openai-api-call 1.0.0

A short wrapper of the OpenAI api call.

中文文档移步这里。

Openai API call

A Python wrapper for OpenAI API, supporting multi-turn dialogue, proxy, and asynchronous data processing.

Installation

pip install openai-api-call --upgrade

Usage

Set API Key and Base URL

Method 1, write in Python code:

import openai_api_call
openai_api_call.api_key = "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
openai_api_call.base_url = "https://api.example.com"

Method 2, set environment variables in ~/.bashrc or ~/.zshrc:

export OPENAI_API_KEY="sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
export OPENAI_BASE_URL="https://api.example.com"

Examples

Example 1, simulate multi-turn dialogue:

# first chat
chat = Chat("Hello, GPT-3.5!")
resp = chat.getresponse()

# continue the chat
chat.user("How are you?")
next_resp = chat.getresponse()

# add response manually
chat.user("What's your name?")
chat.assistant("My name is GPT-3.5.")

# save the chat history
chat.save("chat.json", mode="w") # default to "a"

# print the chat history
chat.print_log()

Example 2, process data in batch, and use a checkpoint file checkpoint:

# write a function to process the data
def msg2chat(msg):
    chat = Chat(api_key=api_key)
    chat.system("You are a helpful translator for numbers.")
    chat.user(f"Please translate the digit to Roman numerals: {msg}")
    chat.getresponse()

checkpoint = "chat.jsonl"
msgs = ["%d" % i for i in range(1, 10)]
# process the data
chats = process_chats(msgs[:5], msg2chat, checkpoint, clearfile=True)
# process the rest data, and read the cache from the last time
continue_chats = process_chats(msgs, msg2chat, checkpoint)

Example 3, process data in batch (asynchronous), print hello using different languages, and use two coroutines:

from openai_api_call import async_chat_completion

chatlogs = [
    {"role":"user", "content":"print hello using %s" % lang} 
    for lang in ["python", "java", "Julia", "C++"]]
async_chat_completion(chatlogs, chkpoint="async_chat.jsonl", ncoroutines=2)

License

This package is licensed under the MIT license. See the LICENSE file for more details.

update log

Current version 1.0.0 is a stable version, with the redundant feature function call removed, and the asynchronous data processing tool added.

Beta version

• Since version 0.2.0, Chat type is used to handle data
• Since version 0.3.0, you can use different API Key to send requests.
• Since version 0.4.0, this package is mantained by cubenlp.
• Since version 0.5.0, one can use process_chats to process the data, with a customized msg2chat function and a checkpoint file.
• Since version 0.6.0, the feature function call is added.