Welcome to wechat-gptbot 👋

A wechat robot based on ChatGPT with no risk, very stable! 🚀
English | 中文文档

🎤 Introduction

When I use bots based on itchat and wechaty, I often encounter the risk of account restrictions when scanning codes to log in. Refer to #158. Is there a safe way to use wechat bots? Here it is~

🌟 Features

Extremely Stable： Implement based on windows hook, no worry about risk of wechat account restriction
Basic Conversation： Smart reply for private chat and group chat, support multiple rounds of session context memory, support GPT-3, GPT-3.5, GPT-4 models
Image Generation： Support image generation, Dell-E only model for now
Flexible Configuration： Support prompt settings, proxy, command settings and etc.

🚀 Getting Start

Environment

Support Windows system(probably support Linux in the future based on sandbox) and Python needs to be installed at the same time

It is recommended that the Python version be between 3.8.X~3.10.X, version 3.10 is perfect

1. Clone repo

git clone https://github.com/iuiaoin/wechat-gptbot && cd wechat-gptbot

2. Install dependencies

pip install -r requirements.txt

Configuration

config.template.json in the root directory contains the configs template, you need to copy the template to create the final effective config.json

  cp config.template.json config.json

Then fill in the configuration in config.json, the following is the description of the default configuration, which can be customized according to the needs:

{
  "openai_api_key": "YOUR API SECRET KEY",             # Fill in your OpenAI API Key
  "model": "gpt-3.5-turbo",                            # ID of the model to use, support gpt-3.5-turbo, gpt-4, gpt-4-32k etc.
  "role_desc": "You are a helpful assistant.",         # Role description as system prompt
  "session_expired_duration": 3600,                    # Session memory kept duration
  "max_tokens": 1000,                                  # Max tokens of characters for session memory
  "temperature": 0.9,                                  # Between 0 and 2. Higher values make the output more random, while lower values more focused
  "proxy": "127.0.0.1:3000",                           # Proxy client ip and port
  "openai_api_base": "",                               # api url used by openai service
  "create_image_prefix": ["draw", "paint", "imagine"], # Text prefix for image generation
  "clear_current_session_command": "#clear session",   # Clear current session
  "clear_all_sessions_command": "#clear all sessions", # Clear all sessions
  "chat_group_session_independent": false,             # Whether sessions of users are independent in chat group
  "single_chat_prefix": ["bot", "@bot"],               # Start conversation with "bot" or "@bot" in single chat to trigger the bot, leave it empty if you wanna make the bot active all the time
  "query_key_command": "#query key"                    # Querying the usage of the api key
  "recent_days": 5                                     # The usage in <recent_days> days
}

Running

1. Prepare

We need the specific wechat version and dll to make windows hook work.

Download assets from the release
Install WeChatSetup-3.2.1.121.exe and login
Run the wechat-dll-injectorV1.0.3.exe
Select 3.2.1.121-LTS.dll and click inject dll, you will see "Successfully injected: 3.2.1.121-LTS.dll"

2. Run command

python app.py

Voilà! Enjoy your exploring journey~

✨ Contributor

🤝 Contributing

Contributions, issues and feature requests are welcome!
Feel free to check issues page.

🙏 Show your support

Give a ⭐️ if you like this project!

📢 Announcements

The WeChatSetup is coming from wechat-windows-versions and wechat-dll-injector from wechat-bot, so you can use it without concern. Also thanks the two repo's owners for their contributions.

bingghost / wechat-gptbot