gpru 0.2.0

Unofficial Python client library for the OpenAI and Azure OpenAI APIs

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

PyPI

CI/CD

Build System

Code

Docstrings

---

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 (
    ChatCompletionModel,
    ChatCompletionRequest,
    OpenAiApi,
    UserMessage,
)

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

req = ChatCompletionRequest(
    model=ChatCompletionModel.GPT_35_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?