Retrieval role of the texts: 'query' for search text, 'document' (the default) for text
that is stored and compared. Asymmetric models embed the two differently, so embed a search
box's text as a query and the items it is compared with as documents.
(Mirrors EmbeddingInputType in @memberjunction/ai, which this package doesn't depend on.)
modelSize
modelSize:"medium"|"small"
textToEmbed
textToEmbed:string|string[]
Either a single string or an array of strings to calculate embeddings for
Retrieval role of the texts:
'query'for search text,'document'(the default) for text that is stored and compared. Asymmetric models embed the two differently, so embed a search box's text as a query and the items it is compared with as documents. (MirrorsEmbeddingInputTypein@memberjunction/ai, which this package doesn't depend on.)