Your AI SaaS business, ready by this week!
Try demoYour AI SaaS business, ready by this week!
Try demoEmbeddings are lists of numbers that represent the meaning of a piece of text, so that texts with similar meaning end up close together and can be found by similarity search.
An embedding model reads a passage and returns a vector, often with hundreds or thousands of dimensions. "Refund policy" and "how do I get my money back" produce vectors that sit close together even though they share no words.
Comparing vectors, usually by cosine similarity, finds the passages most related to a question. That is semantic search, and it is the retrieval step of RAG.
Embeddings are cheap compared with chat models, but they must be recomputed if you switch embedding model, because vectors from different models are not comparable.
When users add files or links to an assistant or chatbot, Aikeedo splits them into chunks, embeds each chunk and stores the vectors for retrieval at answer time.
Discover more terms connected to this one
A vector database stores embeddings and finds the ones closest to a query vector quickly, which makes it the search engine behind RAG and semantic search.
RAG (retrieval-augmented generation) is a technique where relevant passages are first retrieved from a knowledge base and then given to an AI model with the question, so the answer is grounded in that content.
Semantic search finds results by meaning rather than exact keywords, by comparing embeddings of the query and the content.