Build Real-Time ChatGPT Apps with chatGPT-service & chatGPT-stream: Quick Start Guide

chatGPT-service and chatGPT-stream

chatGPT-service: https://github.com/cookeem/chatgpt-service – a backend service that receives ChatGPT messages in real time and forwards them via WebSocket to chatGPT‑stream.

chatGPT-stream: https://github.com/cookeem/chatgpt-stream – a frontend service that receives messages from chatGPT‑service through WebSocket.

Gitee mirrors

https://gitee.com/cookeem/chatgpt-service

https://gitee.com/cookeem/chatgpt-stream

Quick start

# Clone repository
git clone https://github.com/chatgpt-service.git
cd chatgpt-service

# Register ChatGPT and obtain API key
# https://beta.openai.com/signup
# https://www.cnblogs.com/damugua/p/16969508.html
# https://beta.openai.com/account/api-keys

# Edit config.yaml and set your OpenAI appKey
vi config.yaml
appKey: "xxxxxx"

# Start services with Docker
docker-compose ps
# ... (output omitted)

# Access the frontend at http://localhost:3000

How to compile

# Install dependencies
go mod tidy
# Build the project
go build
# Run the binary
./chatgpt-service

# Test WebSocket endpoint
# ws://localhost:9000/api/ws/chat

# Install wscat
npm install -g wscat
# Connect and send queries
wscat --connect ws://localhost:9000/api/ws/chat

Sample article generated by ChatGPT‑Stream

# Write a 1000‑word introduction of an open‑source app named chat‑stream that uses the ChatGPT API, backend in Go, frontend in Vue, and WebSocket for real‑time messages.

Chat‑Stream is an open‑source chatbot built on the ChatGPT API, with a Go backend, Vue frontend, and WebSocket for real‑time message delivery. It supports multi‑language chat, voice recognition, history storage, and integration with social platforms such as Weibo and WeChat.