Skip to main content

Toolkit for Chat API

Project description

基于 OpenAI API 的 Chat 对象,支持多轮对话,代理,以及异步处理数据等。

安装方法

pip install chattool --upgrade

使用方法

设置密钥和代理链接

通过环境变量设置密钥和代理,比如在 ~/.bashrc 或者 ~/.zshrc 中追加

export OPENAI_API_KEY="sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
export OPENAI_API_BASE="https://api.example.com/v1"
export OPENAI_API_BASE_URL="https://api.example.com" # 可选

或者在代码中设置:

import chattool
chattool.api_key = "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
chattool.api_base = "https://api.example.com/v1"

注:环境变量 OPENAI_API_BASE 优先于 OPENAI_API_BASE_URL,二者选其一即可。

示例

示例1,多轮对话:

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

# 继续对话
chat.user("How are you?")
next_resp = chat.getresponse()

# 人为添加返回内容
chat.user("What's your name?")
chat.assistant("My name is GPT-3.5.")

# 保存对话内容
chat.save("chat.json", mode="w") # 默认为 "a"

# 打印对话历史
chat.print_log()

示例2,批量处理数据(串行),并使用缓存文件 chat.jsonl

# 编写处理函数
def data2chat(msg):
    chat = Chat()
    chat.system("你是一个熟练的数字翻译家。")
    chat.user(f"请将该数字翻译为罗马数字:{msg}")
    # 注意,在函数内获取返回
    chat.getresponse()
    return chat

checkpoint = "chat.jsonl" # 缓存文件的名称
msgs = ["1", "2", "3", "4", "5", "6", "7", "8", "9"]
# 处理数据,如果 checkpoint 存在,则从上次中断处继续
continue_chats = process_chats(msgs, data2chat, checkpoint)

示例3,批量处理数据(异步并行),用不同语言打印 hello,并使用两个协程:

from chattool import async_chat_completion, load_chats, Chat

langs = ["python", "java", "Julia", "C++"]
def data2chat(msg):
    chat = Chat()
    chat.user("请用语言 %s 打印 hello world" % msg)
    # 注意,这里不需要 getresponse 而交给异步处理
    return chat

async_chat_completion(langs, chkpoint="async_chat.jsonl", nproc=2, data2chat=data2chat)
chats = load_chats("async_chat.jsonl")

在 Jupyter Notebook 中运行,因其特殊机制,需使用 await 关键字和 wait=True 参数:

await async_chat_completion(langs, chkpoint="async_chat.jsonl", nproc=2, data2chat=data2chat, wait=True)

示例4,使用工具(自定义函数):

# 定义函数
def add(a: int, b: int) -> int:
    """
    This function adds two numbers.

    Parameters:
        a (int): The first number.
        b (int): The second number.

    Returns:
        int: The sum of the two numbers.
    """
    return a + b

def mult(a:int, b:int) -> int:
    """This function multiplies two numbers.
    It is a useful calculator!

    Args:
        a (int): The first number.
        b (int): The second number.

    Returns:
        int: The product of the two numbers.
    """
    return a * b
# 传输函数
chat = Chat("find the value of (23723 * 1322312 ) + 12312") # 传入函数列表,可以是多个函数
# 自动调用工具,默认使用 tool_choice
chat.autoresponse(display=True, tool_choice='tool_choice') # 或者用 function_call

开源协议

使用 MIT 协议开源。

更新日志

  • 当前版本 3.2.1,简化异步处理和串行处理的接口,更新子模块名称,避免冲突
  • 版本 2.3.0,支持调用外部工具,异步处理数据,以及模型微调功能
  • 版本 2.0.0 开始,更名为 chattool
  • 版本 1.0.0 开始,支持异步处理数据
  • 版本 0.6.0 开始,支持 function call 功能
  • 版本 0.5.0 开始,支持使用 process_chats 处理数据,借助 msg2chat 函数以及 checkpoint 文件
  • 版本 0.4.0 开始,工具维护转至 CubeNLP 组织账号
  • 版本 0.3.0 开始不依赖模块 openai.py ,而是直接使用 requests 发送请求
    • 支持对每个 Chat 使用不同 API 密钥
    • 支持使用代理链接
  • 版本 0.2.0 改用 Chat 类型作为中心交互对象

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

chattool-3.2.1.tar.gz (23.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

chattool-3.2.1-py3-none-any.whl (23.8 kB view details)

Uploaded Python 3

File details

Details for the file chattool-3.2.1.tar.gz.

File metadata

  • Download URL: chattool-3.2.1.tar.gz
  • Upload date:
  • Size: 23.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.8.18

File hashes

Hashes for chattool-3.2.1.tar.gz
Algorithm Hash digest
SHA256 aca1f0f1bfa3359ff312c1617fe34e0106b8b05a846d74be1e1a44683a1a7731
MD5 aaf5f96c5b2364e9ff3a05347bc01fba
BLAKE2b-256 5247beca91047d98cd9abd90ce814dc1e4c71322a6ecc6ec03b2a0bf3573ec1f

See more details on using hashes here.

File details

Details for the file chattool-3.2.1-py3-none-any.whl.

File metadata

  • Download URL: chattool-3.2.1-py3-none-any.whl
  • Upload date:
  • Size: 23.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.8.18

File hashes

Hashes for chattool-3.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 e30c192295fef0f698c2e2d87a35edbb130dcfc1644eb7449bda995e2a59d110
MD5 e8a04f4054808868616b2f4c6dea99ef
BLAKE2b-256 cc41a3226b60bfc77a50ac98f8e264bbf27b6bd687d21c14687a160400aff2b9

See more details on using hashes here.

Supported by

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