This project provides an integrated customer service system powered by large language models, designed for businesses to automate customer interactions across multiple social media and e-commerce platforms. It targets businesses seeking to enhance customer support efficiency and personalize user experiences through AI-driven responses and knowledge base integration.

How It Works

The system leverages various LLM providers (GPT3.5/GPT4.0, FastGPT, DifyAI, Tongyi Qianwen, Wenxin Yiyan) to generate intelligent responses. It supports text, voice, and image inputs, and features a plugin system that allows interaction with the operating system and the internet. This architecture enables custom AI applications built upon proprietary knowledge bases, offering a flexible and extensible solution for diverse customer service needs.

Quick Start & Requirements

• Installation: Primarily via GitHub or Gitee.
• Prerequisites: Access to LLM APIs (e.g., OpenAI API key), potentially specific platform API credentials.
• Documentation: GitHub, Gitee, Usage Instructions.

Highlighted Details

• Extensive platform support including WeChat, Douyin, Xiaohongshu, Zhihu, Pinduoduo, and more.
• Handles multimodal inputs: text, voice, and images.
• Plugin system for OS and internet access, enabling advanced functionalities.
• Customizable knowledge base for tailored AI assistants and digital personas.

Maintenance & Community

• Active development with a public roadmap outlining planned features and improvements.
• Community engagement encouraged via GitHub Issues and a WeChat assistant for support.

Licensing & Compatibility

• AGPL-3.0 license.
• Permits personal use; commercial use requires contacting the author for licensing. Modifications or usage of the code must be open-sourced under AGPL-3.0 unless commercial authorization is obtained.

Limitations & Caveats

The AGPL-3.0 license imposes strong copyleft requirements, mandating that any derivative works or systems incorporating this code must also be open-sourced under the same license, which may restrict commercial adoption in closed-source environments.