Embeddings
Also called Vector embeddings, Text embeddings
Embeddings 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.
Example
"How do I get my money back?" and "What is your refund policy?" produce embeddings that sit close together, while "What are your opening hours?" lands far away from both.
Why it matters for a website chatbot
Embeddings let a chatbot find the right passage when a visitor's wording doesn't match yours. ChatBento creates embeddings for every passage of your content with bge-m3, a multilingual model, so a question in Spanish can still match an answer written in English.
See it in practice: Multilingual visitors
Related terms
- Vector searchVector 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.
- 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.
- 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.
- Large language model (LLM)A large language model (LLM) is an AI model trained on very large amounts of text to predict and generate language. It can answer questions, summarize, translate and write. Its general knowledge comes from training data with a cutoff date, so it needs supplied documents to answer accurately about a specific business.