Embeddings, an embedding model, and a vector database are enough for a demo. By themselves, they are rarely enough for a useful search product.

A user searches for “how to handle database connection timeouts”, and the top result is a section about HTTP request timeouts. It is related, but it is not what they were looking for. Another user searches for “Python list comprehension”, and the best match is a paragraph about Python decorators that happens to mention lists.

In both cases, the system finds something nearby, but it misses what the user actually needs.

The difference between "this is related" and "this answers the question" is where most retrieval engineering happens. You get there with better chunking, hybrid retrieval, reranking, useful metadata, and measurement.

That is what this chapter is about.