On this page
AUTOMATION AND AI
Embeddings
Embeddings are lists of numbers produced by a model to represent the meaning of a piece of text, arranged so that passages with similar meaning have similar vectors. A chatbot's knowledge base stores an embedding for every chunk; a customer's question is embedded the same way and the nearest chunks are retrieved as context for the answer.
knowledge baseai agentintent
Why it matters
Embeddings are why a bot can match "do you open on Sunday" to a page that says "weekend hours" without a keyword in common. They also explain retrieval failures: a chunk that mixes several topics has a blurry vector and is retrieved for none of them, which is why chunk size and clean sources matter.
In VGraple CRM
Every knowledge base chunk is embedded when a source is added or refreshed and stored with the workspace; retrieval compares the question's embedding against them and returns the top five. This all happens server-side; the only decision left to you is what to put in the base and how to split it.