What is vector search?
Vector search finds content by meaning instead of exact words. Text is turned into lists of numbers, called embeddings, that place similar meanings close together, so a search for "can I send this back?" also finds a page titled "Refund policy".
Also called: semantic search, embedding search, similarity search.
By Santhul Joseph, AI EngineerUpdated
How vector search works
- Each passage of your content is turned into an embedding: a list of numbers that captures what it is about.
- The embeddings are stored in an index, often called a vector database.
- A customer's question is turned into an embedding the same way.
- The system returns the passages whose numbers are closest to the question's, which means closest in meaning.
Why it beats keyword search for support
Customers don't use your words. They type "how long until it arrives" when your page says "delivery times". Keyword search misses that, while vector search usually finds it, because it compares meaning rather than spelling.
It has one weak spot: it always returns the closest passage, even when none really answers the question. A good system checks whether the match is good enough before the model answers from it.
Vector search in SimplyBoost
You don't set any of this up. When you add website pages, files, snippets or Q&A pairs, SimplyBoost splits and indexes them so the agent can find them by meaning. Everything you add on any plan is searchable this way, with no limit on the number of files.
Questions people ask
What is an embedding?
An embedding is a list of numbers that represents the meaning of a piece of text. Texts with similar meanings get similar numbers, which lets a computer compare meaning.
Is vector search the same as RAG?
No. Vector search is the retrieval step, finding the right passages. Retrieval-augmented generation is the whole process: find those passages, then have a language model write an answer from them.
Do I need a vector database to run an AI chatbot?
Not if your tool handles it. In SimplyBoost you add your website or upload files, and the indexing and searching happen behind the scenes.