A simple explanation of how AI models can 'look up' information they weren't trained on, like an open-book test.
To find the right page quickly, we use something called a Vector Database.
Think of it like a super-smart librarian. Instead of just looking for matching keywords (like "vacation"), it looks for meanings.
If you search for "time off," the librarian knows that means the same thing as "vacation" and finds the right document.
To make this work, we turn text into lists of numbers called Embeddings.
Imagine a giant map. Words with similar meanings are close together on the map. "Dog" is close to "Puppy". "Car" is far away.
The computer uses this map to find documents that are "close" to your question.