core practice · implementation task
Embed a corpus and search it
Embed a small corpus with an embedding model, embed a query, and return the nearest documents by cosine similarity.
The mechanism
An embedding model projects content into a space where 'close' means 'semantically similar'. Search becomes geometry: find the nearest vectors to the query vector.
Expected evidence
Semantically relevant documents for a query that shares no exact keywords.
Try this drill in the practice workspace →
Hints when you need them
- Normalize vectors before cosine.
- Use the same model for corpus and query.
Watch for these mistakes
- Comparing vectors from two different embedding models
- Forgetting to normalize when using cosine similarity
- Ignoring the model's max input length and silently truncating