Text Embeddings Implementation

Text embedding models are translators for machines. They convert text, such as sentences or paragraphs, into sets of numbers, which the machine can easily use in complex calculations.

Preternatural currently supports only OpenAI’s Text Embedding models:

let smallTextEmbeddingsModel = OpenAI.Model.embedding(.text_embedding_3_small)
let largeTextEmbeddingsModel = OpenAI.Model.embedding(.text_embedding_3_large)
let adaTextEmbeddingsModel = OpenAI.Model.embedding(.text_embedding_ada_002)

To create an embedding, simply pass an array of text to the client:

let textInput = "Hello, Text Embeddings!"
 
let textEmbeddingsModel = OpenAI.Model.embedding(.text_embedding_3_small)
 
let embeddings = try await client.textEmbeddings(
    for: [textInput],
    model: textEmbeddingsModel)
    
return embeddings.data.first?.embedding.description

If you are sending an array of text to be processed as text embeddings, note that the embeddings are returned in the order of the initial text array. So the first text value is equivalent to the first embedding in the result and so on.