hicdl/chatgpt-stream

Real-time ChatGPT service, support GPT3/GPT4, support conversation and generate pictures from sentences, this is frontend

Real-time ChatGPT service, support GPT3/GPT4, support conversation and generate pictures from sentences

• English README
• 中文 README

About chatgpt-service and chatgpt-stream

• chatgpt-service: https://github.com/hicdl/chatgpt-service
  • chatgpt-service is a backend service, used to receive chatGPT messages in real time, and feed back to chatGPT-stream in real time through websocket
• chatgpt-stream: https://github.com/hicdl/chatgpt-stream
  • chatgpt-stream is a front-end service that receives messages returned by chatGPT-service in real time through websocket

gitee

• https://gitee.com/hicdl/chatgpt-service
• https://gitee.com/hicdl/chatgpt-stream

Demo

• Real-time conversation mode

• Generate picture patterns from sentences

Quick start

# Pull source code
git clone https://github.com/hicdl/chatgpt-service.git
cd chatgpt-service

# ChatGPT's registration page: https://beta.openai.com/signup
# ChatGPT registration tutorial: https://www.cnblogs.com/damugua/p/16969508.html
# ChatGPT API key management page: https://beta.openai.com/account/api-keys

# Modify the config.yaml configuration file, modify the apiKey, and change it to your openai.com API key
vi config.yaml
#  your openai.com API key
apiKey: "xxxxxx"

# create pictures directory
mkdir -p assets
chown -R 1000:1000 assets

# Start the service with docker-compose
docker-compose up -d

# Check service status
docker-compose ps   
     Name                    Command               State                  Ports                
-----------------------------------------------------------------------------------------------
chatgpt-service   /chatgpt-service/chatgpt-s ...   Up      0.0.0.0:59142->9000/tcp             
chatgpt-stream    /docker-entrypoint.sh ngin ...   Up      0.0.0.0:3000->80/tcp,:::3000->80/tcp


# To access the page, please ensure that your server can access the chatGPT API
# http://localhost:3000

• Enter the question directly, it will call the ChatGPT interface to return the answer
• Enter the picture description after /image, it will call the DALL-E2 interface to automatically generate pictures through the picture description

How to build

# Note that this project needs to run the chatgpt-service backend service first
# .env.development is the configuration file for running tests
# .env.production is the formally built configuration file

# Pull build dependencies
npm install
# Test the project
npm run serve
# Compile the project
npm run build

# If ERR_OSSL_EVP_UNSUPPORTED error occurs, please use the following command to compile
export NODE_OPTIONS=--openssl-legacy-provider && npm run build