Get GPT3 Embeddings

import openai
import numpy as np

openai.api_key = "XXX-YOUkey"

from tenacity import retry, wait_random_exponential, stop_after_attempt

@retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))
def get_embedding(text, engine="davinci-similarity"):

    # replace newlines, which can negatively affect performance.
    text = text.replace("\n", " ")

    return openai.Engine(id=engine).embeddings(input = [text])['data'][0]['embedding']

df_news['babbage_similarity'] = df_news.Text.apply(lambda x: get_embedding(x, engine='babbage-similarity'))
df_news.to_csv('output/embedded_newsgroups.csv')