Embeddings
Numeric vector representations of text (or other data) that capture meaning, so that similar content sits close together in vector space.
An embedding is a list of numbers (a vector) that represents the meaning of a piece of text. Texts with similar meaning produce vectors that are close together, which is what makes semantic search possible.
In an audio knowledge base, each transcript chunk is converted into an
embedding and stored in a vector database. You can generate
embeddings locally (for example via Ollama with nomic-embed-text) to keep everything
on-prem, or call a hosted embedding model.