`text-embedding-ada-002`

[ruby_coder]

More discussion and testing here:

Some questions about text-embedding-ada-002’s embedding

We want to use the embedding generated by the text-embedding-ada-002 model for some search operations in our business, but we encountered a problem when using it. Here are two texts. text1: I need to solve the problem with money text2: Anything you would like to share? following is the code: emb = openai.Embedding.create(input=[text1,text2], engine=model,request_timeout =3) emb1 = np.asarray(emb.data[0]["embedding”]) emb2 = np.asarray(emb.data[1]["embedding”]) def cosine_similarity(a, b): …