openai-async 0.0.1

No project description provided

openai-async

An asynchronous client for openai services - completion, image generation and embeddings.

For the full documentation, go to the openAI website.

Installation

pip install openai-async

Use

Text completion

import openai_async

response = await openai_async.complete(
    "<API KEY>",
    timeout=2,
    payload={
        "model": "text-davinci-003",
        "prompt": "Correct this sentence: Me like you.",
        "temperature": 0.7,
    },
)
print(response.json()["choices"][0]["text"].strip())
>>> "I like you."

Visit the official documentation for more info.

Image generation

import openai_async
import urllib.request
from PIL import Image

response = await openai_async.generate_img(
    "<API KEY>",
    timeout=8,
    payload={
        "prompt": "a white siamese cat",
        "n": 1,
        "size": "512x512"
    },
)
urllib.request.urlretrieve(response.json()["data"][0]["url"], "img.png")
Image.open("img.png").show()

Visit the official documentation for more info: https://beta.openai.com/docs/api-reference/images/create

Embeddings

import openai_async

response = await openai_async.embeddings(
    <API_KEY>,
    timeout=2,
    payload={"model": "text-embedding-ada-002", "input": "a cat"},
)
print(response.json()["data"][0]["embedding"])
>>> [-0.019408401,
-0.009246278,
-0.014390069,
-0.012294915,
-0.0025609178,
0.021252638,
...]

Visit the official documentation for more info.

Get an API key

To generate an openAI API key, while in the openAI website, click on your username in the top right corner, then go to "View API keys" and create a key.

Disclaimer

This repository has no connection whatsoever to openAI.