What is semantic search?

02 · See it in action

Follow the steps

1. Write ten realistic search queries and the expected useful documents.
2. Represent documents and queries with the same embedding model.
3. Apply access and category filters before returning results.
4. Measure how often a relevant document appears in the first three results.

Worked example

Query: "start learning agents without coding"
Relevant: beginner agent concepts
Less relevant: advanced distributed agent runtime
Metric: hit@3 = queries with a relevant top-3 result / all queries

Read the example once, then explain each part aloud in your own words. If it includes Python, you can understand the idea first and run the code later in a local Python environment. Code is shown as text; this page does not execute it.

Sign in to save your reading progress.