openai_utils.py

import openai


def get_embedding(text, model="text-embedding-ada-002"):
    text = text.replace("\n", " ")
    return openai.Embedding.create(input=[text], model=model)["data"][0]["embedding"]


def get_embeddings(text_lists, model="text-embedding-ada-002"):
    res = openai.Embedding.create(input=text_lists, model=model)["data"]
    return [r["embedding"] for r in res]


def whisper_transcription(file_path) -> str:
    audio_file = open(file_path, "rb")

    result = openai.Audio.transcribe(
        model="whisper-1",
        file=audio_file,
    )
    return result["text"]