Embedding
An embedding is a list of numbers representing a piece of text’s meaning, so that texts with similar meanings sit close together in that numeric space.
Embeddings are what make semantic search possible: a query about "car insurance" can retrieve a document about "vehicle cover" without sharing any keywords. They encode meaning, not truth, so a confidently wrong document embeds just as well as a correct one.
Related terms
- RAG (retrieval-augmented generation)
- RAG is a technique that retrieves relevant documents from an external store and places them in the prompt, so the model answers from that material rather than from memory.
- Vector database
- A vector database is a store designed to hold embeddings and find the ones most similar to a query embedding quickly.
- Chunking
- Chunking is splitting documents into smaller passages before embedding them, so retrieval returns a relevant section rather than an entire file.
More on retrieval and agents
See the full glossary, read the guides, or put it into practice in the prompt builder.