Documentation

Everything you need to deploy, configure, and customize GoLiveChat.

Quick Start

Three steps to get GoLiveChat running. MySQL is the only external dependency.

Step 1: Configure MySQL

Edit config/mysql.json and set your MySQL host, port, user, password, and database name.

Step 2: Install & Import Database

./golivechat install

This command creates all required tables and populates initial data automatically.

Step 3: Start the Server

./golivechat server

Your live chat platform is now running. Access the admin panel at http://localhost:8080/main.

System Requirements

CPU1 core minimum, 2+ recommended
RAM2 GB minimum
DatabaseMySQL 8.0+
OSLinux, macOS, Windows

Embed the Chat Widget

After deployment, add this to your website:

<script type='text/javascript'>
  (function(a,b,c,d){
    let h=b.getElementsByTagName('head')[0];
    let s=b.createElement('script');
    s.type='text/javascript';
    s.src=c+"/static/js/kefu-front.js";
    s.onload=function(){d(c);};
    h.appendChild(s);
  })(window,document,"https://your-domain.com",function(u){
    KEFU.init({
      KEFU_URL:u,
      KEFU_KEFU_ID:"your-agent-id",
      KEFU_ENT:"your-tenant-id"
    });
  });
</script>

Configure AI

GoLiveChat supports multiple AI backends. Set your API key in the admin settings panel:

OpenAIGPT-3.5, GPT-4, GPT-4o — standard & Azure endpoints
CozeMulti-model agent platform (Doubao, Kimi, Qwen, GLM-4)
DifyOpen-source AI platform — self-hosted or cloud
FastGPTKnowledge-base Q&A with your documents

Configure RAG Knowledge Base

To enable document-based AI answers:

  1. Start Qdrant vector database (docker-compose up qdrant)
  2. Go to Admin → Knowledge Base → Upload Documents
  3. Upload PDF, Word, Excel, or TXT files
  4. Documents are automatically chunked, embedded, and indexed
  5. When visitors ask questions, the system retrieves relevant context before the AI responds