Hybrid and Semantic Search

This is the core retrieval stack behind modern applications that answer questions using your documents. You will learn to combine two different ways of finding relevant information: checking for exact words and checking for similar meaning. By the end, you will understand why professional systems rarely use just one of these methods, and how to build a search engine that handles both 'page 3 of the refund policy' and 'what happens if I cancel my subscription?' with equal skill. This foundation is necessary before you move on to later topics like refining search results or breaking documents into smaller pieces for better understanding.

Imagine you are an archivist in a vast library. A researcher asks you: 'Find me everything about the 2016 election results.' You have two very different tools at your disposal. The first is an exact index: a card catalogue that lists every mention of the phrase '2016 election results' verbatim. This is fast and precise — you find the documents that literally contain those words. But if the researcher actually means 'the outcome of the presidential race in 2016' or 'who won in November 2016', the card catalogue is useless because it only matches exact strings. That is word-based search. The second tool is a semantic map: every document is a point on a map, and similar documents cluster together. You find the documents closest to your query's point, even if they don't share a single word with your question. That is meaning-based vector similarity — it finds things with similar meanings. The problem: the card catalogue misses paraphrases, and the semantic map can be confused by rare or specific terms like 'EIN-84-2093' (an ID code) which get blurred into an average position on the map. Hybrid search uses both tools at once, combines their scores, and returns a ranked list that is better than either alone. In practice, this means a search that understands meaning AND respects exact terms.

Think of a restaurant that has two ways of finding a dish on its menu. The first is the index at the back of the menu — it lists every page number where the word 'chicken' appears. If you look up 'chicken', you get page 2 and 5. That's word-based search: fast, exact, but if you ask for 'poultry' instead, the index finds nothing. The second way is the chef's mental map of ingredients — he knows that 'poultry', 'chicken', 'bird', and 'fowl' all point to the same section of the kitchen, because they are related in meaning. That's meaning-based vector similarity: it understands synonyms and concepts, but if a customer asks for a specific dish code like 'TN-12' (a special number in the menu), the chef's mental map doesn't know what that means, because it's not a concept — it's just a string. Hybrid search is a waiter who does both: she looks up the exact code in the index, and also asks the chef for 'something like this dish' based on its meaning. She combines the two lists, gives higher rank to dishes that appear in both, and presents the best matches to the customer. The analogy breaks down when we think about the combination step: in the restaurant, the waiter just uses her judgment. In hybrid search, we need a mathematical way to merge two scores — a weighted sum. The waiter could, for instance, trust the exact index 70% and the chef's suggestion 30%. That's score fusion (simply combining scores): decide how much to trust each source, add them up, and sort by the total.

Hybrid search is a retrieval method that combines word-based keyword matching with meaning-based vector similarity to produce a ranked list of documents, typically by calculating a combined score from both methods.

This concept sits beside vector search, which finds documents closest to a query's numeric representation, and reranking, which refines an initial set of results using more detailed analysis. While vector search handles the meaning aspect, hybrid search adds word-based matching on top of it.