Embeddings, an embedding model, and a vector database are enough to build a working demo. But once you try that demo on real documents, the results are often disappointing, not something you would confidently ship in a 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 understands the general topic, but misses the user’s actual intent.

Building a search system that consistently returns precise, trustworthy results is hard. The gap between the two is huge, and closing it requires techniques like better chunking, hybrid retrieval, and re-ranking.

That is what this chapter is about.