Semantic Search: Vector Databases and Embeddings Explained

Imagine you could turn any word into a set of coordinates on a map. Not a geographical map,a meaning map. That's essentially what embeddings are.

Let's start with a simple example. Take the word "King". An embedding model reads that word and outputs a long list of numbers,say, 1,536 of them. Each number captures a different shade of meaning: royalty, power, authority, and hundreds of other subtle dimensions that humans would struggle to articulate.

Now take the word "Queen". It gets its own list of 1,536 numbers. Here's where it gets interesting: those numbers are almost identical to King's, except in the dimensions related to gender. The model has learned, purely from reading text, that a Queen is essentially a King shifted along a gender axis. This is the famous equation that made embeddings click for the AI world: King − Man + Woman ≈ Queen. That's not a metaphor. You can literally do that arithmetic on the number arrays and land near Queen's embedding. The model didn't learn a rule about royalty or gender,it learned the shape of meaning itself.

And it doesn't stop at single words. Modern embedding models can take entire sentences, paragraphs or documents and compress their meaning into that same format: a list of numbers that captures what it's about.

So now you have thousands, maybe millions, of these number arrays. Each one represents a piece of content: a product description, a support ticket, a medical record, a song lyric. You need somewhere to store them, and more importantly, you need to search them fast. A regular database is built for exact matches. Ask it for "Queen" and it finds rows where a column literally says "Queen". It has no idea that "female monarch" means the same thing.

A vector database stores those embedding arrays (called vectors) and is purpose-built for a completely different question: "What's closest to this?" Think back to our meaning map. If you plotted King, Queen, Prince and Princess as dots, they'd form a tight cluster. The word "Bicycle" would be way off in the distance. A vector database lets you point at any spot on that map and instantly find the nearest neighbours, even across millions of points.

Popular vector databases include Pinecone, Weaviate, ChromaDB and pgvector (a PostgreSQL extension often used with Supabase). They use clever indexing algorithms so that finding the nearest neighbours among 100 million vectors takes milliseconds, not hours.

Traditional keyword search is fragile. If a customer searches your help centre for "my payment didn't go through", a keyword engine only finds articles containing those exact words. An article titled "Troubleshooting Failed Transactions" might never surface, even though it's exactly what they need.

Semantic search fixes this in three steps. First, embed your content: take every article, product listing, or document and pass it through an embedding model, then store the resulting vectors in a vector database. Second, embed the query: when a user searches, that sentence gets its own embedding, a point on the meaning map. Third, find the nearest neighbours: the vector database returns the content whose embeddings are closest to the query's embedding. Because "payment didn't go through" and "failed transaction" land in nearly the same spot on the meaning map, the right article surfaces. No keyword overlap required.

The practical applications are wide. In search, Airbnb reported a 12% increase in booking conversion after switching to embedding-based search. Organisations using semantic search for internal documentation typically see 30–50% reduction in time-to-answer. In clustering, support teams have reduced manual triage time by up to 60%. In recommendations, Spotify's embedding engine drives over 30% of all listening hours through Discover Weekly. In anomaly detection, financial institutions report catching up to 30% more fraudulent transactions while reducing false positives by 25%. In classification, zero-shot approaches using embeddings achieve 80–90% accuracy with no task-specific training data at all.

The mental model is simple: embeddings turn meaning into math. Vector databases make that math searchable at scale. Semantic search is the user-facing result. Once that clicks, every application,clustering, recommendations, anomaly detection, classification, diversity measurement,is just a different question you ask of the same underlying geometry.

Start small. Embed a hundred documents. Search them. The moment you see a query with zero keyword overlap return the perfect result, you'll understand why this matters.