Guide to the terminology used in Relevance AI

VectorsAKA embeddings, 1D arrays, latent space vectors
Vectorizers/models/EncodersTurns data into vectors (e.g. Word2Vec turns words into vectors)
Vector Similarity SearchNearest neighbor search, distance search
DatasetIndex, Table (a dataset is made up of multiple documents)
Documents(AKA JSON, item, dictionary, data row) - a document can contain vectors and other important information (e.g. the shown example above)
FieldA field is a key in a Python dictionary (e.g. product_title or product_description_vector_ in the example document above)
ValueA value is a value in a Python dictionary (e.g. 711158459 or [0.01, 0.23, 0.45, 0.67, 0.89, 0.1, 0.12] in the example document above)
Upload(AKA index a dataset) is the process of uploading a dataset to Relevance AI platform

Did this page help you?