Vector search
Also called Semantic search, Vector database
Vector search finds items whose embeddings are closest to the embedding of a query, so results match by meaning rather than by exact words. The embeddings are stored in a vector index or vector database built to find the nearest matches quickly, even across millions of items.
Example
A search for "laptop won't turn on" returns an article titled "Troubleshooting power problems" even though the two share no keywords.
Why it matters for a website chatbot
Keyword search fails when visitors use different words than your docs. Vector search is how a chatbot finds the right paragraph anyway. ChatBento stores your content's embeddings in a vector index and pulls the closest passages for each question before writing an answer.
See it in practice: Docs and help-center search
Related terms
- EmbeddingsEmbeddings are lists of numbers that represent the meaning of a piece of text, image or other data, produced by a machine-learning model. Texts with similar meanings get similar numbers, even when they share no words, which lets software compare meaning mathematically for search, recommendations and grouping.
- Retrieval-augmented generation (RAG)Retrieval-augmented generation (RAG) is a technique in which an AI system first retrieves relevant passages from a chosen set of documents, then gives them to a language model to write its answer. It lets the model answer from current, specific information it was never trained on, and makes answers easier to check.
- Help centerA help center is a section of a website, or a separate site, that collects support articles, guides and answers to common questions, usually organized by topic and searchable. Customers use it to solve problems themselves, and support teams link to its articles when replying, so the same answers stay consistent.
- ChunkingChunking is splitting long documents into smaller passages, or chunks, before creating embeddings for retrieval. Chunks need to be small enough to match specific questions and fit in a model's context window, but large enough to keep their meaning. Many systems overlap neighboring chunks slightly so sentences aren't cut off.