Skip to main content

Unofficial Python client library for the OpenAI and Azure OpenAI APIs

Project description

GPRU: Unofficial Python Client Library for the OpenAI and Azure OpenAI APIs

PyPI PyPI - Version PyPI - Python Version License

CI/CD test lint

Build System Hatch project

Code pre-commit Code style: black Imports: isort Checked with mypy Ruff

Docstrings docformatter numpy


GPRU is an unofficial Python client library for the OpenAI and Azure OpenAI APIs with improved usability through comprehensive annotations.

WARNING: GPRU is currently under development and any destructive changes may be made until version 1.0.0.

Installation

pip install gpru

Examples

OpenAI API

Notes Before anything else, you must ensure that the API key is set as an environment variable named OPENAI_API_KEY.

Here is an example of chat completion, also known as ChatGPT.

import os

from gpru.openai.api import ChatCompletionRequest, OpenAiApi, UserMessage

key = os.environ["OPENAI_API_KEY"]
api = OpenAiApi(key)

req = ChatCompletionRequest(model="gpt-3.5-turbo", messages=[UserMessage("Hello!")])
chat_completion = api.create_chat_completion(req)
print(chat_completion.content)
# Greetings! How can I assist you today?

Azure OpenAI API

The following code replaces the same example with the Azure OpenAI API.

Notes Set the following environment variables before executing the program.

Variable name Value
AZURE_OPENAI_API_ENDPOINT URL in the form of https://{your-resource-name}.openai.azure.com/.
AZURE_OPENAI_API_KEY Secret key.
AZURE_OPENAI_API_DEPLOYMENT_ID Custom name you chose for your deployment when you deployed a model.
import os

from gpru.azure.preview_2023_06_01 import (
    AzureOpenAiApi,
    ChatCompletionRequest,
    UserMessage,
)

endpoint = os.environ["AZURE_OPENAI_API_ENDPOINT"]
key = os.environ["AZURE_OPENAI_API_KEY"]
deployment_id = os.environ["AZURE_OPENAI_API_DEPLOYMENT_ID"]
api = AzureOpenAiApi(endpoint, key)

req = ChatCompletionRequest(messages=[UserMessage("Hello!")])
chat_completion = api.create_chat_completion(deployment_id, req)
print(chat_completion.content)
# Greetings! How can I assist you today?

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gpru-0.1.0.tar.gz (75.5 kB view details)

Uploaded Source

Built Distribution

gpru-0.1.0-py3-none-any.whl (83.1 kB view details)

Uploaded Python 3

File details

Details for the file gpru-0.1.0.tar.gz.

File metadata

  • Download URL: gpru-0.1.0.tar.gz
  • Upload date:
  • Size: 75.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: python-httpx/0.24.1

File hashes

Hashes for gpru-0.1.0.tar.gz
Algorithm Hash digest
SHA256 e64543ae3e3ef073243a5879c06f93e80e78e45aa7c552642c7f650bc4154e16
MD5 516e42168ae71bbbb8f95228490c14ca
BLAKE2b-256 f4c0b8d22566179fa0b7ff06b4942451355348524ecf48b5ba95f6fe5d1c314f

See more details on using hashes here.

File details

Details for the file gpru-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: gpru-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 83.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: python-httpx/0.24.1

File hashes

Hashes for gpru-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f2f65615fd12b64efa5b13f9118ca4c6377f84d2f14dd14c1a5d87121d0668cb
MD5 3715c8b64632f0b66b9f7c9d269a0bf9
BLAKE2b-256 ce3395797047a5a45a27ba76a1c415bb1edc9920b1aaf8225649dd9aee74c6b8

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page