async-openai 0.0.1

Async Python client library for the OpenAI API

async-openai

Async Python client library for the OpenAI API based on Documented Specs

Features

• Asyncio based with Sync and Async Support

• Supports all API endpoints

  • Completions

  • Edits

  • Embeddings

• Handles Retries automatically

---

Installation

pip install async-openai

Quick Usage

import asyncio
from async_openai import OpenAI, settings

# Environment variables should pick up the defaults
# however, you can also set them explicitly.

settings.configure(
    api_key = "sk-XXXX",
    organization = "org-XXXX",
)

# [Sync] create a completion
# Results return a CompletionResult object
result = OpenAI.completions.create(
    prompt = 'say this is a test',
    max_tokens = 4,
    stream = True
)

# print the completion text
# which are concatenated together from the result['choices'][n]['text']

print(result.completion_text)

# print the number of choices returned
print(len(result))

# [Async] create a completion
# All async methods are generally prefixed with `async_`

result = asyncio.run(
    OpenAI.completions.async_create(
        prompt = 'say this is a test',
        max_tokens = 4,
        stream = True
    )
)

Alternative Usage

Following a similar pattern to the original openai python project, you can additionally use the methods as a drop-in replacement for most functions

import asyncio
import async_openapi as openai

# Environment variables should pick up the defaults
# however, you can also set them explicitly.

openai.settings.configure(
    api_key = "sk-XXXX",
    organization = "org-XXXX",
)

# [Sync] create a completion
# Results return a CompletionResult object
# Note, the only difference in this method is that the `Completion` is capitalized to match the OpenAI API

result = openai.Completions.create(
    prompt = 'say this is a test',
    max_tokens = 4,
    stream = True
)

# print the completion text
# which are concatenated together from the result['choices'][n]['text']

print(result.completion_text)

# print the number of choices returned
print(len(result))

# [Async] create a completion
result = asyncio.run(
    openai.Completions.async_create(
        prompt = 'say this is a test',
        max_tokens = 4,
        stream = True
    )
)

---

Dependencies

The aim of this library is to be as lightweight as possible. It is built on top of the following libraries:

• httpx: Async / Sync HTTP Requests

• pydantic: Type Support

• loguru: Logging

• file-io: Async Cloud-based File Storage I/O

• backoff: Retries with Exponential Backoff