purchase" close together, "shipping to Riyadh" far away. Then a Spring AI EmbeddingModel call returning a float[] (verify the API before recording).
Check your understanding
Why can you not mix vectors from two models in one column?
Show answer
Each model has its own space, so distances between them are meaningless.
Practice
Apply this lesson with the module's lab, exercises and quiz.
Marking a lesson complete is optional and you can undo it any time. Your progress stays in this browser.