Embeddings are the A.I-native way to represent any kind of data, making them the perfect fit for working with all kinds of A.I-powered tools and algorithms. They can represent text, images, and soon audio and video. There are many options for creating embeddings, whether locally using an installed library, or by calling an API. Embeddings are a way to power semantic search. You run an ML model like [[MiniLM-L6-v2]] over some text and get back vectors. Then, you can use cosine similarity to index and lookup text based on semantic similarity. You might store your vectors in one of many [[Vector Databases]], though this seems like overkill for most usecases.